THIRUVENKATANATHAN PRADYUMNA (GB)
WO2016108914A1 | 2016-07-07 | |||
WO2018178279A1 | 2018-10-04 |
US20190277135A1 | 2019-09-12 | |||
US20200173273A1 | 2020-06-04 | |||
EP2020051817W | 2020-01-24 |
CLAIMS What is claimed is: 1. A method of identifying events within a wellbore, the method comprising: identifying one or more events within the wellbore; obtaining a first set of measurements comprising a first signal within the wellbore associated with the identified one or more event; training one or more event models using the second set of measurements and the identification of the one or more events as inputs; and using the one or more event models to identify at least one additional event. 2. The method of claim 1, further comprising: obtaining a second set of measurements comprising a second signal within a wellbore, wherein identifying the one or more events within the wellbore comprises identifying the one or more events within the wellbore using the second set of measurements, and wherein the first signal and the second signal represent different physical measurements. 3. The method of claim 1 or 2, wherein identifying the one or more events within the wellbore comprises using an identity of the one or more events based on a known event or induced event within the wellbore. 4. The method of claim 2 or 3, wherein the first set of measurements comprises acoustic measurements obtained within the wellbore. 5. The method of any one of claims 1-4, wherein the one or more events comprise a fluid inflow event a, a fluid outflow event, a fluid flow event within the wellbore, a fluid injection event, a fluid phase flow, a mixed phase flow, a leak event, a well integrity event, an, annular fluid flow event, an overburden event, a fluid induced hydraulic fracture event, sand detection event, or any combination thereof. 6. The method of any one of claims 2-5, wherein the second set of measurements comprise at least one of an acoustic sensor measurement, a temperature sensor measurement, a flow sensor measurement, a pressure sensor measurement, a strain sensor measurement, a position sensor measurement, a current meter measurement, a level sensor measurement, a phase sensor measurement, a composition sensor measurement, an optical sensor measurement, an image sensor measurement, or any combination thereof. 7. The method of any one of claims 1-6, further comprising: creating labeled data using the identified one or more events and the first set of measurements. 8. The method of any one of claims 1 -7, wherein the first set of measurements and the second set of measurements are obtained simultaneously. 9. The method of any one of claims 1 -8, wherein the first set of measurements and the second set of measurements are obtained at different time intervals. 10. The method of claim of any one of claims 2-9, wherein identifying the one or more events comprises: using the second set of measurements with one or more wellbore event models; and identifying the one or more events with the one or more wellbore event models. 11. The method of claim 10, further comprising: monitoring the first signal within the wellbore; monitoring the second signal within the wellbore; using the second signal in the one or more wellbore event models; using the first signal in the one or more event models; and detecting the at least one additional event based on outputs of both the one or more wellbore event models and the one or more event models. 12. The method of any one of claims 1-11, wherein the one or more event models are one or more pre-trained event models , and wherein training the one or more event models using the first set of measurements and the identification of the one or more events as inputs comprises: calibrating the one or more pre-trained event models using the first set of measurements and the identification of the one or more events as inputs; and updating at least one parameter of the one or more pre-trained event models in response to the calibrating. 13. The method of any one of claims 1-12, further comprising: obtaining a third set of measurements comprising a third signal within a wellbore, wherein the third signal and the first signal represent different physical measurements, and wherein the third set of measurements represent the at least one additional event; and training one or more additional event models using the third set of measurements and the identification of the at least one addition event as inputs. 14. The method of claim 13, wherein identifying the one or more events within the wellbore using the first set of measurements comprises: using the one or more additional event models to identify the one or more events within the wellbore, and wherein training the one or more additional event models using the third set of measurements and the identification of the at least one additional event as inputs comprises: retaining the one or more additional event models using the third set of measurements and the identification of the at least one additional event as inputs. 15. A system for identifying events within a wellbore, the system comprising: a memory; an identification program stored in the memory; and a processor, wherein the identification program, when executed on the processor, configures the process to: identify one or more events within the wellbore; receive a first set of measurements of a first signal within the wellbore; train one or more event models using the first set of measurements and the identification of the one or more events as inputs; and use the one or more event models to identify at least one additional event. 16. The system of claim 15, wherein the identification program further configures the processor to: receive a second set of measurements comprising a second signal, wherein the identification of the one or more events within the wellbore comprises an identification of the one or more events within the wellbore based on the second set of measurements, and wherein the first signal and the second signal represent different physical measurements. 17 The system of claim 15 or 16, wherein the identification of the one or more events within the wellbore comprises receiving an identity of the one or more events based on a known event or induced event within the wellbore. 18. The system of any one of claims 15-17, wherein the first set of measurements comprise acoustic measurements from the wellbore. 19. The system of any one of claims 15-18, wherein the one or more events comprise a fluid inflow event a, a fluid outflow event, a fluid flow event within the wellbore, a fluid injection event, a fluid phase flow, a mixed phase flow, a leak event, a well integrity event, an, annular fluid flow event, an overburden event, a fluid induced hydraulic fracture event, sand detection event, or any combination thereof. 20. The system of any one of claims 15-19, wherein the second set of measurements are received from at least one of an acoustic sensor, a temperature sensor, a flow sensor, a pressure sensor, a strain sensor, a position sensor, a current meter, a level sensor, a phase sensor, a composition sensor, an optical sensor, an image sensor, or any combination thereof. 21. The system of any one of claims 15-20, wherein the processor is further configured to: create labeled data using the identified one or more events and the first set of measurements. 22. The system of any one of claims 16-21, wherein the first set of measurements and the second set of measurements are from a same time interval. 23. The system of any one of claims 16-21, wherein the first set of measurements and the second set of measurements are from different time intervals. 24. The system of claim of any one of claims 16-23, wherein the processor is further configured to: use the second set of measurements with one or more wellbore event models; and identify the one or more events with the one or more wellbore event models. 25. The system of claim 24, wherein the processor is further configured to: monitor the first signal within the wellbore; monitor the second signal within the wellbore; use the second signal in the one or more wellbore event models; use the first signal in the one or more event models; and detect the one or more events based on outputs of both the one or more wellbore event models and the one or more event models. 26. The system of any one of claims 15-25, wherein the one or more event models are one or more pre-trained event models, and wherein the processor is further configured to: calibrate the one or more pre-trained event models using the first set of measurements and the identification of the one or more events as inputs; and update at least one parameter of the one or more pre-trained event models in response to the calibrating. 27. A method of identifying events within a wellbore, the method comprising: obtaining a first set of measurements of a first signal within a wellbore; identifying one or more events within the wellbore using the first set of measurements, wherein the one or more events comprise a gas phase inflow, a liquid phase inflow, or sand ingress into the wellbore; obtaining an acoustic data set from within the wellbore, wherein the first signal is not an acoustic signal; training one or more fluid inflow models using the acoustic data set and the identification of the one or more events as inputs; and using the trained one or more fluid inflow models to identify at least one additional fluid inflow event. 28. The method of claim 27, wherein the first set of measurements comprises distributed temperature sensor measurements. 29. The method of claim 27 or 28, wherein the first set of measurements comprise production volumetric information. 30. The method of any one of claims 27-29, wherein identifying the one or more events within the wellbore comprises: identifying a first location having a first event of the one or more events; and identifying the first event at the first location using one or more wellbore event models. 31. The method of claim 30, wherein training the one or more fluid inflow models comprises: obtaining acoustic data for the first location from the acoustic data set; and training the one or more fluid inflow models using the acoustic data for the first location and the identification of the first event at the first location. 32. The method of claim 31 , wherein using the trained one or more fluid inflow models to identify the at least one additional fluid inflow event within the wellbore comprises using the one or more trained fluid inflow models to identify the at least one additional fluid inflow event along the length of the wellbore. |
A = coefficient, ft " 1 C pL = specific heat of liquid, Btu/Ibm-°F C pm = specific heal of mixture, Btu/lbm-^F C po = specific heat of oil, Btti/ltet- e F C pw = specific heat of water, Bdi/Ibm-°F d c = casing diameter, in. d t = tubing diameter, in,
= wellbore diameter, in.
D = depth, ft Dinj = injection depth, ft f = modified dimensionless heat conduction time function for tong times for earth f (t) = dimensionless transient heat conduction time function for earth
F c = correction factor
F c = average correction factor for one length interval g = acceleration of gravity, 32.2 ft/sec 2 g c = conversion factor, 32.2 ft-lbm/secMbf g G = geothermal gradient, °F/ft A = specific enthalpy, Btu/lbm J = mechanical equivalent of heal, 778 ft-lbf/Btu k m = thermal conductivity of material in annulus, Bto/D-fi-°F k mg = thermal conductivity of gas in annulus, Btu/D-ft-°F k anw = thermal conductivity of water in annulus,
Btu/D-ft-T k cem = thermal conductivity of cement, Btu/D-ft-°F k e = thermal conductivity of earth, Btu/D-ft-°F L = length of well from perforations, ft
L m - = length from perforation to Met, ft p = pressure, psi
Pn h =* wellhead pressure, psig qg = formation gas flow rate, scf/D q ginj = injection gas flow rate, scf/D q o = oil flow rate, STB/D q w = water flow rate, STB/D Q = heat transfer between fluid and surrounding area, Btu/lbm r ci = inside casing radius, in. r co = outside casing radius, in. r ti = inside tubing radius, in. r to = outside tubing radius, in. r wb = wellbore radius, in.
R gL = gas/liquid ratio, scf/STB T = temperature, °F T bh = bottomhole temperature, °F T c = casing temperature, °F T g = surrounding earth temperature, °F T gjff = earth temperature at inlet, °F Tf = flowing fluid temperature, °F T fin = flowing fluid temperature at inlet, °F T h = cement/earth iaterface temperature, °F U = overall heat transfer coefficient, Bta/D*ft 2 -°F v = fluid velocity, ft/sec V = volume w, *= total mass flow rate, Ibm/sec Z = height from botom of hole, ft Z in = height from botom of hole at Met, ft α = thermal diffusivity of earth, 0.04 ft 2 /hr γAPI = oil gravity, °API γ g = gas specific gravity (ajr«l) γ o = oil specific gravity γ w = water specific gravity θ = angle of inclination, degrees μ = Joule-Thomson coefficient [0097] In some embodiments, the temperature features can comprise a heat loss parameter. As described hereinabove, Sagar’s model describes the relationship between various input parameters, including the mass rate w t and temperature change in depth dT f /d L . These parameters can be utilized as temperature features in a machine learning model which uses features from known cases (production logging results) as learning data sets, when available. These features can include geothermal temperature, deviation, dimensions of the tubulars 120 that are in the well (casing 112, tubing 120, gravel pack 122 components, etc.), as well as the wellbore 114, well head pressure, individual separator rates, downhole pressure, gas/liquid ratio, and/or a combination thereof. Such heat loss parameters can, for example, be utilized as inputs in a machine learning model for events comprising fluid flow quantification of the mass flow rate w t .
[0098] In some embodiments, the temperature features an comprise a time-depth derivative and/or a depth-time derivative. A temperature feature comprising a time-depth derivative can comprise a change in a temperature measurement at one or more locations across the wellbore taken first with respect to time, and a change in the resulting values with respect to depth can then be determined. Similarly, a temperature feature comprising a depth-time derivative can comprise a change in a temperature measurement at one or more locations across the wellbore taken first with respect to depth, and a change in the resulting values with respect to time can then be determined. [0099] In some embodiments, the temperature features can be based on dynamic temperature measurements rather than steady state or flowing temperature measurements. In order to obtain dynamic temperature measurements, a change in the operation of the system (e.g., wellbore) can be introduced, and the temperature monitored using the temperature monitoring system. For example in a wellbore environment, the change in conditions can be introduced by shutting in the wellbore, opening one or more sections of the wellbore to flow, introducing a fluid to the wellbore (e.g., injecting a fluid), and the like. When the wellbore is shut in from a flowing state, the temperature profile along the wellbore may be expected to change from the flowing profile to the baseline profile over time. Similarly, when a wellbore that is shut in is opened for flow, the temperature profile may change from a baseline profile to a flowing profile. Based on the change in the condition of the wellbore, the temperature measurements can change dynamically over time. In some embodiments, this approach can allow for a contrast in thermal conductivity to be determined between a location or interval having radial flow (e.g., into or out of the wellbore) to a location or interval without radial flow. One or more temperature features can then be determined using the dynamic temperature measurements. Once the temperature features are determined from the temperature measurements obtained from the temperature monitoring system, one or more of the temperature features can be used to identify events along the length being monitored (e.g., within the wellbore), as described in more detail herein.
[00100] As described with respect to the temperature measurements, the flow of fluids in the wellbore 114 an also create acoustic sounds that can be detected using the acoustic monitoring system such as a DAS system. Accordingly, the flow of the various fluids in the wellbore 114 and/or through the wellbore 114 can create vibrations or acoustic sounds that can be detected using acoustic monitoring system. Each type of fluid flow event such as the different fluid flows and fluid flow locations can produce an acoustic signature with unique frequency domain features. Other events such as leaks, overburden movements, equipment failures, and the like (e.g., any of the events described herein) can also create acoustic signals that can have a unique relationship between one or more frequency domain features.
[00101] As used herein, various frequency domain features can be obtained from the acoustic signal, and in some contexts, the frequency domain features can also be referred to herein as spectral features or spectral descriptors. The frequency domain features are features obtained from a frequency domain analysis of the acoustic signals obtained within the wellbore. The frequency domain features can be derived from the full spectrum of the frequency domain of the acoustic signal such that each of the frequency domain features can be representative of the frequency spectrum of the acoustic signal. Further, a plurality of different frequency domain features can be obtained from the same acoustic signal (e.g., the same acoustic signal at a location or depth within the wellbore), where each of the different frequency domain features is representative of frequencies across the same frequency spectrum of the acoustic signal as the other frequency domain features. For example, the frequency domain features (e.g., each frequency domain feature) can be a statistical shape measurement or spectral shape function of the spectral power measurement across the same frequency bandwidth of the acoustic signal. Further, as used herein, frequency domain features can also refer to features or feature sets derived from one or more frequency domain features, including combinations of features, mathematical modifications to the one or more frequency domain features, rates of change of the one or more frequency domain features, and the like. [00102] The frequency domain features can be determined by processing the acoustic signals from within the wellbore at one or more locations along the wellbore. As the acoustics signals at a given location along the wellbore contain a combination of acoustic signals, the determination of the frequency domain features can be used to separate and identify individual events. As an example, FIG. 3 illustrates sand 202 flowing from the formation 102 into the wellbore 114 and then into the tubular 120. As the sand 202 flows into the tubular 120, it can collide against the inner surface 204 of the tubular 120, and with the fiber 162 (e.g., in cases where the fiber 162 is placed within the tubular 120), in a random fashion. Without being limited by this or any particular theory, the intensity of the collisions depends on the effective mass and the rate of change in the velocity of the impinging sand particles 202, which can depend on a number of factors including, without limitation, the direction of travel of the sand 202 in the wellbore 114 and/or tubular 120. The resulting random impacts can produce a random, broadband acoustic signal that can be captured on the optical fiber 162 coupled (e.g., strapped) to the tubular 120. The random excitation response tends to have a broadband acoustic signal with excitation frequencies extending up to the high frequency bands, for example, up to and beyond about 5 kHz depending on the size of the sand particles 202. In general, larger particle sizes may produce higher frequencies. The intensity of the acoustic signal may be proportional to the concentration of sand 202 generating the excitations such that an increased broad band power intensity can be expected at increasing sand 202 concentrations. In some embodiments, the resulting broadband acoustic signals that can be identified can include frequencies in the range of about 5 Hz to about 10 kHz, frequencies in the range of about 5 Hz to about 5 kHz or about 50 Hz to about 5 kHz, or frequencies in the range of about 500 Hz to about 5 kHz. Any frequency ranges between the lower frequencies values (e.g., 5 Hz, 50 Hz, 500 Hz, etc.) and the upper frequency values (e.g., 10 kHz, 7 kHz, 5 kHz, etc.) can be used to define the frequency range for a broadband acoustic signal.
[00103] In addition to the sand entering the wellbore, fluid flow at the location can also create acoustic signals along with fluid flowing axially or longitudinally through the wellbore. Background noise can also be present. Other acoustic signal sources can include fluid flow with or without sand 202 through the formation 102, fluid flow with or without sand 202 through a gravel pack 122, fluid flow with or without sand 202 within or through the tubular 120 and/or sand screen 118, fluid flow with sand 202 within or through the tubular 120 and/or sand screen 118, fluid flow without sand 202 into the tubular 120 and/or sand screen 118, gas / liquid flow, hydraulic fracturing, fluid leaks past restrictions (e.g., gas leaks, liquid leaks, etc.) mechanical instrumentation and geophysical acoustic noises and potential point reflection noise within the fiber caused by cracks in the fiber optic cable / conduit under investigation. The combined acoustic signal can then be detected by the acoustic monitoring system. In order to detect one or more of these events, the acoustic signal can be processed to determine one or more frequency domain features of the acoustic signal at a depth in the wellbore.
[00104] In order to determine the frequency domain features, an acoustic signal can be obtained using the acoustic monitoring system during operation of the wellbore. The resulting acoustic signal can be optionally pre-processed using a number of steps. Depending on the type of DAS system employed, the optical data may or may not be phase coherent and may be pre- processed to improve the signal quality (e.g., denoised for opto-electronic noise normalization / de-trending single point-reflection noise removal through the use of median fdtering techniques or even through the use of spatial moving average computations with averaging windows set to the spatial resolution of the acquisition unit, etc.). The raw optical data from the acoustic sensor can be received, processed, and generated by the sensor to produce the acoustic signal.
[00105] In some embodiments, a processor or collection of processors (e.g., processor 168 in FIG. 3) may be utilized to perform the optional pre-processing steps described herein. In an embodiment, the noise detrended “acoustic variant” data can be subjected to an optional spatial filtering step following the other pre-processing steps, if present. A spatial sample point fdter can be applied that uses a fdter to obtain a portion of the acoustic signal corresponding to a desired depth or depth range in the wellbore. Since the time the light pulse sent into the optical fiber returns as backscattered light can correspond to the travel distance, and therefore depth in the wellbore, the acoustic data can be processed to obtain a sample indicative of the desired depth or depth range. This may allow a specific location within the wellbore to be isolated for further analysis. The pre-processing may also include removal of spurious back reflection type noises at specific depths through spatial median filtering or spatial averaging techniques. This is an optional step and helps focus primarily on an interval of interest in the wellbore. For example, the spatial filtering step can be used to focus on a producing interval where there is high likelihood of sand ingress, for example. The resulting data set produced through the conversion of the raw optical data can be referred to as the acoustic sample data. [00106] The acoustic data, including the optionally pre-processed and/or filtered data, can be transformed from the time domain into the frequency domain using a transform. For example, a Fourier transform such as a Discrete Fourier transformations (DFT), a short time Fourier transform (STFT), or the like can be used to transform the acoustic data measured at each depth section along the fiber or a section thereof into a frequency domain representation of the signal. The resulting frequency domain representation of the data can then be used to provide the data from which the plurality of frequency domain features can be determined. Spectral feature extraction using the frequency domain features through time and space can be used to determine one or more frequency domain features.
[00107] The use of frequency domain features to identify fluid flow events and locations, flow phase identification, and/or flow quantities of one or more fluid phases can provide a number of advantages. First, the use of frequency domain features results in significant data reduction relative to the raw DAS data stream. Thus, a number of frequency domain features can be calculated and used to allow for event identification while the remaining data can be discarded or otherwise stored, and the remaining analysis can performed using the frequency domain features. Even when the raw DAS data is stored, the remaining processing power is significantly reduced through the use of the frequency domain features rather than the raw acoustic data itself. Further, the use of the frequency domain features can, with the appropriate selection of one or more of the frequency domain features, provide a concise, quantitative measure of the spectral character or acoustic signature of specific sounds pertinent to downhole fluid surveillance and other applications.
[00108] While a number of frequency domain features can be determined for the acoustic sample data, not every frequency domain feature may be used to identify fluid flow events and locations, flow phase identification, and/or flow quantities of one or more fluid phases. The frequency domain features represent specific properties or characteristics of the acoustic signals. [00109] In some embodiments, combinations of frequency domain features can be used as the frequency domain features themselves, and the resulting combinations are considered to be part of the frequency domain features as described herein. In some embodiments, a plurality of frequency domain features can be transformed to create values that can be used to define various event signatures. This can include mathematical transformations including ratios, equations, rates of change, transforms (e.g., wavelets, Fourier transforms, other wave form transforms, etc.), other features derived from the feature set, and/or the like as well as the use of various equations that can define lines, surfaces, volumes, or multi-variable envelopes. The transformation can use other measurements or values outside of the frequency domain features as part of the transformation. For example, time domain features, other acoustic features, and non-acoustic measurements can also be used. In this type of analysis, time can also be considered as a factor in addition to the frequency domain features themselves. As an example, a plurality of frequency domain features can be used to define a surface (e.g., a plane, a three-dimensional surface, etc.) in a multivariable space, and the measured frequency domain features can then be used to determine if the specific readings from an acoustic sample fall above or below the surface. The positioning of the readings relative to the surface can then be used to determine if the event is present or not at that location in that detected acoustic sample.
[00110] The frequency domain features can include any frequency domain features derived from the frequency domain representations of the acoustic data. Such frequency domain features can include, but are not limited to, the spectral centroid, the spectral spread, the spectral roll-off, the spectral skewness, the root mean square (RMS) band energy (or the normalized sub-band energies / band energy ratios), a loudness or total RMS energy, a spectral flatness, a spectral slope, a spectral kurtosis, a spectral flux, a spectral autocorrelation function, or a normalized variant thereof.
[00111] The spectral centroid denotes the “brightness” of the sound captured by the optical fiber (e.g., optical fiber 162 shown in FIG. 3) and indicates the center of gravity of the frequency spectrum in the acoustic sample. The spectral centroid can be calculated as the weighted mean of the frequencies present in the signal, where the magnitudes of the frequencies present can be used as their weights in some embodiments.
[00112] The spectral spread is a measure of the shape of the spectrum and helps measure how the spectrum is distributed around the spectral centroid. In order to compute the spectral spread, Si, one has to take the deviation of the spectrum from the computed centroid as per the following equation (all other terms defined above):
[00113] The spectral roll-off is a measure of the bandwidth of the audio signal. The Spectral roll-off of the i th frame, is defined as the frequency bin ‘y’ below which the accumulated magnitudes of the short-time Fourier transform reach a certain percentage value (usually between 85% - 95%) of the overall sum of magnitudes of the spectrum.
[00114] where c=85 or 95. The result of the spectral roll-off calculation is a bin index and enables distinguishing acoustic events based on dominant energy contributions in the frequency domain (e.g., between gas influx and liquid flow, etc.).
[00115] The spectral skewness measures the symmetry of the distribution of the spectral magnitude values around their arithmetic mean.
[00116] The RMS band energy provides a measure of the signal energy within defined frequency bins that may then be used for signal amplitude population. The selection of the bandwidths can be based on the characteristics of the captured acoustic signal. In some embodiments, a sub-band energy ratio representing the ratio of the upper frequency in the selected band to the lower frequency in the selected band can range between about 1.5:1 to about 3:1. In some embodiments, the sub-band energy ratio can range from about 2.5:1 to about 1.8:1, or alternatively be about 2: IThe total RMS energy of the acoustic waveform calculated in the time domain can indicate the loudness of the acoustic signal. In some embodiments, the total RMS energy can also be extracted from the temporal domain after filtering the signal for noise.
[00117] The spectral flatness is a measure of the noisiness / tonality of an acoustic spectrum.
It can be computed by the ratio of the geometric mean to the arithmetic mean of the energy spectrum value and may be used as an alternative approach to detect broad-banded signals. For tonal signals, the spectral flatness can be close to 0 and for broader band signals it can be closer to 1
[00118] The spectral slope provides a basic approximation of the spectrum shape by a linearly regressed line. The spectral slope represents the decrease of the spectral amplitudes from low to high frequencies (e.g., a spectral tilt). The slope, the y-intersection, and the max and media regression error may be used as features.
[00119] The spectral kurtosis provides a measure of the flatness of a distribution around the mean value.
[00120] The spectral flux is a measure of instantaneous changes in the magnitude of a spectrum. It provides a measure of the frame-to-frame squared difference of the spectral magnitude vector summed across all frequencies or a selected portion of the spectrum. Signals with slowly varying (or nearly constant) spectral properties (e.g., noise) have a low spectral flux, while signals with abrupt spectral changes have a high spectral flux. The spectral flux can allow for a direct measure of the local spectral rate of change and consequently serves as an event detection scheme that could be used to pick up the onset of acoustic events that may then be further analyzed using the feature set above to identify and uniquely classify the acoustic signal.
[00121] The spectral autocorrelation function provides a method in which the signal is shifted, and for each signal shift (lag) the correlation or the resemblance of the shifted signal with the original one is computed. This enables computation of the fundamental period by choosing the lag, for which the signal best resembles itself, for example, where the autocorrelation is maximized. This can be useful in exploratory signature analysis / even for anomaly detection for well integrity monitoring across specific depths where well barrier elements to be monitored are positioned.
[00122] Any of these frequency domain features, or any combination of these frequency domain features (including transformations of any of the frequency domain features and combinations thereof), can be used to detect and identify one or more events and locations. In some aspects, a selected set of characteristics can be used to identify the events, and/or all of the frequency domain features that are calculated can be used as a group in characterizing the identity and location of the one or more events. The specific values for the frequency domain features that are calculated can vary depending on the specific attributes of the acoustic signal acquisition system, such that the absolute value of each frequency domain feature can change between systems. In some aspects, the frequency domain features can be calculated for each event based on the system being used to capture the acoustic signal and/or the differences between systems can be taken into account in determining the frequency domain feature values for each fluid inflow event between or among the systems used to determine the values and the systems used to capture the acoustic signal being evaluated. For example, the frequency domain features can be normalized based on the acquired values to provide more consistent readings between systems and locations.
[00123] One or a plurality of frequency domain features can be used to identify events and locations. In an embodiment, one, or at least two, three, four, five, six, seven, eight, etc. different frequency domain features can be used to identify the one or more events and their locations. The frequency domain features can be combined or transformed in order to define the event signatures for one or more events, such as, for instance, a fluid flow event location or flowrate. While exemplary numerical ranges are provided herein, the actual numerical results may vary depending on the data acquisition system and/or the values can be normalized or otherwise processed to provide different results.
[00124] In embodiments, the method 10 of identifying one or more events within wellbore 114 further comprises creating labeled data using the identified one or more events identified at 13 and the second set of measurements obtained at 15.
[00125] As depicted in FIG. 2A, which is a flow diagram of identifying one or more events within the wellbore 114 using the first set of measurements at 13, in embodiments, identifying the one or more events at 13 comprises: using the first set of measurements with one or more wellbore event models at 13'; and identifying the one or more events with the one or more wellbore event models at 13". For example, when the first set of measurements comprises DTS measurements, the first set of (e.g., DTS) measurements can be utilized as described hereinabove with one or more wellbore event models to identify the one or more events. For example, as depicted in FIG. 2B, in such embodiments, identifying one or more events within the wellbore 114 using the first set of measurements at 13 can comprise determining temperature features at 13"', using the temperature features with one or more wellbore event models at 13', and determining the presence of (i.e., “identifying”) the one or more events (such as, without limitation, fluid flow) at one or more locations in the wellbore 114 using an output from the one or more wellbore event models at 13". [00126] In some aspects, the one or more wellbore event models can comprise physics, fluid mechanics, or first principles models. For example, temperature based measurements can be used in a first principles model to identify the inflow of a gas phase hydrocarbon into the wellbore. Various phenomena such as Joule-Thomson cooling can result in a localized temperature change to identify the inflow of gas. Other first principles or similar type models can also be used to identify the one or more events at 13. In some aspects, the one or more wellbore event models can comprise a plurality of models using different parameters. For example, first principles models can be combined with temperature based machine learning models to fully identify the one or more events at 13.
[00127] In embodiments, subsequent training of the one or more event models at 17, the method 10 can further comprise at 19 (e.g., using the one or more event models to identify the at least one additional event within the wellbore 114): monitoring the first signal within the wellbore 114; monitoring the second signal within the wellbore 114; using the first signal in the one or more wellbore event models; using the second signal in the (now trained) one or more event models; and detecting the at least one additional event based on outputs of both the one or more wellbore event models and the one or more event models. In this manner, the trained one or more event models and the one or more wellbore event models utilized to identify the one or more events at 13 that were subsequently utilized to train the one or more event models at 17 can be utilized at 19 to identify the at least one additional event within the wellbore 114.
[00128] In some aspects, the second signal can comprise an acoustic signal. In such embodiments, a method of identifying events within a wellbore according to this disclosure can comprise: obtaining a first set of measurements of a first signal within a wellbore 114 at 11; identifying one or more events within the wellbore 114 at 13; obtaining an acoustic data set from within the wellbore 114 at 15, wherein the first signal is not an acoustic signal; training, at 17, one or more second event models using the acoustic data set and the identification of the one or more events as inputs; and using the trained one or more second event models at 19 to identify at least one additional event within the wellbore 114.
[00129] As noted hereinabove, the second signal comprises an acoustic signal, the first set of measurements can comprise distributed temperature sensor (DTS) measurements. Alternatively or additionally, the first set of measurements can comprise production volumetric (e.g., PLT) information. Identifying the one or more events within the wellbore 114 at 13 can comprise: identifying a first location having a first event of the one or more events; and identifying the first event at the first location using one or more wellbore event models.
[00130] Referring to FIG. 1, training the one or more event models at 17 can comprise: obtaining acoustic data for the first location from the acoustic data set (e.g., as described hereinabove with reference to FIG. 3); and training the one or more event models using the acoustic data for the first location and the identification of the first event at the first location. Using the trained one or more event models at 19 to identify the at least one additional event within the wellbore 114 can comprise using the one or more trained event models (optionally in conjunction with the one or more wellbore event models) to identify the at least one additional event. The event can be identified along the length of the wellbore 114, or in some aspects, within another wellbore. [00131] For an event comprising fluid flow, one or more fluids that can include gas, a liquid aqueous phase, a liquid hydrocarbon phase, and potentially other fluids as well as various combinations thereof can enter the wellbore 114 at one or more locations along the wellbore 114. Temperature features can be utilized to identify these inflow locations. As noted hereinabove, temperature features can be utilized with one or more first or wellbore event models to provide an output of the one or more first or wellbore event models and then be utilized with the one or more second event models to provide an output of the second model. Subsequent to training of the one or more event models, the presence (and/or extent) of the at least one additional event at one or more locations can be determined using an output from the one or more first or wellbore event models, an output from the one or more second event models, or a combined output obtained using the output from the one or more first or wellbore event models and the output from the one or more second event models.
[00132] The temperature features can be determined using the temperature monitoring system to obtain temperature measurements along the length being monitored (e.g., the length of the wellbore). In some embodiments, a DTS system can be used to receive distributed temperature measurement signals from a sensor disposed along the length (e.g., the length of the wellbore), such as an optical fiber. The resulting signals from the temperature monitoring system can be used to determine one or more temperature features as described herein. In some embodiments, a baseline or background temperature profde can be used to determine the temperature features, and the baseline temperature profile can be obtained prior to obtaining the temperature measurements. [00133] In some embodiments, a plurality of temperature features can be determined from the temperature measurements, and the plurality of temperature features can comprise at least two of: a depth derivative of temperature with respect to depth, a temperature excursion measurement, a baseline temperature excursion, a peak-to-peak value, a fast Fourier transform, a Laplace transform, a wavelet transform, a derivative of temperature with respect to length (e.g., depth), a heat loss parameter, an autocorrelation, as detailed hereinabove, and/or the like. Other temperature features can also be used in some embodiments. The temperature excursion measurement can comprise a difference between a temperature reading at a first depth, and a smoothed temperature reading over a depth range, where the first depth is within the depth range. The baseline temperature excursion can comprise a derivative of a baseline excursion with depth, where the baseline excursion can comprise a difference between a baseline temperature profile and a smoothed temperature profile. The peak-to-peak value can comprise a derivative of a peak-to-peak difference with depth, where the peak-to-peak difference comprises a difference between a peak high temperature reading and a peak low temperature reading with an interval. The fast Fourier Transform can comprise an FFT of the distributed temperature sensing signal. The Laplace transform can comprise a Laplace transform of the distributed temperature sensing signal. The wavelet transform can comprise a wavelet transform of the distributed temperature sensing signal or of the derivative of the distributed temperature sensing signal with respect to length (e.g., depth). The derivative of the distributed temperature sensing signal with respect to length (e.g., depth) can comprise the derivative of the flowing temperature with respect to depth. The heat loss parameter can comprise one or more of the geothermal temperature, a deviation, dimensions of the tubulars that are in the well, well head pressure, individual separator rates, downhole pressure, gas/liquid ratio, or the like. The autocorrelation can comprise a cross-correlation of the distributed temperature sensing signal with itself.
[00134] Once the temperature features are obtained, the temperature features can be used with one or more first or wellbore event models to identify the presence of the event at one or more locations. In some embodiments, the one or more first or wellbore event models can accept a plurality of temperature features as inputs. In general, the temperature features are representative of feature at a particular location (e.g., a depth resolution portion of the optical fiber along the length of the wellbore 114 being monitored) along the length. The one or more first or wellbore event models can comprise one or more models configured to accept the temperature features as input(s) and provide an indication of whether or not there is an event at the particular location along the length. The output of the one or more first or wellbore event models can be in the form of a binary yes/no result, and/or a likelihood of an event (e.g., a percentage likelihood, etc.). Other outputs providing an indication of an event are also possible. In some embodiments, the one or more first or wellbore event models can comprise a a machine learning model using supervised or unsupervised learning algorithms such as a multivariate model, neural network, or the like. [00135] In some embodiments, the one or more first or wellbore event models can comprise a multivariate model. A multivariate model allows for the use of a plurality of variables in a model to determine or predict an outcome. A multivariate model can be developed using known data on events along with features for those events to develop a relationship between the features and the presence of the event at the locations within the available data. One or more multivariate models can be developed using data, where each multivariate model uses a plurality of features as inputs to determine the likelihood of an event occurring at the particular location along the length. [00136] As noted above, in some embodiments, the one or more first or wellbore event models can comprise one or more multivariate models that use one or more features (e.g., temperature features, frequency domain features, other features derived from other types of sensors, etc.). The multivariate model can use multivariate equations, and the multivariate model equations can use the features or combinations or transformations thereof to determine when an event is present. The multivariate model can define a threshold, decision point, and/or decision boundary having any type of shapes such as a point, line, surface, or envelope between the presence and absence of the specific event. In some embodiments, the multivariate model can be in the form of a polynomial, though other representations are also possible. The model can include coefficients that can be calibrated based on known event data. While there can be variability or uncertainty in the resulting values used in the model, the uncertainty can be taken into account in the output of the model. Once calibrated or tuned, the model can then be used with the corresponding features to provide an output that is indicative of the occurrence of an event. [00137] The multivariate model is not limited to two dimensions (e.g., two features or two variables representing transformed values from two or more features), and rather can have any number of variables or dimensions in defining the threshold between the presence or absence of the event. When used, the detected values can be used in the multivariate model, and the calculated value can be compared to the model values. The presence of the event can be indicated when the calculated value is on one side of the threshold and the absence of the event can be indicated when the calculated value is on the other side of the threshold. In some embodiments, the output of the multivariate model can be based on a value from the model relative to a normal distribution for the model. Thus, the model can represent a distribution or envelope and the resulting features can be used to define where the output of the model lies along the distribution at the location along the length being monitored (e.g., along the length of the wellbore). Thus, each multivariate model can, in some embodiments, represent a specific determination between the presence or absence of an event at a specific location along the length. Different multivariate models, and therefore thresholds, can be used for different events, and each multivariate model can rely on different features or combinations or transformations of features. Since the multivariate models define thresholds for the determination and/or identification of events, the multivariate models and the one or more first or wellbore event models using such multivariate models can be considered to be based event signatures for each type of event.
[00138] In some embodiments, the one or more first or wellbore event models can comprise a plurality of models. Each of the models can use one or more of the features as inputs. The models can comprise any suitable model that can relate one or more features to an occurrence of an event (e.g., a likelihood of the event, a binary yes/no output, etc.). The output of each model can then be combined to form a composite or combined output. The combined output can then be used to determine if an event has occurred, for example, by comparing the combined output with a threshold value. The determination of the occurrence of an event can then be based on the comparison of the combined output with the threshold value.
[00139] As an example, the one or more first or wellbore event models can include a plurality of multivariate models, each using a plurality of features as described above. The output of the multivariate models can include a percentage likelihood of the occurrence of an event at the particular location at which each model is applied. The resulting output values can then be used in a function such as a simple multiplication, a weighted average, a voting scheme, or the like to provide a combined output. The resulting output can then be compared to a threshold to determine if an event has occurred. For example, a combined output indicating that there is greater than a fifty percent likelihood of an event at the particular location can be taken as an indication that the event has occurred at the location of interest.
[00140] In some embodiments, the one or more first or wellbore event models can also comprise other types of models, including other machine learning models, first principles models, and/or physics based models. In some embodiments, a machine learning approach comprises a logistic regression model. In some such embodiments, one or more features can be used to determine if an event is present at one or more locations of interest. The machine learning approach can rely on a training data set that can be obtained from a test set-up or obtained based on actual data from known events (e.g., from in-situ data as described herein in any of the aspects or embodiments). The one or more features in the training data set can then be used to train the one or more first or wellbore event models using machine learning, including any supervised or unsupervised learning approach. For example, the one or more first or wellbore event models can include or consist of a neural network, a Bayesian network, a decision tree, a logistical regression model, a normalized logistical regression model, or the like. In some embodiments, the one or more first or wellbore event models can comprise a model developed using unsupervised learning techniques such a k-means clustering and the like.
[00141] In some embodiments, the one or more first or wellbore event models can be developed and trained using a logistic regression model. As an example for training of a model used to determine the presence or absence of an event, the training of the model can begin with providing the one or more temperature features to the logistic regression model corresponding to one or more reference data sets in which event(s) are present. Additional reference data sets can be provided in which event(s) are not present. The one or more features can be provided to the logistic regression model, and a first multivariate model can be determined using the one or more features as inputs. The first multivariate model can define a relationship between a presence and an absence of the events.
[00142] Once the one or more first or wellbore event models are trained, the one or more first or wellbore event models can be used to determine the presence or absence of an event at one or more locations along the length of the wellbore 114, and the one or more events identified at 13 can be utilized at 17 to identify corresponding data for training the one or more event models. The features determined for each location along the length can be used with the one or more first or wellbore event models. The output of the one or more first or wellbore event models can provide an indication of the presence of an event at each location for which the temperature features are obtained. When the output indicates that an event has occurred at a given location, an output can be generated indicating the presence of the event. The process can be repeated along the length to provide an event profile, which can comprise an indication of the events at one or more locations along the length being monitored. In some aspects, the event may be known or induced, and the use of the first wellbore event models may not be used to identify the event.
[00143] In some embodiments, the determination of the one or more events can be presented as a profile along a length on an output device. The outputs can be presented in the form of an event profile depicted along an axis with or without a schematic. The event profile can then be used to visualize the event locations, which can allow for various processes to be carried out. For example, for events comprising fluid flow, the fluid flow locations can be compared to the producing zones within a completion to understand where fluid is entering, leaving, or flowing along the wellbore. In some embodiments, fluid flow can be detected at locations other than a producing zone, which may provide an indication that a remediation procedure is needed within the wellbore 114. For example, fluid flow during a shut-in period outside of a producing zone may indicate a leak behind the casing.
[00144] The identification of the event at step 13 allows the second set of measurements of the second signal to be obtained and associated or labeled with the event. For example, DTS measurements and/or temperature features can be used to identify an event at a location in the wellbore. A second set of measurements such as acoustic measurements can then be taken and labeled as being associated with an identified event. The labeled data can then be used to train the one or more event models at 17, as described in more detail below. Obtaining the second set of measurements at step 15 can occur simultaneously with obtaining the first set of measurements at step 11. For example, both sets of measurements can be detected at the same time. Once the event is identified using the first set of measurements, the second set of measurements can be stored with the event identification. Since some events are relatively constant, obtaining the first set of measurements can occur prior to or after obtaining the second set of measurements. For example, flow rate measurements from a PLT can be used to identify a fluid flow of a specific phase at a first time. The PLT can then be moved in the wellbore or removed altogether, and a second set of measurements can be obtained, where the fluid flow can be assumed to be the same at the time of the second set of measurement even though they are not obtained simultaneously. The resulting event identification can then be used to label the in-situ data for use in training the one or more event models at step 17.
[00145] According to this disclosure, the one or more second event models can be trained using a labeled data set, obtained from field or in situ data (i.e., from event locations identified from the first set of measurements of the first signal) that is labeled using other instrumentation to identify the presence and/or extent of an event. In some embodiments, the one or more second event models can be further trained using a labeled data set, which can be obtained using a test apparatus such as a test flow set-up and/or field data that is labeled using other instrumentation to identify the extent of an event. Using labeled data, the method of developing the one or more second event models can include determining one or more frequency domain features from the acoustic signal for at least a portion of the data from the labeled data. The one or more frequency domain features can be obtained across the portion of length where the event occurs, which can be determined using the first event model or models. The second event model can then be trained using the frequency domain features from the labeled data and/or the tests. The training of the second event model can use machine learning, including any supervised or unsupervised learning approach. For example, the one or more second event models can include or be a neural network, a Bayesian network, a decision tree, a logistical regression model, a normalized logistical regression model, k-means clustering or the like.
[00146] In some embodiments, the one or more second event models can be developed and trained using a logistic regression model. As an example for training of a model used to determine the extent of an event comprising fluid flow (e.g., to determine the fluid flow rate), the training of the one or more second event models can begin with providing one or more frequency domain features to the logistic regression model corresponding to one or more event tests where known event extents have been measured. Similarly, one or more frequency domain features can be provided to the logistic regression model corresponding to one or more tests where no event is present. A first multivariate model can be determined using the one or more frequency domain features as inputs. The first multivariate model can define a relationship between a presence and an absence of the event and/or event extent.
[00147] In the one or more second event models, the multivariate model equations can use the frequency domain features or combinations or transformations thereof to determine when a specific event or event extent (e.g., a specific fluid flow rate or fluid flow rate for a fluid phase) is present. The multivariate model can define a threshold, decision point, and/or decision boundary having any type of shapes such as a point, line, surface, or envelope between the presence and absence of the event or an event extent (e.g., the specific fluid flow rate or fluid flow rate for a phase). In some embodiments, the multivariate model can be in the form of a polynomial, though other representations are also possible. When models such a neural networks are used, the thresholds can be based on node thresholds within the model. As noted herein, the multivariate model is not limited to two dimensions (e.g., two frequency domain features or two variables representing transformed values from two or more frequency domain features), and rather can have any number of variables or dimensions in defining the threshold between the presence or absence of the event (e.g., fluid flow) and the specific event extents (e.g., fluid flow rates for one or more fluids and/or fluid phases). Different multivariate models can be used for various events and/or event extents (e.g., flow rate for each fluid type and/or fluid flow phase), and each multivariate model can rely on different frequency domain features or combinations or transformations of frequency domain features. [00148] Whether a test system or in situ sensors are used to obtain data on the event extents (e.g., flow rates), collectively referred to as “reference data”, one or more models can be developed for the determination of the event extents (e.g., flow rates) using the reference data. The model(s) can be developed by determining one or more frequency domain features from the acoustic signal for at least a portion of the reference data. The training of the model(s) can use machine learning, including any supervised or unsupervised learning approach. For example, one or more of the model(s) can be a neural network, a Bayesian network, a decision tree, a logistical regression model, a normalized logistical regression model, k-means clustering, or the like.
[00149] The one or more frequency domain features used in the one or more second event models can include any frequency domain features noted hereinabove as well as combinations and transformations thereof. For example, In some embodiments, the one or more frequency domain features comprise a spectral centroid, a spectral spread, a spectral roll-off, a spectral skewness, an RMS band energy, a total RMS energy, a spectral flatness, a spectral slope, a spectral kurtosis, a spectral flux, a spectral autocorrelation function, combinations and/or transformations thereof, or any normalized variant thereof. In some embodiments, the one or more frequency domain features comprise a normalized variant of the spectral spread (NVSS) and/or a normalized variant of the spectral centroid (NVSC).
[00150] The output of the (trained) one or more second event models can comprise an indication of the event location(s) and/or extent(s) (e.g., the flow rate(s) of one or more fluids and/or fluid phases). For example, for events comprising fluid flow, the total liquid flow rate at one or more event locations can be determined from the one or more second event models. The resulting output can, in aspects, be compared to the output of the one or more first or wellbore event models to allow the event (e.g., fluid flow) location determination to be based both on the one or more first or wellbore event models (e.g., using the temperature features) and the one or more second event models (e.g., using the frequency domain features). In aspects, a final output can be a function of both the output from the one or more first or wellbore event models and the one or more second event models. In some embodiments, the outputs can be combined as a product, weighted product, ratio, or other mathematical combination. Other combinations can include voting schemes, thresholds, or the like to allow the outputs from both models to be combined. As an example, if the output from either model is zero, then the event identification at the location would also indicate that there is no event at the location. In this example, one model can indicate that an event is present, but the other model can indicate that no event is present. The final result can indicate that no event is present. When both models indicate that the event is present, the final combined output can provide a positive indication of the event at the location. It is noted that the output of the one or more second event models can provide one or more indications of event extents (e.g., a fluid flow rate of one or more fluids and/or fluid phases). While this output can be distinct from the output of the one or more first or wellbore event models, the two outputs can be combined to improve the accuracy of the event location identification.
[00151] In aspects, a combined or hybrid approach to determining event extents (e.g., fluid flow rates) at the one or more locations at which an event (e.g., fluid flow) is identified is utilized. In these embodiments, the outputs of the one or more first or wellbore event models and the one or more (trained) second event models can be used together to help to determine or confirm the presence and/or extent of an event (e.g., a flow rate of one or more fluids and/or fluid phases) along the length being monitored (e.g., within the wellbore 114). In some embodiments, the outputs of the two models can be combined to form a final event presence and/or event extent determination. [00152] Subsequent to the training of the one or more event models at 17, the one or more second event models can use one or more frequency domain features in one or more event models to validate the identified one or more events and/or predict an extent of the event(s) (e. g. , a quantity or flow rate of one or more fluids and/or fluid phases into the wellbore 114, amount of leakage from a pipeline, etc.). For example, when the event comprises fluid flow in a wellbore 114, the one or more second event models can be used to identify the fluid flow, to validate a flow location identified by the one or more first or wellbore event models, and/or predict the flow rates of one or more fluids including a gas, an aqueous liquid, a hydrocarbon liquid, or another fluid within the wellbore 114. In some embodiments, the one or more second event models can be utilized to predict the flow rate of a fluid phase such as a gas phase and/or a liquid phase (e.g., including a liquid aqueous phase and a hydrocarbon liquid phase).
[00153] In some embodiments, the frequency domain features can be used with one or more second event models to predict a fluid flow rate, such as a liquid flowrate into the wellbore 114. The one or more second event models can relate a fluid flow rate of one or more phases (e.g., including a total liquid flow rate) to one or more frequency domain features. In some embodiments, the trained one or more second event models can accept one or more frequency domain features as inputs. In general, the frequency domain features are representative of feature at a particular location (e.g., a depth resolution portion of the optical fiber along the length, e.g., the length of the wellbore) along the length. The one or more second event models can comprise one or more models configured to accept the frequency domain features as input(s) and provide an indication of the presence and/or extent of the event (e.g., a fluid flowrate) at one or more locations within wellbore 114. When the event comprises fluid inflow, for example, the output of the one or more second event models can be, for example, in the form of a flow rate of one or more fluids and/or fluid phases. In some embodiments, the one or more second event models can comprise a multivariate model, a machine learning model using supervised or unsupervised learning algorithms, or the like.
[00154] In some embodiments, one or more second event models can be developed using a machine learning approach. In some such embodiments, a single frequency domain feature (e.g., spectral flatness, RMS bin values, etc.) can be used to determine if the event is present at each location of interest. In some embodiments, the supervised learning approach can be used to determine a model of the event extent (e.g., flow rate of one or more fluids and/or fluid phases, such as gas flow rate, a hydrocarbon flow rate, a water flow rate, a total gas phase flow rate, and/or a total liquid phase (e.g., a liquid aqueous phase and a liquid hydrocarbon phase) flow rate). [00155] In some aspects, the event identification and corresponding reference data can be used to calibrate the one or more first event models. In this context, training the one or more second event models can include a calibration process. For example, the models or structure of the model (e.g., the type of model, identification of the model variables, etc.) can be known or pre-trained, and the event identification and corresponding reference data can be used as a new training data set or used to supplement the original training data set to re-train or calibrate the one or more second event models. This can allow one or more parameters (e.g., coefficients, weightings, etc.) to be updated or calibrated to provide a more accurate model. This process may be useful to calibrate existing models for specific wellbores, formations, or fields to improve the event identifications in those locations.
[00156] Continuing the example above for a fluid flow events, the use of the event identification and reference data can allow for a fluid flow event model to be trained using the fluid flow event identification and reference data to be used as the input data. A fluid inflow model such as a hydrocarbon inflow model, may be defined by one or more frequency domain features and a relationship between the features. The event identification can be used to select the appropriate model (e.g., as defined by the identification and relationship of the one or more frequency domain features), and the reference data can be used to train the model to determine the model parameters (e.g., coefficients, weightings, etc.). This process can represent a calibration of the one or more second event models rather than developing an entirely new model.
[00157] The in-situ identification of training data can also be used to cross-check and validate existing models. For example, the in-situ identified data can be used to train the one or more second event models as described herein. When an additional event is identified using the trained one or more second models, the event identification can be used to identify additional data using the first signals, which would correspond to the first set of measurements. The first set of models can be trained to verify whether or not the newly trained model matches the original model within a given threshold. When the models match, the system can provide an indication that the event is the only event present. When the models do not match, it can be an indication that another, unidentified event is present within the data. Additional training and event identification can then be used to identify the additional event. The cross-checking and validation process can be carried out using subsequent data in time, at different depths along the wellbore, and/or across different wellbores.
[00158] Using the example above for fluid flow events, DTS data can be used to identify an event during a fluid flow event such as a hydrocarbon flow. Corresponding DAS acoustic data can be obtained during the hydrocarbon flow event, and the resulting reference data can be used to train one or more second event models for hydrocarbon flow using one or more frequency domain features obtained from the DAS data. The resulting hydrocarbon flow event models using the one or more frequency domain features can then be used alone or in combination with the DTS models to identify a hydrocarbon flow event.
[00159] Continuing with the example, the DAS data can be used to identify a hydrocarbon flow event using the trained hydrocarbon flow models. When a hydrocarbon flow event is detected, additional data such as DTS data can be obtained. The training process can then be repeated using the DTS data to train a hydrocarbon flow model, and the resulting trained model can be compared to the original DTS model for hydrocarbon flow. If the models match within a threshold (e. g. , within a margin of error, etc.), then the models can be understood to detect hydrocarbon flow with reasonable certainty. However, if the models do not match, an additional event may be present. For example, the flow event as detected by the trained hydrocarbon flow model using the one or more frequency domain features may include both hydrocarbon flow and water flow. By training the model using the identified DTS data, the model may not match the original model due to the presence of the water in the flowing fluids.
[00160] When the models do not match within a threshold or margin of error, the various data can be used to identify one or more events and identify any remaining noise or background signals. The remaining signals can then be attributed to a separate event that can be identified using other signatures, models, or processes. For example, the produced fluids can be observed on the surface to provide data indicating that water is present in addition to the hydrocarbon fluids. This information can then be used with the noise signals to identify additional data that can be used to train an additional one or more event models to capture the additional events.
[00161] Even when the original model and the additional model match within a margin of error, the process can be used to improve both sets of models. In some embodiments, once one or more second event models are trained using the reference data, the one or more second event models can be used to identify one or more events. Additional data using a signal that represents a different physical measurement, which can be the same as the first signal used to train the one or more second event models, can be obtained and labeled using the identification of the event. The original thresholds, signatures, and/or models can then be retrained using the new reference data and/or a set of reference data supplemented by the new reference data (e.g., the original training data set and the new reference data combined to provide a larger training data set). This process can provide an improvement in the model output.
[00162] This process can be carried out at different locations along the wellbore, at different locations in different wellbores, and/or at different times in the same or different locations in the wellbore or a separate wellbore. This can allow for an improved reference data set (e.g., that is labeled with the identified events) that can be used to train the one or more event models over time to provide improved results for event identification.
[00163] FIG. 6 illustrates a flow chart for a method 500 of determining the presence and/or extent of an event after training of the one or more event models. Subsequent to training the one or more event models, the one or more event models can be utilized alone or in conjunction with and/or the one or more wellbore event models or other data. For example, subsequent training of one or more event models with DAS data in combination with the location of one or more events identified via DTS data, the one or more trained event models can be utilized alone or in combination with the one or more wellbore event models to identify at least one additional event in the or another wellbore. In applications, DAS and DTS can be combined as described, for example, in PCT Patent Application No. PCT/EP2020/051817, entitled, “Event Characterization Using Hybrid DAS/DTS Measurements”, filed on January 24, 2020, which is incorporated herein in its entirety. At step 502, temperature features can be determined using any of the processes and systems as described herein. In some embodiments, a DTS system can be used to obtain distributed temperature sensing signal along the length being monitored (e.g., along a length within the wellbore 114). The DTS system can provide distributed temperature measurements along the length over time. A baseline temperature can be stored for the length as described herein and used along with the temperature measurements to determine the temperature features. The temperature features can include any of those described herein including a depth derivative of temperature with respect to depth, a temperature excursion measurement, a baseline temperature excursion, a peak- to-peak value, a fast Fourier transform, a Laplace transform, a wavelet transform, a derivative of temperature with respect to length (e.g., depth), a heat loss parameter, an autocorrelation, a statistical measure of a variation with respect to time and/or distance, as detailed hereinabove, or a combination thereof.
[00164] At step 504, one or more frequency domain features can be obtained from an acoustic signal originating along the length being monitored (e.g., within the wellbore 114). The frequency domain features can be determined using any of the processes and systems as described herein. In some embodiments, a DAS system can be used to obtain a distributed acoustic signal along the length of wellbore 114 being monitored. The acoustic signals obtained from the DAS system can then be processed to determine one or more frequency domain features as described herein. In some embodiments, the frequency domain features can comprise at least one of: a spectral centroid, a spectral spread, a spectral roll-off, a spectral skewness, an RMS band energy, a total RMS energy, a spectral flatness, a spectral slope, a spectral kurtosis, a spectral flux, a spectral autocorrelation function, or any combination thereof, including combinations and modifications thereof.
[00165] The temperature features and/or the frequency domain features can then be used to determine a presence and/or extent of one or more events (e.g., a fluid inflow at one or more locations in a wellbore 114 and/or a fluid inflow rate thereof) at one or more locations along the length being monitored in step 506. The temperature features and/or the frequency domain features can be used in several ways to determine the presence and/or the extent of the one or more events along the length being monitored. In some embodiments, the temperature features can be used in the one or more first or wellbore event models to obtain an identification of one or more locations along the length having the event. Any of the models and methods of using the temperature features within the models as described herein can be used to determine the one or more event (e.g., fluid inflow) locations. As detailed hereinabove, the output of the one or more first or wellbore event models was utilized (e.g., at step 13 of FIG. 1) to provide labeled training data from which the one or more event models was trained, after which, the one or more wellbore event models and/or the one or more event models can be utilized alone or in combination with the one or more wellbore event models in the well or another well to provide an indication of one or more locations along the length being monitored (e.g., along the length of the wellbore) having at least one additional event in the or another wellbore.
[00166] In aspects, frequency domain features can be used in the trained one or more second event models to obtain an indication of the event extent (e.g., fluid inflow rate for one or more fluids and/or fluid phases) at the one or more locations along the length of the wellbore 114. In some embodiments, the one or more second event models can be limited to being executed at the one or more locations identified by the one or more first or wellbore event models. The one or more second event models can then predict the event extent(s) (e.g., fluid inflow rates of one or more fluids and/or fluid phases) at the one or more locations. The event extent(s) (e.g., fluid inflow rates) can then be representative of the event extents at the one or more locations along the length of the wellbore 144.
[00167] In some embodiments, subsequent to the training at 17, the output of the one or more first or wellbore event models and the one or more second event models can be combined to provide a combined output from the one or more first or wellbore event models and the one or more second event models to identify the at least one additional event at step 19. The resulting combined output can then be used to determine an event extent (e.g., a fluid inflow rate) at the one or more locations along the length of wellbore 114 being monitored as identified by the one or more first or wellbore event models. The combined output can be determined as a function of the output of the one or more first or wellbore event models and the output of the one or more second event models. Any suitable functions can be used to combine the outputs of the two models. This can include formulas, products, averages, and the like, each of which can comprise one or more constants or weightings to provide the final output. The ability to determine the event extent(s) as a function of the output of both models can allow for either model to override the output of the other model. For example, if the one or more first or wellbore event models indicate that a location along the length being monitored has an event, but the one or more second event models indicate no event, the resulting combined output may be considered to indicate that there is no event at that location. Similarly, if the one or more first or wellbore event models indicate a non-zero but low likelihood of an event at a location, the output can serve as a weighting to any event extents determined by the one or more second event models. Thus, a hybrid model approach can be utilized to provide two separate ways to verify and determine the event extents along the length (e.g., fluid inflow rates into the wellbore 114). Alternatively, subsequent to the training of the one or more second event models, the one or more second event models are utilized alone to identify the at least one additional event within the wellbore 114 at 19.
[00168] The resulting output of the one or more event model(s) (and/or the one or more wellbore event models) at 19 can be an indication of an event at one or more locations along the length. The event prediction can be for one or more events (e.g., one or more fluids (e.g., a gas, an aqueous liquid, a hydrocarbon liquid, etc.) and/or a fluid phase (e.g., a gas phase, a liquid phase, etc.)). The event extents can be used as indicated by the model in their form as output by the model. In some embodiments, the total event extents can be normalized across the one or more locations having the event. This can allow for a determination of a relative proportion of the event at each of the identified locations. This can be useful for understanding where the contributions to an event are occurring along the length, irrespective of the absolute event extent along the length.
[00169] In some embodiments, the event extents can be refined by using an independent measure of the event extent (e.g., fluid flow rate from the wellbore as measured at logging tool above the producing zones, a wellhead, surface flow line, or the like). Thus, as depicted in FIG. 6, method 500 can further comprise optional step 508 of independently measuring an event extent. For example, when the event comprises fluid inflow and the event extent comprises the fluid inflow rate, the fluid production rate can be measured by a standard fluid flowrate measurement tool that is not associated with the acoustic monitoring system or the temperature monitoring system within the wellbore 114. For example, the fluid production rate can be measured with various flow meters. The fluid production rate can comprise an indication of the fluid flow rates of one or more fluids and/or one or more fluid phases. The resulting event extent (e.g., fluid production rate) information can then be combined with the output of the models as described herein. In some embodiments, the resulting normalized event extents can be used with the actual event extents (e.g., production rates) to allocate the actual event extent (e.g., production rates) across the one or more event (e.g., fluid) inflow locations along the length being monitored (e.g., within the wellbore 114). Thus, method 500 of FIG. 6 can further comprise optional step 510 of allocating the event extent across the one or more locations. As an example, for events comprising fluid inflow and event extents comprising fluid inflow rates at one or more locations, if the model(s) indicate that thirty percent of a liquid phase inflow rate is occurring at a first location and seventy percent is occurring at a second location, the actual production rate can be allocated so that thirty percent of the produced liquid phase flowrate is attributed to the first location and the remaining seventy percent of the liquid phase flow rate is flowing into the wellbore at the second location. The allocations can be made for one or more of the fluid inflow rates and/or fluid phase inflow rates, where the actual production rates for the fluids and/or fluid phases can be used with the corresponding model outputs for one or more fluids and/or fluid phases. The allocation process can allow for an improved accuracy for the determination of fluid inflow rates at the one or more locations along the wellbore 114.
[00170] Also disclosed herein is a method of predicting wellbore sensor data. Description of such a method of predicting wellbore sensor data will now be made with reference to FIG. 7, which is a flow diagram of a method 20 of predicting wellbore sensor data according to some embodiments. As depicted in FIG. 7, method 20 comprises: obtaining a first set of measurements of a first signal within a wellbore 114 at 21 ; identifying one or more events within the wellbore 114 using the first set of measurements at 22; obtaining a second set of measurements of a second signal within the wellbore 114 at 23, wherein the first signal and the second signal represent different physical measurements; training one or more event models using the second set of measurements and the identification of the one or more events as inputs at 24; identifying, using the one or more event models, one or more additional events within the wellbore 114 at 25; using the one or more additional events with one or more formation properties at 26; and predicting a third set of measurements in response to combining the one or more additional events with the formation properties at 27, wherein the third set of measurements represents a third signal that is different than the first signal and the second signal. Steps 21, 22, 23, 24, and 25 correspond with and can be substantially as described hereinabove with reference to steps 11, 13, 15, 17, and 19, respectively, of FIG. 1. [00171] In embodiments, a method of predicting wellbore sensor data according to this disclosure comprises: training one or more event models using a second set of measurements and an identification of one or more events as inputs, wherein a first set of measurements of a first signal are obtained within a wellbore 114, wherein one or more events within the wellbore 114 are identified using the first set of measurements, wherein the second set of measurements of a second signal are obtained within the wellbore 114, and wherein the first signal and the second signal represent different physical measurements; identifying, using the one or more event models, one or more additional events within the wellbore 114; using the one or more additional events with one or more formation properties; and predicting a third set of measurements in response to combining the one or more additional events with the formation properties, wherein the third set of measurements represents a third signal that is different than the first signal and the second signal. [00172] The method of predicting wellbore sensor data according to this disclosure can further comprise: identifying, using the one or more event models, one or more additional events within the wellbore 114.
[00173] As noted above, the first signal and the second signal represent different physical measurements, and the third set of measurements represents a third signal that is different than the first signal and the second signal. For example, without limitation, in aspects, the third set of measurements can be predicted pressure measurements along the wellbore 114, or predicted flow measurements along the wellbore 114. As described hereinabove with regard to FIG. 1, the first set of measurements can comprise at least one of distributed temperature sensor (DTS) measurements, production logging tool (PLT) measurements, flow meter measurements, or pressure sensor measurements, and/or the second set of measurements can comprise acoustic measurements obtained within the wellbore 114. As detailed previously with reference to the method of even identification described with reference to FIG. 1, the one or more events can comprise inflow events, leak events, sand ingress events, or any combination thereof, and/or the first set of measurements and the second set of measurements can be obtained simultaneously or at different time intervals.
[00174] The method can further comprise creating labeled data using the identified one or more events and the second set of measurements. The rock properties can comprise porosity, permeability, or the like, provided, for example, as porosity or permeability logs, respectively. [00175] By way of example, in aspects, the first set of measurements comprises DTS data and the second set of measurements comprises DAS data. The local or reference DTS data (e.g., first set of measurements) can be utilized as detailed hereinabove along with the DAS measurements (e.g., the second set of data) to train one or more event models. Once trained, the one or more trained event models can subsequently be utilized in the same or another well to predict and/or validate data. For example, in aspects, the DAS/DTS data are utilized as detailed herein to generate synthetic thermal profdes (e.g., predicted DTS data in another wellbore) and/or synthetic pressure data (e.g., DPS) data in the same or another well. The synthetic or predicted data can be utilized to cross check data obtained via another means or sensor. For example, predicted or synthetic flow logs from the one or more trained event models can be utilized to cross validate PLT data obtained in situ. Alternatively or additionally, DPS data predicted from the trained event models in combination with the rock properties can be utilized to cross check pressure measurements from one or more in situ pressure sensors. One of skill in the art and with the help of this disclosure will understand that the herein disclosed system and method can be utilized to predict a variety of wellbore sensor data, which can be utilized in many ways to enhance wellbore management, planning, and production.
[00176] Any of the systems and methods disclosed herein can be carried out on a computer or other device comprising a processor (e.g., a desktop computer, a laptop computer, a tablet, a server, a smartphone, or some combination thereof), such as the acquisition device 160 of FIG. 3. FIG. 8 illustrates a computer system 680 suitable for implementing one or more embodiments disclosed herein such as the acquisition device or any portion thereof. The computer system 680 includes a processor 682 (which may be referred to as a central processor unit or CPU) that is in communication with memory devices including secondary storage 684, read only memory (ROM) 686, random access memory (RAM) 688, input/output (I/O) devices 690, and network connectivity devices 692. The processor 682 may be implemented as one or more CPU chips.
[00177] It is understood that by programming and/or loading executable instructions onto the computer system 680, at least one of the CPU 682, the RAM 688, and the ROM 686 are changed, transforming the computer system 680 in part into a particular machine or apparatus having the novel functionality taught by the present disclosure. It is fundamental to the electrical engineering and software engineering arts that functionality that can be implemented by loading executable software into a computer can be converted to a hardware implementation by well-known design rules. Decisions between implementing a concept in software versus hardware typically hinge on considerations of stability of the design and numbers of units to be produced rather than any issues involved in translating from the software domain to the hardware domain. Generally, a design that is still subject to frequent change may be preferred to be implemented in software, because re spinning a hardware implementation is more expensive than re-spinning a software design. Generally, a design that is stable that will be produced in large volume may be preferred to be implemented in hardware, for example in an application specific integrated circuit (ASIC), because for large production runs the hardware implementation may be less expensive than the software implementation. Often a design may be developed and tested in a software form and later transformed, by well-known design rules, to an equivalent hardware implementation in an application specific integrated circuit that hardwires the instructions of the software. In the same manner as a machine controlled by a new ASIC is a particular machine or apparatus, likewise a computer that has been programmed and/or loaded with executable instructions may be viewed as a particular machine or apparatus.
[00178] Additionally, after the system 680 is turned on or booted, the CPU 682 may execute a computer program or application. For example, the CPU 682 may execute software or firmware stored in the ROM 686 or stored in the RAM 688. In some cases, on boot and/or when the application is initiated, the CPU 682 may copy the application or portions of the application from the secondary storage 684 to the RAM 688 or to memory space within the CPU 682 itself, and the CPU 682 may then execute instructions of which the application is comprised. In some cases, the CPU 682 may copy the application or portions of the application from memory accessed via the network connectivity devices 692 or via the I/O devices 690 to the RAM 688 or to memory space within the CPU 682, and the CPU 682 may then execute instructions of which the application is comprised. During execution, an application may load instructions into the CPU 682, for example load some of the instructions of the application into a cache of the CPU 682. In some contexts, an application that is executed may be said to configure the CPU 682 to do something, e.g., to configure the CPU 682 to perform the function or functions promoted by the subject application. When the CPU 682 is configured in this way by the application, the CPU 682 becomes a specific purpose computer or a specific purpose machine.
[00179] The secondary storage 684 is typically comprised of one or more disk drives or tape drives and is used for non-volatile storage of data and as an over-flow data storage device if RAM 688 is not large enough to hold all working data. Secondary storage 684 may be used to store programs which are loaded into RAM 688 when such programs are selected for execution. The ROM 686 is used to store instructions and perhaps data which are read during program execution. ROM 686 is a non-volatile memory device which typically has a small memory capacity relative to the larger memory capacity of secondary storage 684. The RAM 688 is used to store volatile data and perhaps to store instructions. Access to both ROM 686 and RAM 688 is typically faster than to secondary storage 684. The secondary storage 684, the RAM 688, and/or the ROM 686 may be referred to in some contexts as computer readable storage media and/or non-transitory computer readable media.
[00180] I/O devices 690 may include printers, video monitors, electronic displays (e.g., liquid crystal displays (LCDs), plasma displays, organic light emitting diode displays (OLED), touch sensitive displays, etc.), keyboards, keypads, switches, dials, mice, track balls, voice recognizers, card readers, paper tape readers, or other well-known input devices.
[00181] The network connectivity devices 692 may take the form of modems, modem banks, Ethernet cards, universal serial bus (USB) interface cards, serial interfaces, token ring cards, fiber distributed data interface (FDDI) cards, wireless local area network (WLAN) cards, radio transceiver cards that promote radio communications using protocols such as code division multiple access (CDMA), global system for mobile communications (GSM), long-term evolution (LTE), worldwide interoperability for microwave access (WiMAX), near field communications (NFC), radio frequency identity (RFID), and/or other air interface protocol radio transceiver cards, and other well-known network devices. These network connectivity devices 692 may enable the processor 682 to communicate with the Internet or one or more intranets. With such a network connection, it is contemplated that the processor 682 might receive information from the network, or might output information to the network (e.g., to an event database) in the course of performing the above-described method steps. Such information, which is often represented as a sequence of instructions to be executed using processor 682, may be received from and outputted to the network, for example, in the form of a computer data signal embodied in a carrier wave.
[00182] Such information, which may include data or instructions to be executed using processor 682 for example, may be received from and outputted to the network, for example, in the form of a computer data baseband signal or signal embodied in a carrier wave. The baseband signal or signal embedded in the carrier wave, or other types of signals currently used or hereafter developed, may be generated according to several known methods. The baseband signal and/or signal embedded in the carrier wave may be referred to in some contexts as a transitory signal. [00183] The processor 682 executes instructions, codes, computer programs, scripts which it accesses from hard disk, floppy disk, optical disk (these various disk based systems may all be considered secondary storage 684), flash drive, ROM 686, RAM 688, or the network connectivity devices 692. While only one processor 682 is shown, multiple processors may be present. Thus, while instructions may be discussed as executed by a processor, the instructions may be executed simultaneously, serially, or otherwise executed by one or multiple processors. Instructions, codes, computer programs, scripts, and/or data that may be accessed from the secondary storage 684, for example, hard drives, floppy disks, optical disks, and/or other device, the ROM 686, and/or the RAM 688 may be referred to in some contexts as non-transitory instructions and/or non-transitory information.
[00184] In an embodiment, the computer system 680 may comprise two or more computers in communication with each other that collaborate to perform a task. For example, but not by way of limitation, an application may be partitioned in such a way as to permit concurrent and/or parallel processing of the instructions of the application. Alternatively, the data processed by the application may be partitioned in such a way as to permit concurrent and/or parallel processing of different portions of a data set by the two or more computers. In an embodiment, virtualization software may be employed by the computer system 680 to provide the functionality of a number of servers that is not directly bound to the number of computers in the computer system 680. For example, virtualization software may provide twenty virtual servers on four physical computers. In an embodiment, the functionality disclosed above may be provided by executing the application and/or applications in a cloud computing environment. Cloud computing may comprise providing computing services via a network connection using dynamically scalable computing resources. Cloud computing may be supported, at least in part, by virtualization software. A cloud computing environment may be established by an enterprise and/or may be hired on an as-needed basis from a third party provider. Some cloud computing environments may comprise cloud computing resources owned and operated by the enterprise as well as cloud computing resources hired and/or leased from a third party provider.
[00185] In an embodiment, some or all of the functionality disclosed above may be provided as a computer program product. The computer program product may comprise one or more computer readable storage medium having computer usable program code embodied therein to implement the functionality disclosed above. The computer program product may comprise data structures, executable instructions, and other computer usable program code. The computer program product may be embodied in removable computer storage media and/or non-removable computer storage media. The removable computer readable storage medium may comprise, without limitation, a paper tape, a magnetic tape, magnetic disk, an optical disk, a solid state memory chip, for example analog magnetic tape, compact disk read only memory (CD-ROM) disks, floppy disks, jump drives, digital cards, multimedia cards, and others. The computer program product may be suitable for loading, by the computer system 680, at least portions of the contents of the computer program product to the secondary storage 684, to the ROM 686, to the RAM 688, and/or to other non volatile memory and volatile memory of the computer system 680. The processor 682 may process the executable instructions and/or data structures in part by directly accessing the computer program product, for example by reading from a CD-ROM disk inserted into a disk drive peripheral of the computer system 680. Alternatively, the processor 682 may process the executable instructions and/or data structures by remotely accessing the computer program product, for example by downloading the executable instructions and/or data structures from a remote server through the network connectivity devices 692. The computer program product may comprise instructions that promote the loading and/or copying of data, data structures, files, and/or executable instructions to the secondary storage 684, to the ROM 686, to the RAM 688, and/or to other non-volatile memory and volatile memory of the computer system 680.
[00186] In some contexts, the secondary storage 684, the ROM 686, and the RAM 688 may be referred to as a non-transitory computer readable medium or a computer readable storage media. A dynamic RAM embodiment of the RAM 688, likewise, may be referred to as a non-transitory computer readable medium in that while the dynamic RAM receives electrical power and is operated in accordance with its design, for example during a period of time during which the computer system 680 is turned on and operational, the dynamic RAM stores information that is written to it. Similarly, the processor 682 may comprise an internal RAM, an internal ROM, a cache memory, and/or other internal non-transitory storage blocks, sections, or components that may be referred to in some contexts as non-transitory computer readable media or computer readable storage media. [00187] Also disclosed herein is a system for identifying events within a wellbore 114. The system comprises: a memory (e.g., RAM 688, ROM 686); an identification program stored in the memory; and a processor 682, wherein the identification program, when executed on the processor 682, configures the process to: receive a first set of measurements of a first signal within a wellbore 114; identify one or more events within the wellbore 114 using the first set of measurements; receive a second set of measurements of a second signal within the wellbore 114, wherein the first signal and the second signal represent different physical measurements; train one or more event models using the second set of measurements and the identification of the one or more events as inputs; and use the one or more event models to identify at least one additional event within the wellbore 114.
[00188] As described hereinabove, in embodiments, the one or more events comprise inflow events, leak events, sand ingress events, or any combination thereof. The second set of measurements can comprise acoustic measurements from the wellbore 114, and/or the first set of measurements can be received from at least one of distributed temperature sensor (DTS) measurements, production logging tool (PLT) measurements, flow meter measurements, or pressure sensor measurements. The first set of measurements and the second set of measurements can be from a same time interval, or from different time intervals.
[00189] The processor 682 can be further configured to: create labeled data using the identified one or more events and the second set of measurements. In aspects, the processor 682 is further configured to: use the first set of measurements with one or more wellbore event models; and identify the one or more events with the one or more wellbore event models. In some such embodiments, the processor 682 can be further configured to: monitor the first signal within the wellbore 114; monitor the second signal within the wellbore 114; use the first signal in the one or more wellbore event models; use the second signal in the one or more event models; and detect the one or more events based on outputs of both the one or more wellbore event models and the one or more event models.
[00190] Also disclosed herein is a system for predicting wellbore sensor data. The system comprises: a memory (e.g., RAM 688, ROM 686); a prediction program stored in the memory; and a processor 682, wherein the prediction program, when executed on the processor 682, configures the process to: receive a first set of measurements of a first signal, wherein the first set of measurements originate from within a wellbore 114; identify one or more events within the wellbore 114 using the first set of measurements; receive a second set of measurements of a second signal, wherein the second set of measurements originate from within the wellbore 114, wherein the first signal and the second signal represent different physical measurements; train one or more event models using the second set of measurements and the identification of the one or more events as inputs; identify, using the one or more event models, one or more additional events within the wellbore 114; use the one or more additional events with one or more formation properties; and determine a third set of measurements in response to combining the one or more additional events with the formation properties, wherein the third set of measurements represent predicted physical parameters within the wellbore 114, wherein the third set of measurements represents a third signal that is different than the first signal and the second signal.
[00191] In aspects, the prediction program is further configured to: identify, using the one or more event models, one or more additional events within the wellbore 114. As noted hereinabove with reference to FIG. 7, the third set of measurements can be, for example, predicted pressure measurements along the wellbore 114, and/or predicted flow measurements along the wellbore 114. The second set of measurements can comprise acoustic measurements obtained within the wellbore 114. The one or more events can comprise inflow events, leak events, sand ingress events, or any combination thereof. The first set of measurements can comprise at least one of distributed temperature sensor (DTS) measurements, production logging tool (PLT) measurements, flow meter measurements, or pressure sensor measurements. The first set of measurements and the second set of measurements can be obtained simultaneously, or at different time intervals.
[00192] The prediction program can be further configured to: create labeled data using the identified one or more events and the second set of measurements.
[00193] As detailed hereinabove, a first set of measurements from a wellbore 114 can be utilized to train one or more event models operable with a second set of measurements from a wellbore 114. The first set of measurements and the second set of measurements can be obtained from the same wellbore 114, or another same or similar wellbore 114 (e.g., having a same completion type and/or in a same or similar formation). Utilizing local data as reference for training the one or more event models can simplify the use of the one or more event models and subsequently (i.e., after training the one or more event models), the trained one or more event models can be utilized alone or in conjunction with the first set of measurements (e.g., with one or more wellbore event models therefor) to identify at least one additional event in the or another wellbore 114. In aspects, the trained one or more event models can be utilized in conjunction with the first set of measurements (e.g., with one or more wellbore event models therefor) to provide additional information beyond information either the one or more event models or the one or more wellbore event models can provide independently, and/or to provide validation of the outputs from the one or more event models and/or the one or more wellbore event models. For example, when the first set of measurements comprises DTS data and the second set of measurements comprises DAS data, the one or more event models can be trained using the second set of measurements and the identification of the one or more events provided by the first set of measurements, and subsequently, the one or more trained event models can be utilized to determine the presence or absence of an influx of liquid along with influx of gas where the one or more wellbore event models (e.g., the DTS data) indicate influx of fluid, but cannot specify liquid and/or gas. In this manner, for example, influx of liquid can be decoupled from influx of gas. The system and method of identifying events in a wellbore as disclosed herein can thus be utilized to provide more information than can typically be provided by the one or more wellbore event models and/or the one or more event models alone, and/or can be utilized to build confidence in the outputs thereof. [00194] Furthermore, the system and method of wellbore sensor data allows the first set of measurements and the second set of measurements to be utilized to predict a third set of measurements. For example, in aspects, the first set of measurements comprises DTS data and the second set of measurements comprises DAS data, and the DAS/DTS data are utilized as detailed herein to generate synthetic thermal profiles (e.g., predicted DTS data in another wellbore) and/or synthetic pressure data (e.g., DPS) data. For example, DTS data can be utilized to train one or more event models that utilize DAS measurements, and the trained model subsequently utilized in the or another well to predict and/or validate DPS data. In aspects, the synthetic or predicted data can be utilized to cross check data. For example, in aspects, predicted or synthetic pressure data can be utilized to cross validate obtained PLT data.
[00195] The herein disclosed systems and methods can be utilized within a well and/or across wells and/or fields to determine where to place additional wells and/or to optimize production from the well(s).
[00196] Having described various systems and methods, certain aspects can include, but are not limited to: [00197] In a first aspect, a method of identifying events within a wellbore comprises: identifying one or more events within the wellbore; obtaining a first set of measurements comprising a first signal within the wellbore associated with the identified one or more event; training one or more event models using the second set of measurements and the identification of the one or more events as inputs; and using the one or more event models to identify at least one additional event.
[00198] A second aspect can include the method of the first aspect, further comprising: obtaining a second set of measurements comprising a second signal within a wellbore, wherein identifying the one or more events within the wellbore comprises identifying the one or more events within the wellbore using the second set of measurements, and wherein the first signal and the second signal represent different physical measurements.
[00199] A third aspect can include the method of the first or second aspect, wherein identifying the one or more events within the wellbore comprises using an identity of the one or more events based on a known event or induced event within the wellbore.
[00200] A fourth aspect can include the method of the first or second aspect, wherein the first set of measurements comprises acoustic measurements obtained within the wellbore.
[00201] A fifth aspect can include the method of any one of the first to fourth aspects, wherein the one or more events comprise a fluid inflow event a, a fluid outflow event, a fluid flow event within the wellbore, a fluid injection event, a fluid phase flow, a mixed phase flow, a leak event, a well integrity event, an, annular fluid flow event, an overburden event, a fluid induced hydraulic fracture event, sand detection event, or any combination thereof.
[00202] A sixth aspect can include the method of any one of the second to fifth aspects, wherein the second set of measurements comprise at least one of an acoustic sensor measurement, a temperature sensor measurement, a flow sensor measurement, a pressure sensor measurement, a strain sensor measurement, a position sensor measurement, a current meter measurement, a level sensor measurement, a phase sensor measurement, a composition sensor measurement, an optical sensor measurement, an image sensor measurement, or any combination thereof [00203] A seventh aspect can include the method of any one of the first to sixth aspects, further comprising: creating labeled data using the identified one or more events and the first set of measurements. [00204] An eighth aspect can include the method of any one of the first to seventh aspects, wherein the first set of measurements and the second set of measurements are obtained simultaneously.
[00205] A ninth aspect can include the method of any one of the first to eighth aspects, wherein the first set of measurements and the second set of measurements are obtained at different time intervals.
[00206] A tenth aspect can include the method of any one of the second to ninth aspects, wherein identifying the one or more events comprises: using the second set of measurements with one or more wellbore event models; and identifying the one or more events with the one or more wellbore event models.
[00207] An eleventh aspect can include the method of the tenth aspect, further comprising: monitoring the first signal within the wellbore; monitoring the second signal within the wellbore; using the second signal in the one or more wellbore event models; using the first signal in the one or more event models; and detecting the at least one additional event based on outputs of both the one or more wellbore event models and the one or more event models.
[00208] A twelfth aspect can include the method of any one of the first to eleventh aspects, wherein the one or more event models are one or more pre-trained event models , and wherein training the one or more event models using the first set of measurements and the identification of the one or more events as inputs comprises: calibrating the one or more pre-trained event models using the first set of measurements and the identification of the one or more events as inputs; and updating at least one parameter of the one or more pre-trained event models in response to the calibrating.
[00209] A thirteenth aspect can include the method of any one of the first to twelfth aspects, further comprising: obtaining a third set of measurements comprising a third signal within a wellbore, wherein the third signal and the first signal represent different physical measurements, and wherein the third set of measurements represent the at least one additional event; and training one or more additional event models using the third set of measurements and the identification of the at least one addition event as inputs.
[00210] A fourteenth aspect can include the method of the thirteenth aspect, wherein identifying the one or more events within the wellbore using the first set of measurements comprises: using the one or more additional event models to identify the one or more events within the wellbore, and wherein training the one or more additional event models using the third set of measurements and the identification of the at least one additional event as inputs comprises: retaining the one or more additional event models using the third set of measurements and the identification of the at least one additional event as inputs.
[00211] In a fifteenth aspect, a system for identifying events within a wellbore comprises: a memory; an identification program stored in the memory; and a processor, wherein the identification program, when executed on the processor, configures the process to: identify one or more events within the wellbore; receive a first set of measurements of a first signal within the wellbore; train one or more event models using the first set of measurements and the identification of the one or more events as inputs; and use the one or more event models to identify at least one additional event.
[00212] A sixteenth aspect can include the system of the fifteenth aspect, wherein the identification program further configures the processor to: receive a second set of measurements comprising a second signal, wherein the identification of the one or more events within the wellbore comprises an identification of the one or more events within the wellbore based on the second set of measurements, and wherein the first signal and the second signal represent different physical measurements.
[00213] A seventeenth aspect can include the system of the fifteenth or sixteenth aspect, wherein the identification of the one or more events within the wellbore comprises receiving an identity of the one or more events based on a known event or induced event within the wellbore.
[00214] An eighteenth aspect can include the system of any one of the fifteenth to seventeenth aspects, wherein the first set of measurements comprise acoustic measurements from the wellbore. [00215] A nineteenth aspect can include the system of any one of the fifteenth to eighteenth aspects, wherein the one or more events comprise a fluid inflow event a, a fluid outflow event, a fluid flow event within the wellbore, a fluid injection event, a fluid phase flow, a mixed phase flow, a leak event, a well integrity event, an, annular fluid flow event, an overburden event, a fluid induced hydraulic fracture event, sand detection event, or any combination thereof.
[00216] A twentieth aspect can include the system of any one of the fifteenth to nineteenth aspects, wherein the second set of measurements are received from at least one of an acoustic sensor, a temperature sensor, a flow sensor, a pressure sensor, a strain sensor, a position sensor, a current meter, a level sensor, a phase sensor, a composition sensor, an optical sensor, an image sensor, or any combination thereof.
[00217] A twenty first aspect can include the system of any one of the fifteenth to twentieth aspects, wherein the processor is further configured to: create labeled data using the identified one or more events and the first set of measurements.
[00218] A twenty second aspect can include the system of any one of the fifteenth to twenty first aspects, wherein the first set of measurements and the second set of measurements are from a same time interval.
[00219] A twenty third aspect can include the system of any one of the sixteenth to twenty first aspects, wherein the first set of measurements and the second set of measurements are from different time intervals.
[00220] A twenty fourth aspect can include the system of any one of the sixteenth to twenty third aspects, wherein the processor is further configured to: use the second set of measurements with one or more wellbore event models; and identify the one or more events with the one or more wellbore event models.
[00221] A twenty fifth aspect can include the system of the twenty fourth aspect, wherein the processor is further configured to: monitor the first signal within the wellbore; monitor the second signal within the wellbore; use the second signal in the one or more wellbore event models; use the first signal in the one or more event models; and detect the one or more events based on outputs of both the one or more wellbore event models and the one or more event models.
[00222] A twenty sixth aspect can include the system of any one of the fifteenth to twenty fifth aspects, wherein the one or more event models are one or more pre-trained event models, and wherein the processor is further configured to: calibrate the one or more pre-trained event models using the first set of measurements and the identification of the one or more events as inputs; and update at least one parameter of the one or more pre-trained event models in response to the calibrating.
[00223] In a twenty seventh aspect, a method of identifying events within a wellbore comprises: obtaining a first set of measurements of a first signal within a wellbore; identifying one or more events within the wellbore using the first set of measurements, wherein the one or more events comprise a gas phase inflow, a liquid phase inflow, or sand ingress into the wellbore; obtaining an acoustic data set from within the wellbore, wherein the first signal is not an acoustic signal; training one or more fluid inflow models using the acoustic data set and the identification of the one or more events as inputs; and using the trained one or more fluid inflow models to identify at least one additional fluid inflow event.
[00224] A twenty eighth aspect can include the method of the twenty seventh aspect, wherein the first set of measurements comprises distributed temperature sensor measurements.
[00225] A twenty ninth aspect can include the method of the twenty seventh or twenty eighth aspect, wherein the first set of measurements comprise production volumetric information. [00226] A thirtieth aspect can include the method of any one of the twenty seventh to twenty ninth aspects, wherein identifying the one or more events within the wellbore comprises: identifying a first location having a first event of the one or more events; and identifying the first event at the first location using one or more wellbore event models.
[00227] A thirty first aspect can include the method of the thirtieth aspect, wherein training the one or more fluid inflow models comprises: obtaining acoustic data for the first location from the acoustic data set; and training the one or more fluid inflow models using the acoustic data for the first location and the identification of the first event at the first location.
[00228] A thirty second aspect can include the method of the thirty first aspect, wherein using the trained one or more fluid inflow models to identify the at least one additional fluid inflow event within the wellbore comprises using the one or more trained fluid inflow models to identify the at least one additional fluid inflow event along the length of the wellbore.
[00229] The embodiments disclosed herein have included systems and methods for identifying events and for predicting sensor data within a subterranean wellbore, or a plurality of such wellbores. Thus, through use of the systems and methods described herein, one may more effectively enhance the economic production therefrom.
[00230] While exemplary embodiments have been shown and described, modifications thereof can be made by one skilled in the art without departing from the scope or teachings herein. The embodiments described herein are exemplary only and are not limiting. Many variations and modifications of the systems, apparatus, and processes described herein are possible and are within the scope of the disclosure. Accordingly, the scope of protection is not limited to the embodiments described herein, but is only limited by the claims that follow, the scope of which shall include all equivalents of the subject matter of the claims. Unless expressly stated otherwise, the steps in a method claim may be performed in any order. The recitation of identifiers such as (a), (b), (c) or (1), (2), (3) before steps in a method claim are not intended to and do not specify a particular order to the steps, but rather are used to simplify subsequent reference to such steps.
Next Patent: A PLATE HAVING A VENTILATION CHANNEL