PRIORITY DOCUMENTS

[0001] The present application claims priority from Australian Provisional Patent Application No. 2021900659 titled “PIPELINE ANOMALY DETECTION METHOD AND SYSTEM” and filed on 9 March 2021, the content of which is hereby incorporated by reference in its entirety.

CROSS-REFERENCE TO CO-PENDING APPLICATIONS

[0002] The following co-pending patent applications are related to the present application:

PCT Application No PCT/AU2019/000148 (W02020102846) titled “METHOD AND SYSTEM TO ANALYSE PIPELINE CONDITION”, filed on 22 November 2019 in the name of The University of Adelaide;

PCT Application No PCT/AU2020/000080 (WO2021022315) titled “METHOD AND SYSTEM TO MONITOR PIPELINE CONDITION, filed on 3 August 2020 in the name of The University of Adelaide; and

PCT Application No PCT/AU2016/000246 (WO2017008100) titled “SYSTEM AND METHOD FOR GENERATION OF A PRESSURE SIGNAL”, filed on 8 July 2016 in the name of the University of Adelaide.

[0003] The contents of the above co-pending applications are incorporated by reference in their entirety.

TECHNICAL FIELD

[0004] The present disclosure relates to the detection of anomalies in a pipeline carrying a fluid. In a particular form, the present disclosure relates to the use of artificial neural networks to analyse transient pressure information to detect anomalies in a pipeline.

BACKGROUND

[0005] The Applicant has previously developed methods and systems for determining the condition of a pipeline based on measuring transient pressure information from the pipeline and then processing this information to determine the presence of an anomaly or fault based on specifically configured artificial neural networks (ANN).

[0006] In one implementation described in PCT Application No PCT/AU2019/000148 (W02020102846) titled “METHOD AND SYSTEM TO ANALYSE PIPELINE CONDITION”, filed on 22 November 2019 in the name of The University of Adelaide, whose contents are incorporated by reference in their entirety in the present disclosure, the detection system involves the generation of a transient pressure wave in the pipeline and then the real time processing of the resulting transient pressure wave interaction signal measured in the pipeline by an ANN trained to detect the presence of the anomaly. In one example implementation, the anomaly detector ANN is both trained and operates on downsampled pressure information which allows the detection process to occur in real time.

[0007] In another implementation, described in PCT Application No PCT/AU2020/000080 (WO2021022315) titled “METHOD AND SYSTEM TO MONITOR PIPELINE CONDITION, filed on 3 August 2020 in the name of The University of Adelaide, whose contents are incorporated by reference in their entirety in the present disclosure, the detection system functions to monitor continuously pipeline pressure information and applies a first classifier ANN to this information to determine the overall condition of the pipeline and if an anomaly is detected, a second anomaly detector ANN functions to determine the type of anomaly and its associated anomaly characteristics.

[0008] While both of these previous implementations have performed well in many applications, there is always the requirement to improve the performance of the anomaly detection system or at least provide alternative approaches that may be used in different applications. In one example, the analysed system might be exposed to background noise, as a result preventing existing techniques from performing as well as required. In another example, the focus may be further improving the performance of an ANN for a specific anomaly detection task.

SUMMARY

[0009] In one aspect, the present disclosure provides a method for detecting an anomaly in a pipeline, comprising: generating a transient pressure wave in a fluid carried along the pipeline; measuring a transient pressure wave interaction signal corresponding to a response from the anomaly to the generated transient pressure wave; processing the transient pressure wave interaction signal to detect the anomaly by a series of artificial neural networks (ANNs) each trained to detect the anomaly on respective datasets of noise modulated training data; and determining a performance measure characterising the detection of the anomaly based on anomaly detection results from each of the ANNs.

[0010] In another form, a dataset of noise modulated training data is generated in accordance with a characteristic pressure noise signal that is based on the pipeline and an anomaly type of the anomaly that the ANN is trained to detect. [0011] In another form, generating a dataset of noise modulated training data in accordance with the characteristic pressure noise signal comprises: generating for the anomaly type a plurality of pressure wave interaction signals covering a range of anomaly characteristics associated with the anomaly type; determining a representative pressure fluctuation value based on the pipeline and the anomaly type; determining a characteristic pressure noise signal based on the representative pressure fluctuation value; and modulating the plurality of pressure wave interaction signals by the characteristic pressure noise signal to generate the dataset of noise modulated training data.

[0012] In another form, determining a representative pressure fluctuation value comprises comparing a first transient pressure wave interaction signal where there is no anomaly in the pipeline with a second transient pressure wave interaction signal where the pipeline has the anomaly.

[0013] In another form, determining the characteristic pressure noise signal based on the representative pressure fluctuation value comprises forming a Gaussian distribution function having a zero mean and a standard deviation defined as a multiple of the representative pressure fluctuation value.

[0014] In another form, additional datasets of noise modulated training data that comprise the respective datasets of noise modulated training data are generated by additionally modulating the plurality of pressure wave interaction signals by the characteristic pressure noise signal to generate each additional dataset of noise modulated training data.

[0015] In another form, each of the respective datasets of noise modulated training data is divided into a training dataset for training a respective ANN of the series of ANNs and a testing dataset for testing and/or validating the respective ANN.

[0016] In another form, the method further comprises pre-processing the transient pressure wave interaction signal following measurement of the pressure wave interaction signal to remove signal artefacts arising from generating the transient pressure wave.

[0017] In another form, the signal artefact arising from generating of the transient pressure wave is an increased pressure variability in a portion of the pressure wave interaction signal corresponding to prior to generation of the transient pressure wave and pre-processing the transient pressure wave interaction signal comprises reducing the pressure variability in that portion of the pressure wave interaction signal. [0018] In another form, the method further comprises pre-processing the transient pressure wave interaction signal following measurement by offsetting the pressure wave interaction signal to more closely conform with the pressure wave interaction signals used to train the ANNs.

[0019] In another form, the performance measure assesses a variability of the anomaly detection results.

[0020] In another form, the method further comprises verifying the anomaly detection results.

[0021] In a second aspect, the present disclosure provides a system for detecting an anomaly in a pipeline, the system including: a transient pressure wave generator for generating a transient pressure wave in fluid carried along the pipeline; a pressure detector for measuring a transient pressure wave interaction signal corresponding to a response from the anomaly to the generated transient pressure wave; an analysis module comprising one or more data processors configured for: processing the transient pressure wave interaction signal to detect the anomaly by a series of artificial neural networks (ANNs) each trained to detect the anomaly on respective sets of noise modulated training data; and determining a performance measure characterising the detection of the anomaly based on anomaly detection results from each of the ANNs.

[0022] In another form, a dataset of noise modulated training data is generated in accordance with a characteristic pressure noise signal that is based on the pipeline and an anomaly type of the anomaly that the ANN is trained to detect.

[0023] In another form, generating a dataset of noise modulated training data in accordance with the characteristic pressure noise signal comprises: generating for the anomaly type a plurality of pressure wave interaction signals covering a range of anomaly characteristics associated with the anomaly type; determining a representative pressure fluctuation value based on the pipeline and the anomaly type; determining a characteristic pressure noise signal based on the representative pressure fluctuation value; modulating the plurality of pressure wave interaction signals by the characteristic pressure noise signal to generate the dataset of noise modulated training data. [0024] In another form, determining a representative pressure fluctuation value comprises comparing a first transient pressure wave interaction signal where there is no anomaly in the pipeline with a second transient pressure wave interaction signal where the pipeline has the anomaly.

[0025] In another form, determining the characteristic pressure noise signal based on the representative pressure fluctuation value comprises forming a Gaussian distribution function having a zero mean and a standard deviation defined as a multiple of the representative pressure fluctuation value.

[0026] In another form, additional datasets of noise modulated training data that comprise the respective datasets of noise modulated training data are generated by additionally modulating the plurality of pressure wave interaction signals by the characteristic pressure noise signal to generate each additional dataset of noise modulated training data.

[0027] In another form, each of the respective datasets of noise modulated training data is divided into a training dataset for training a respective ANN of the series of ANNs and a testing dataset for testing and/or validating the respective ANN.

[0028] In another form, the system further comprises pre-processing the transient pressure wave interaction signal following measurement of the pressure wave interaction signal to remove signal artefacts arising from generating the transient pressure wave.

[0029] In another form, the signal artefact arising from generating of the transient pressure wave is an increased pressure variability in a portion of the pressure wave interaction signal corresponding to prior to generation of the transient pressure wave and pre-processing the transient pressure wave interaction signal comprises reducing the pressure variability in that portion of the pressure wave interaction signal.

[0030] In another form, the system further comprises pre-processing the transient pressure wave interaction signal following measurement by offsetting the pressure wave interaction signal to more closely conform with the pressure wave interaction signals used to train the ANNs.

[0031] In another form, the performance measure assesses a variability of anomaly detection results.

[0032] In another form, the analysis module is further configured for verifying the anomaly detection results.

[0033] In a third aspect, the present disclosure provides a system for detecting an anomaly in a pipeline comprising means configured to carry out a method in accordance with the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0034] Embodiments of the present disclosure will be discussed with reference to the accompanying drawings wherein:

[0035] Figure 1 is a flowchart of a method for detecting an anomaly in a pipeline in accordance with an illustrative embodiment;

[0036] Figure 2 is a system overview diagram of an anomaly detection system for detecting an anomaly in a pipeline in accordance with an illustrative embodiment;

[0037] Figure 3 is a pipeline model for training the ANN to determine an anomaly in a pipeline in accordance with an illustrative embodiment;

[0038] Figure 4 is a flowchart of a method for generating noise modulated training data in accordance with an illustrative embodiment;

[0039] Figure 5 is a plot of two transient pressure wave interaction signals comparing the pipeline response for an intact pipeline with a pipeline having a small leak to determine a representative noise in accordance with an illustrative embodiment;

[0040] Figures 6a and 6b are plots of the average leak location organised by leak size for an ANN trained with original training data (ie, Figure 6a) and an ANN trained with noise modulated data (ie, Figure 6b) in accordance with an illustrative embodiment;

[0041] Figures 7a-d are a series of plots depicting the original transient pressure wave interaction signal overlayed with a corresponding noise modulated transient pressure wave interaction signal in accordance with an illustrative embodiment;

[0042] Figure 8 is a data flow diagram showing figuratively the training of a series of ANNs on respective sets of noise modulated training data in accordance with an illustrative embodiment;

[0043] Figure 9 is a flowchart of a method for detecting an anomaly in a pipeline in accordance with another illustrative embodiment;

[0044] Figure 10 is a flowchart showing example pre-processing steps for the transient pressure wave interaction signal in accordance with an illustrative embodiment; [0045] Figure 11 is a plot showing the results of a sensitivity analysis conducted on an ANN trained to detect an anomaly in accordance with an illustrative embodiment;

[0046] Figure 12 is a plot of a measured transient pressure wave interaction signal following the generation of a transient pressure wave showing in detail the pressure fluctuations before and after generation of the transient pressure wave in accordance with an illustrative embodiment;

[0047] Figure 13 is a plot of the distributions of pressure head for the (a) and (b) regions shown in Figure

12;

[0048] Figure 14 is a plot of the cumulative distribution function (CDF) for the (a) region shown in Figure 12 and a modified CDF having the same mean but with the standard deviation of the (b) region;

[0049] Figure 15 is a figurative view of a pipeline arrangement for experimental confirmation in accordance with an illustrative embodiment;

[0050] Figure 16 is a plot of the measured transient pressure wave interaction signals obtained from the pipeline arrangement illustrated in Figure 15 in accordance with an illustrative embodiment;

[0051] Figure 17 is a figurative view of the different series of ANNs trained on respective sets of noise modulated training data in accordance with an illustrative embodiment;

[0052] Figures 18a-g is a series of plots illustrating the percentage of exceedance associated with the absolute average error for the location of a leak following training and testing for each noise intensity according to an illustrative embodiment;

[0053] Figure 19 is a plot showing the measured transient pressure wave interaction signals in Figure 16 following pre-processing in accordance with an illustrative embodiment;

[0054] Figures 20 to 26 are plots of the distribution of predictions for determining the location of a leak for each of the transient pressure wave signals illustrated in Figure 19 following the processing by a series of ANNs trained on noise modulated training data having different noise intensities in accordance with an illustrative embodiment;

[0055] Figure 27 is a plot of the performance of the trained ANNs on the measured and processed transient pressure wave signals illustrated in Figure 19 for each noise intensity in accordance with an illustrative embodiment; [0056] Figure 28 is a plot of the average values (in circles) and distributions of the Root Mean Square Error (RMSE) for the training (in lighter shade) and the testing (in black) of the trained anomaly detector ANNs for each noise intensity in accordance with an illustrative embodiment;

[0057] Figure 29 is a plot of the error in RMSE (in circles) and the range for the prediction of a leak location (whiskers) for the training (in lighter shade) and the testing (in black) of the trained anomaly detector ANNs for each noise intensity in accordance with an illustrative embodiment; and

[0058] Figure 30 is a plot comparing the predicted transient pressure wave interaction signal obtained by numerically generating the expected trace based on the determined anomaly characteristics with the measured transient pressure wave interaction signal used to determine the anomaly characteristics in accordance with an illustrative embodiment.

[0059] In the following description, like reference characters designate like or corresponding parts throughout the figures.

DESCRIPTION OF EMBODIMENTS

[0060] Referring now to Figure 1, there is shown a flowchart of a method 100 for detecting an anomaly in a pipeline. As would be appreciated, the present method and system is applicable to any fluid carrying pipeline system or network including, but not limited to, water transmission pipes, pipelines in chemical plants, wastewater pumping pipelines or oil and gas pipelines.

[0061] Throughout this specification, the term “anomaly” is taken to mean any feature or component of the pipeline that affects the hydraulic performance of the pipeline. An anomaly may be classified under different anomaly types, including, but not limited to, the following anomaly types:

• a short reach in the pipeline with significant wall deterioration;

• a leak;

• a burst;

• a blockage;

• a change in pipeline material;

• an illegal pipeline consumption; or

• an air pocket.

[0062] An anomaly may also involve associated characteristics that characterise the anomaly. As a non limiting example, the anomaly may be of the type “leak” and the associate anomaly characteristics may include the location of the “leak”, the size of the “leak” and the flow rate of fluid exiting the pipeline as a result of the “leak”. [0063] At step 110 of Figure 1, a transient pressure wave is generated in the fluid carried along the pipeline by in this example a pressure wave generator. Referring also to Figure 2, there is shown an anomaly detection system 200 for detecting an anomaly in a pipeline according to an illustrative embodiment operable to implement method 100. In this illustrative embodiment, anomaly detection system 200 includes a transient pressure wave generator 205 for generating a transient pressure wave in the fluid of the pipeline and a pressure sensor or detector 210 in the form of a pressure or acoustic transducer for detecting the transient pressure wave interaction signal. System 200 further includes an analysis and control module 220 for processing of the transient pressure wave interaction signal to analyse a region of interest of the pipeline. In one example, anomaly detection system 200 may also control the operation of pressure wave generator 205.

[0064] This transient pressure wave may be generated in the fluid by any one of a number of techniques. In the example of a water transmission pipeline, a transient pressure wave may be generated at a device attached to, for example, an existing scour or fire plug air valve or offtake valve and then abruptly stopping the flow of water. This has the effect of progressively stopping or altering the flow of water along the pipe that had been previously established. This progressive stopping or alteration of the flow of water along the pipeline is equivalent to the generation of a transient pressure wave resulting in the propagation of a transient wavefront along the pipeline.

[0065] Other means to generate a transient pressure wave include, but are not limited to, inline valve closure devices, side discharge valves and piston chambers where an amount of fluid is drawn into a chamber containing a piston which is then operated. One example system for generating a transient pressure wave in fluid carried by the pipeline is described in PCT Application No PCT/AU2016/000246 (W02017008100) titled “SYSTEM AND METHOD FOR GENERATION OF A PRESSURE SIGNAL”, filed by the Applicant here, and whose entire contents are incorporated by reference in their entirety in the present disclosure.

[0066] As referred to above, a popular method for generating the transient pressure wave consists of generating a single step pulse created by the fast closure of a valve within the pipeline system or attached to the system. However, the typical useful bandwidth of this method may be less than 100 Hz, which means that, for some applications, a single pulse may not allow the extraction of enough information from the transient pressure wave interaction signal recorded for the pipeline system. Another transient pressure wave generation method consists of a pulse generation or sine wave stepping technique. The sine wave stepping technique uses a single frequency sinusoidal oscillatory signal as the input, and this frequency is adjusted to cover the range of frequencies required. In other examples, generating a transient pressure wave may include the generation of persistent signals known as pseudo-random binary sequences (PRBS). These signals consist of randomly spaced and equal magnitude pulses that are set to repeat periodically, and have a spectrum similar to that of a single input pulse. This generation method can use Maximum-Length Binary Sequences (MLBS) or Inverse Repeated Sequences (IRS).

[0067] In another example, the hydraulic noise of the system may be used to generate the transient pressure waves in the pipeline for analysis of the pipeline in accordance with the present disclosure. In other examples, customized and small amplitude pressure signals may be obtained from a piezoelectric actuator driven by a linear power amplifier to generate the transient pressure wave. In another example, controlled electrical sparks are employed to generate a vapour cavity that then collapses. An electrical spark surrounded by water causes the development of a localized vapour cavity, the collapse of which induces a transient pressure wave into the surrounding body of fluid having the characteristics of an extremely sharp pressure pulse. This typically results in high frequency pressure waves that can improve the incident signal bandwidth.

[0068] Considering all the available methods for generating a transient pressure wave, the methods and systems presented in this disclosure are applicable irrespective of the transient generation method chosen.

[0069] Referring back to Figure 1, at step 120 a transient pressure wave interaction signal that corresponds to a response from the anomaly to the generated transient pressure wave is measured by in one example pressure sensor or detector 210. The time duration of this transient pressure wave interaction signal that is detected may be selected to cover the first complete cycle of reflections of the transient pressure wave (4 L/a) seconds where L is the length of region of interest of the pipeline and a is the transient wave speed in the fluid. In other examples shown, the time duration is selected to be between 2 L/a and 4L/a seconds, where again L is the length of region of interest of the pipeline and a is the transient wave speed in the fluid. In one example, the time window covers at least 2.5 L/a. In another example, the transient pressure wave interaction signal covers at least 3 L/a. In yet another example, the signal covers at least 3.5 L/a.

[0070] As would be understood, L may be selected to be the entire length of the pipeline and in one example, the boundaries of the analysed transient pressure wave interaction signal would include at least L/a seconds before the generation of the transient pressure wave and at least 2.0 L/a seconds after the transient pressure wave to cover the complete length of the pipeline.

[0071] In this illustrative embodiment, a pressure detector 210 is employed in the form of a pressure or acoustic transducer in combination with a data acquisition capability.

[0072] In terms of the pressure sensor or detector 210, as would be appreciated, any type of high frequency response pressure detector, optical fibre sensor or transducer configured to record the transient pressure wave interaction signal of the pipeline following initiation of a transient pressure wave for a time duration as described above at a selected detection sampling rate or frequency typically between 2,000 Hz and 10,000 Hz may be used. The selection of a detection sampling frequency depends on the pipe wall properties of the pipeline, the wave speed of the fluid and the expected speed of occurrence of the anomaly.

[0073] In other examples, the detection sampling frequency for detecting the transient pressure wave interaction signal may be selected from the following frequency ranges, including, but not limited to, greater than 2 kHz, 2 kHz - 5 kHz, 5 kHz - 10 kHz, 2 kHz - 3 kHz, 3 kHz - 4 kHz, 4 kHz - 5 kHz, 5 kHz - 6 kHz, 6 kHz - 7 kHz, 7 kHz - 8 kHz, 8 kHz - 9 kHz, 9 kHz - 10 kHz, or greater than 10 kHz.

[0074] In this illustrative embodiment, analysis module 220 includes a customised data logging and analysis arrangement comprising a timing module 222 or other clock arrangement which may be GPS based, a data acquisition module 224, data processing module 226 and a remote communications module 228 to convey analysis results to a central location as required. As would be appreciated, the functionality of the various modules may be implemented primarily in hardware or in a combination of hardware and software or primarily in software.

[0075] In one example, the pressure wave generator 205 is deployed remotely from the pressure detector 210 and analysis module 220. In this implementation, the pressure detector 210 and analysis module 220 may together form a “measurement station”. In other example deployments, the pressure wave generator 205 may be co-located together with the pressure detector 210 and/or analysis module 220. As will be described below, other implementations may include multiple measurement stations which will detect the transient pressure wave interaction signal at different locations along the pipeline.

[0076] At step 130, the transient pressure wave interaction signal is processed by a series of artificial neural networks (ANNs) that have each been trained to detect the anomaly of interest on respective sets of noise modulated training data.

[0077] An overview of ANNs and their application to the characterisation of pipelines systems is provided in PCT Application Nos PCT/AU2019/000148 (W02020102846) and PCT/AU2020/000080 (W02021022315) titled “METHOD AND SYSTEM TO ANALYSE PIPELINE CONDITION” and “METHOD AND SYSTEM TO MONITOR PIPELINE CONDITION”, filed on 22 November 2019 and 3 August 2020 respectively in the name Applicant here, whose entire contents are incorporated by reference in the present disclosure.

[0078] In these earlier applications, ID Convolution Network and Dense Network architectures were described. In one example, a ID Convolutional Network architecture with three layers for the ANN was adopted as appropriate for characterising the condition of a pipeline. [0079] In the present disclosure, and in accordance with an exemplary embodiment, a ID Convolutional ANN architecture is also adopted but modified to include: a) four convolutional layers, b) use of Leak Rectified Linear Unit as activation function, c) 20 filters that increase to 30 filters in the last convolutional layer; and d) three dense layers of size 14, 6 and 2.

[0080] The four convolutional layers contain weights connecting each neuron in a layer to neurons in the corresponding neighbourhood in the subsequent layer while in the dense layers each neuron in a layer is connected to every neuron in the subsequent layer. The final shape of the initial convolutional layer depends on the downsampling frequency selected for the generation of the transient wave pressure signal for the ANN training. The rest of the architecture of the ID Convolutional ANN depends on this initial shape following this structure: a) convolutional layer #1 with L neurons corresponding to L values of the downsampled transient pressure wave signals and 20 filters, b) convolutional layer #2 with the same shape size of L neurons corresponding to L values of the downsampled transient pressure wave signals and 20 filters, c) max pooling layer where the resulting shape is U2 neurons corresponding to L values of the downsampled transient pressure wave signals and 20 filters, d) convolutional layer #3 with a shape size of U2 neurons corresponding to L values of the downsampled transient pressure wave signals and 20 filters, e) max pooling layer where the resulting shape is U4 neurons corresponding to L values of the downsampled transient pressure wave signals and 20 filters, f) convolutional layer #4 with a shape size of U4 neurons corresponding to L values of the downsampled transient pressure wave signals and 30 filters, g) max pooling layer where the resulting shape is L/8 neurons corresponding to L values of the downsampled transient pressure wave signals and 30 filters, h) flatten layer that transforms the Convolutional layer #4 into a dense layer with shape L/8 neurons and 30 filters, i) dense layer #1 with size 14 neurons, j) dense layer #2 with size 7 neurons; and k) dense layer #3 with size 2 neurons corresponding to the ANN output.

[0081] In the present disclosure, a new ANN architecture was designed with the analysis of five different alternatives of ID-convolutional neural networks using different number of layers and filters in each layer. These five ANN architectures were trained using two input datasets: one using numerically generated transient pressure wave signals and a second one using these numerical transient pressure wave signals including the addition of a Gaussian distribution of noise. The analysis of the results of these ANN training procedures demonstrated that out of these five ANN architectures, a ID-convolutional ANN with the architecture described above showed more potential of achieving consistent and accurate results for a leak location in a real pipeline and was thus selected as the final ANN architecture.

[0082] As would be appreciated, this ANN architecture evaluation exercise may be carried out for other anomaly types to determine the ANN architecture suitable for the particular anomaly detection requirement. Accordingly, the resulting ANN architecture might have a different number of convolutional, max pooling and/or dense layers, a different distribution of filters across the convolutional layers or a different length of filters. Variations in these parameters will affect the total number of weights as described in Equation 1 below and will modify the predictions of the anomaly location and size.

[0083] In this example, the resulting total number of weights, W, for the ID Convolutional ANN is given by: Equation 1

[0084] where the first term represents the weights in the convolutional layers (n) and the second term the weights in the dense layers (/). In this equation, w and h are the width and height of the filters, f _n is the number of filters in the convolutional layer n and C _j are the number of neurons in the dense layer j.

For the first dense layer (i.e.y = 1), c^_ ₁ will depend on the dimensions of the ANN input set which will correspond to the number of individual data points in the transient pressure wave interaction signal after appropriate sampling.

[0085] In one embodiment, a set of training data corresponding to the anomaly being detected is generated. In one non-limiting example, the anomaly is a leak in the pipeline and the associated anomaly characteristics include the location of the leak as defined with respect to some reference point and the size of leak which is given by an equivalent circular diameter, D _L , of the orifice functioning as the leak source.

[0086] Referring now to Figure 3, there is shown an example pipeline model 300 for generating numerical training data for training the ANN to detect an anomaly 320 in the pipeline 310 according to an illustrative embodiment. In this example, pipeline 310 is supplied by a reservoir 330 with an initial head pressure H ₀ (in metres), where the pipeline 310 has an internal diameter D and a total length L _T . On the downstream end of pipeline 310, there is a side discharge valve G that is initially open with a flow Q ₀ and which functions to generate a transient pressure wave in the fluid in the pipeline on closing. The transient pressure wave response information or interaction signal is obtained from a measurement point (M), which in this example is positioned at the same location as the side discharge valve G.

[0087] In one example, the numerical model used for the generation of the training data is created to replicate the specific characteristics of the analysed pipeline if these are known. However, a particular numerical model can undergo a further non-dimensional transformation which allows the ANN to determine results for any pipeline configuration regardless of its dimensions. One example system for transforming a transient pressure wave interaction signal into a non-dimensional form is described in PCT Application No PCT/AU2019/000148 (W02020102846) titled “METHOD AND SYSTEM TO ANALYSE PIPELINE CONDITION”, filed by the Applicant here, and whose entire contents are incorporated by reference in their entirety in the present disclosure.

[0088] As would be appreciated, an anomaly in the form of a leak could be present at any location along pipeline 310 and additionally the leak could have a range of leak sizes which are modelled as circular orifices having a diameter D _L so the training data is generated to covering the potential range of locations of the leak and sizes of the leak.

[0089] More generally, for other types of anomaly training data would be generated covering a range of associated anomaly characteristics such as the location of the anomaly and any other relevant associated anomaly characteristics that quantify the anomaly and its effect on the pipeline. These characteristics are set out below in a non-exhaustive list of some anomaly characteristics.

[0090] In this example, the training data is a set of numerically generated transient pressure wave interaction signals based on the modelled pipeline response to the generated transient pressure wave from the anomaly by a computational hydrodynamic model. In one embodiment, the computational hydrodynamic model employs the Method of Characteristics (MOC). In accordance with pipeline model 300, input transient pressure wave is modelled as the instantaneous closure of side discharge valve G.

[0091] In other embodiments, the transient characteristics of the generated transient pressure wave may be more closely modelled. As an example, the closure characteristics of the side discharge valve G may be experimentally determined and incorporated into the computational hydrodynamic model. In other examples, where the input transient pressure wave is inputted by other means, eg, mechanical actuator, solenoid activated valve or any other pressure wave generator, the experimentally determined input transient characteristics of the generated transient pressure wave may be incorporated into the computational hydrodynamic model.

[0092] In one example, corresponding to the detection of a leak, 50,000 different transient pressure wave interaction signals are generated by the computational hydrodynamic model corresponding to 5,000 leak locations randomly selected from 5,000 segments into which pipeline 310 has been divided and leak sizes randomly selected from a range of 10 predetermined leak sizes. This range would generally be chosen to cover the expected range of leak sizes given the physical configuration of the pipeline, including its carrying capacity. While in this example, the leak has been parameterised as a circular orifice in other examples, the leak could be parameterised in terms of a flow rate or other suitable physical characteristic of the leak.

[0093] Referring now to Figure 4, there is shown a flowchart of a method 400 for generating noise modulated training data for an ANN according to an illustrative embodiment of the present disclosure. In one example, a dataset of noise modulated training data is generated in accordance with a characteristic pressure noise signal that is based on the pipeline that is being analysed and the type of anomaly of the anomaly that the ANN will be trained to detect.

[0094] Initially, at step 410 training data for the anomaly detection ANN is generated as has been described above. In other embodiments, the training data may be determined empirically by measurements of pipeline systems exhibiting the relevant anomaly which in another example may be combined with numerically generated training data. As a result, a plurality of pressure wave interaction signals are generated that cover the expected range of the anomaly characteristics associated with the anomaly type.

[0095] At step 420, a representative pressure variation is determined based on the pipeline and the type of anomaly that the ANN is being trained to detect. The representative pressure variation is a measure of the variation in pressure that would be expected as a result of the anomaly and provides a basis for determining a characteristic pressure noise signal that may be introduced into the training data. Taking the example of the pipeline 310 shown in Figure 3, with an anomaly in the form of a leak 320, a representative pressure fluctuation may be determined by modelling the change in pressure resulting from the anomaly and/or by empirical measurement and/or by theoretical calculation.

[0096] Referring now to Figure 5, there is shown a plot 500 of two example transient pressure wave interaction signals overlayed with respect to each other where the unit is head pressure in metres (see left hand axis). The first transient pressure wave interaction signal 510 (shown in continuous line) corresponds to the response from a generated transient pressure wave in the form of the closure of the side discharge valve G where there is no anomaly in pipeline 310, ie the pipeline is intact with no anomaly. The second overlayed transient pressure wave interaction signal 520 (shown in dash-dotted line) corresponds to the transient pressure wave response from a generated transient pressure wave in the form of the closure of the side discharge valve G, except now there is a leak 320 in pipeline.

[0097] In this illustrative embodiment, the leak is chosen to be the smallest leak that is of interest to be detected by the anomaly detection method. In another example, typical historical anomalies detected in a particular pipeline or anomalies with the severity of interest to be detected can be used to determine the pressure variation used for the noise generation. Also shown in Figure 5, is the pressure difference 530 Ah between the first and second transient pressure wave interaction signals (shown in dashed line using right hand axis).

[0098] While in this example, first and second transient pressure wave interaction signals 510, 520 have been numerically generated based on pipeline model 300 shown in Figure 3, in other embodiments, these transient pressure wave interaction signals and their difference may be determined empirically by measurement of a pipeline either as deployed or in a laboratory setting or obtained from historical data available from the analysed pipeline to determine a representative pressure fluctuation.

[0099] As can be seen from inspection of Figure 5, the initial pressure increase after the closure of the valve is the same in both cases but differences arise when part of the generated transient pressure wave reflects from the leak 320. It is expected for this type of anomaly that the larger the leak present in the pipeline then the bigger the drop in pressure will be shown. As shown in pressure difference trace 530, there is a difference Ah during the first 2 L/a seconds after the closure of the valve indicated as Ah ₀ . In this manner, Ah ₀ is equivalent to a representative pressure variation of pipeline 310 with respect to an anomaly in the form of a leak. In this example, Ah ₀ is a change in head pressure below which it is expected that a small leak would not be detectable in the transient pressure wave interaction signal.

[00100] Considering this, if any added noise to training data has a standard distribution larger than this representative pressure fluctuation, the normal expectation would be that the trained ANN will not perform well in identifying those small leaks due to the loss of clarity in the transient pressure head trace. As an example of this effect, and referring now to Figures 6a and 6b, there is shown the average leak location organised by leak size for an example numerical pipeline where two ANNs are used to locate and characterise this particular anomaly.

[00101] Plot 610 as shown in Figure 6a is the average leak location error (as a percentage) when an ANN is trained with the original training data without the addition of any noise modulated data. This shows that the ANN performs satisfactorily in determining the location of leaks in numerical pipelines for all leak sizes. Plot 620 in Figure 6b shows the average leak location error (as a percentage) for an ANN trained with the original training data combined with a pressure noise signal with a standard deviation equal to Ah ₀ .

[00102] It is observed that the ability of the ANN to detect leaks with the smaller sizes from the numerical pipeline decreases when noise is added to the signal. However, even for the smallest leaks, the relative error in the leak location is less than 5% and for the rest of the leak sizes it is around 0.5%. This shows that even though the addition of noise to the training data can affect the accuracy of the detection of small leaks, this effect is not significant and the ANN is able to predict the location of anomalies in pipelines experiencing background noise. In this manner, the representative pressure fluctuation is determined by comparing a first transient pressure wave interaction signal where there is no anomaly in the pipeline with a second transient pressure wave interaction signal where the pipeline has the anomaly.

[00103] Referring back to Figure 4, having determined a representative pressure fluctuation value based on the pipeline and the anomaly, at step 430 the next step is to determine a characteristic pressure noise signal that will be used to modulate the original training data to provide the noise modulated training data referred to above.

[00104] In one example, the noise modulated training data comprises the original training data combined with a characteristic pressure noise signal having a variability corresponding to the representative pressure variation of the pipeline as determined above. In one example, the form of the characteristic pressure noise signal is a Gaussian distribution with a zero mean and having a standard deviation s defined by the representative pressure variation referred to above, ie Ah ₀ . In this manner, the standard deviation s is equivalent to a noise intensity as it quantifies the variation of pressure about the mean value. In another example, the standard deviation s is defined by a positive multiple k _n of the representative pressure variation Ah ₀ such as defined below: u _n = k _n Ah ₀ Equation 2

[00105] At step 440, the noise modulated training data is generated by taking one pressure data point from one transient pressure wave interaction signal and adding to that data point a random noise value sampled from the Gaussian distribution forming the characteristic pressure noise signal. This process is then repeated for every pressure data point in each transient pressure wave interaction signal of the original training data to form multiple sets of noise modulated training data. In another example, the form of the characteristic pressure noise signal can be a random, pseudo-random or a chaotic time series. While a random signal with a Gaussian distribution is a good working choice, other signal types and distributions can be used such as Gamma, Beta, Poisson or negative binomial. Essentially those signal distributions that most efficiently cover the parameter phase space are the ones that provide the best performance.

[00106] Referring now to Figures 7 a to 7d, there are shown a series of plots depicting the original transient pressure wave interaction signal comprising the original training data overlayed with the noise modulated transient pressure wave interaction signal which comprises the noise modulated training data that will be used to train the ANNs according to an illustrative embodiment. In this case, moving from Figure 7a to 7d, it can be seen that the value for s, or equivalently the noise intensity, is increasing.

[00107] Referring now to Figure 8, there is shown a data flow diagram 700 showing figuratively the training of a series of ANNs 711, 712, 713, 714, 715 on respective sets of noise modulated training data 720 that in this example has been generated from original training data 710 in accordance with an illustrative embodiment. As would be appreciated, the original training data 710 will comprise a first set of training data consisting of multiple transient pressure wave interaction signals (eg, 50,000) that characterise the anomaly which has either been generated numerically as described above or obtained empirically or a combination of these two sources.

[00108] Multiple sets of noise modulated training data are then generated each based on the original set of training data. Multiple ANNs are then trained on respective sets of noise modulated training data. In the example shown in Figure 8, five separate ANNs are trained on five respective sets of noise modulated training data 720 each, in this example, resulting from the originally generated training data 710. In this manner, additional datasets of noise modulated training data are generated by additionally modulating the plurality of pressure wave interaction signals comprising the original set of training data by the characteristic pressure noise signal.

[00109] In the example where the initial training data consisted of a set of 50,000 different transient pressure wave interaction signals corresponding to pipeline 310 being divided into 5,000 segments in which the leak could occur and further the leak sizes are selected from a range of 10 predetermined leak sizes, then for a series of n ANNs to be trained on respective sets of noise modulated training data there would be total of n X 50,000 noise modulated transient pressure wave signals corresponding to a given noise intensity that would be required. [00110] In one illustrative embodiment, the original noise modulated training data is randomly divided into groups of equal size comprising a reduced set of noise modulated training data and an equal sized set of noise modulated testing data for testing the ANNs once they have been trained with reduced set of noise modulated training data.

[00111] In this example, for the ANN training process, once the division of the total dataset between training and testing data is conducted, smaller groups (batches) of noise modulated training data may be selected one at a time to train values for the ANN weights and then validated with the rest of the training data. This is known as batch training and it allows the ANN to learn from smaller groups of data to assist in avoiding overfitting by the trained ANNs.

[00112] A loss function metric is computed using different metrics by comparing the predicted results obtained from the ANN and the real value of the location and characteristics of the anomaly. In one example, this metric can be the Mean Absolute Error (MAE). In another example, this metric can correspond to the Mean Square Error (MSE). In another example, this metric can be the logarithm of the MSE (Log MSE). Other names are also possible. An iterative process is included to repeat this batch training until a threshold in the loss function is met or the maximum time is reached.

[00113] In another embodiment, the complete noise modulated training data is used to calculate the ANN weights and then validated with the testing data. In another example, different metrics are used and the performance of the ANNs are inspected with noise modulated validation data. In yet another example, the learning rate specified during the training process is increased to provide for a quicker training process in each iteration and to increase the variation in the network weights between iterations in order to improve the global search of weight configurations produced by the iterative process.

[00114] As would be appreciated, as separation of the initial complete noise modulated training data into the reduced training and validating datasets is random then the set of noise modulated training data for each training iteration will be different for each of the five ANNs to be trained resulting in individual trained ANNs whose weights will be different even though they are all trained to detect the same anomaly.

[00115] Once the training process is complete, the testing dataset is used to obtain predictions of leak location and size in the dataset that the trained ANNs have not been exposed to. These predictions are then compared to the input anomaly locations and sizes for the testing data. An ANN that has been successfully trained should present with a similar distribution of errors in the training and the testing datasets. [00116] In one embodiment, an ANN test measure is determined based on the performance of the trained ANN for the training and the testing dataset. In one example, the Root Mean Square Error (RMSE) from the results of the trained ANN for the training and the testing dataset are computed. Taking each prediction for the leak location and size obtained from analysing a transient pressure wave interaction signal that belongs to the training or testing dataset, the leak location and size error are both individually computed. Once all the individual errors for leak location and size have been calculated, the RMSE is computed as a unified metric of the ANN performance on the training and the testing dataset.

[00117] This process assists, in combination with the results from the leak location and size predictions obtained from a measured transient pressure wave interaction signal, in choosing the correct noise intensity for noise modulation of the original training data. At a training and testing stage, it is desirable that that the RMSE obtained for the training dataset and the testing dataset are similar as this demonstrates that the ANN is able to predict the characteristics of the leak similarly for a set of transient pressure wave interaction signals that have not been analysed by the ANN before.

[00118] Referring back to Figure 1, at step 140 a performance measure is determined that characterises the detection of the anomaly based on the results from each of the ANNs. In one example, the performance measure assesses the variability of the anomaly detection results from the series of ANNs by determining the variability in the associated anomaly characteristics for the anomaly type being detected. As an example, where the anomaly type is a leak then the performance measure comprises determining the variability between the different leak locations that are determined by each of the ANNs that are trained on respective sets of noise modulated data. In another example, the performance measure comprises determining the variability between the different leak apertures that are determined by each of the ANNs that are trained on respective sets of noise modulated data. In another example, the performance measure may be a combined measure over a number of associated characteristics.

[00119] In one example a box whisker plot may be generated summarising the distribution of the predicted leak locations determined by each of the ANNs that are trained on respective sets of noise modulated data. A box whisker plot is a standardized way of displaying the variability in a dataset by showing the minimum and maximum values of the dataset as well as the median value and first and third quartiles of the dataset.

[00120] In another example, where multiple ANNs have been trained on respective sets of noise modulated data, the leak location predictions can be adjusted to a probability distribution to characterise this distribution. In another example, a histogram can be built based on the ANN predictions organised by each noise intensity. In another example, violin plots, a plot combining a box plot and a kernel density plot, can be used to assess the performance of the ANNs trained on respective sets of noise modulated data considering that this type of plot allows for the analysis of the density curve of the ANNs training on different noise intensities.

[00121] The Applicant has found that where the results from the differently trained ANNs are consistent, ie where the spread of values between the ANNs is small, then this provides an indicator as to the accuracy of the determination of the anomaly and any associated anomaly characteristics. By obtaining a small distribution of the predictions from different ANNs trained under the same noise modulated data, there is a higher confidence that the predictions are accurate because different ANNs, with different sets of weights, predict a similar leak location and size. Using a distribution of predictions instead of one value also provides for a measurement of how satisfactory the ANNs are performing.

[00122] Referring now to Figure 9, there is shown a flowchart of a method 800 for detecting an anomaly in a pipeline in accordance with another illustrative embodiment. Method 800 is essentially equivalent to method 100 illustrated in Figure 1 except that it includes a pre-processing step of pre processing the measured transient pressure wave interaction signal at step 825 prior to the processing of the transient pressure wave signal by the trained ANNs at step 830 (equivalent to step 130 of method 100) as well as an optional verification step at step 850 where the results from the anomaly detection are verified.

[00123] Referring now to Figure 10, there is shown a flowchart 900 depicting example pre processing methods or approaches that may be adopted either solely or in combination in accordance with pre-processing step 825.

[00124] In one example, pre-processing the transient pressure wave interaction signal at step 825 comprises at step 910 the downsampling of the transient pressure wave interaction signal to generate a downsampled transient pressure wave interaction signal.

[00125] The expected parameters for the numerical generation of the training data by the computational hydrodynamic model may be understood by defining a spatial (Dc) and time (At) resolution that is consistent with the wave speed of the pipeline following the relationship: a = Ax /At Equation 3

[00126] where a is again the wave speed in the pipeline. This implies that for a desired spatial resolution, ie, Dc, a specific time resolution needs to be selected for a pipeline for a given wave speed a.

[00127] Taking the example above, where leaks are generated at 5,000 different locations, it can be seen that the time resolution required to guarantee that each transient pressure wave interaction signal is different is relatively small. As an example, considering a pipeline having a length of 1,000 m and a wave speed of 1,000 nx/s, then the average separation between transient pressure wave signals (ie, transient pressure wave interaction signals) would be 0.2 m, resulting in a required time resolution of 0.2 ms.

[00128] This implies that to generate a transient pressure wave interaction signal having a length

2 L/a seconds, there would be 10,000 pressure values for each of the transient pressure wave signals. If these complete transient pressure wave signals were used for the training of the ANNs, the total required parameters to train one ANN having the configuration referred to above would be 454,000 according to Equation 1, and the total input training data would have 500 million individual pressure values.

[00129] As would be appreciated, while it is possible to train and apply ANNs of this size if there are suitable computing resources, in other embodiments the transient pressure wave interaction signal may be downsampled in the time domain as referred to above. This has a number of benefits including that not only is the input size of the ANNs being trained reduced based on the degree of downsampling but also the input size of measured transient data fed into the ANN will be correspondingly reduced. This will substantially improve the time performance of the trained ANN where this is a system requirement. Taking the example above, where the time resolution is 0.2 ms this corresponds to an original sampling frequency of 5 kHz for the measured transient pressure wave signal.

[00130] In one example, the measured transient pressure wave interaction signal may be downsampled to an equivalent downsampled sampling frequency using a uniform selection of the n-th sample of the transient pressure wave interaction signal. The size of the resulting downsampled transient pressure wave interaction signal in this example depends on the size of the original pressure trace and the selected n.

[00131] In another example, the measured transient pressure wave interaction signal may be downsampled to an equivalent downsampled sampling frequency by averaging the values of an n-th block of sampled pressure values into one value of pressure. In both this downsampling technique and the technique above, the sampling frequency and the frequency used for the training of the ANNs need to be related by an integer n.

[00132] In yet another example, the measured transient pressure wave interaction signal may be downsampled to an equivalent downsampled sampling frequency by defining a new sample grid that matches the one used for the training of the ANN. In this downsampling technique, the pressure value in the new grid is calculated by interpolation (eg, linear, quadratic, cubic, Gaussian, nearest neighbour, etc). By using this technique, the downsampling frequency (eg, selecting every n-th sample or averaging over every n-th sample block or grouping) does not need to be explicitly related to the frequency used for training the ANN by an integer factor. [00133] The final size of the downsampled transient pressure wave interaction signal and, therefore, the size of the input for the ANN, may be selected depending on the desired resolution for the identification of the features. As would be appreciated, there is a trade-off between the equivalent downsampled sampling frequency of the downsampled transient pressure wave signal and the computational time required to develop the training and testing of the ANN. A larger input dataset for the ANN will require in general more time to train, however, the testing time is not affected to the same extent.

[00134] In one example, the downsampled sampling frequency is selected from the following ranges, including, but not limited to: greater than 200 Hz, 200 Hz - 250 Hz, 250 Hz - 300 Hz, 300 Hz - 350 Hz, 350 Hz - 400 Hz, 400 Hz - 450 Hz, 450 Hz - 500 Hz, greater than 500 Hz, 500 Hz - 550 Hz, 550 Hz - 600 Hz, 600 Hz - 650 Hz, 650 Hz - 700 Hz, 700 Hz - 750 Hz, 750 Hz - 800 Hz, 800 Hz - 850 Hz,

850 Hz - 900 Hz, 900 Hz - 950 Hz, 950 Hz - 1 kHz, greater than 1 kHz, 1 kHz - 1.05 kHz, 1.05 kHz - 1.1 kHz, 1.1 kHz - 1.15 kHz, 1.15 kHz- 1.2 kHz, 1.2 kHz- 1.25 kHz, 1.25 kHz - 1.3 kHz, 1.3 kHz- 1.35 kHz, 1.35 kHz - 1.4 kHz, 1.4 Hz - 1.45 kHz, 1.45 kHz - 1.5 kHz, greater than 1.5 kHz, 1.5 kHz - 1.55 kHz, 1.55 kHz - 1.6 kHz, 1.6 kHz - 1.65 kHz, 1.65 kHz - 1.7 Hz, 1.7 kHz - 1.75 kHz, 1.75 kHz - 1.8 kHz, 1.8 kHz - 1.85 Hz, 1.85 kHz - 1.9 kHz, 1.9 kHz - 1.95 kHz, 1.95 Hz - 2 kHz, or greater than 2 kHz.

[00135] In other examples, the ratio of the downsampled sampling frequency to the detection sampling frequency is selected from the following ranges, including, but not limited to: 0.01 - 0.025, 0.025 - 0.05, 0.05 - 0.075, 0.075 - 0.1, 0.1 - 0.15, 0.15 - 0.2, 0.2 - 0.25, less than 0.25, 0.25 - 0.3, 0.3 - 0.35, 0.35 - 0.4, 0.4 - 0.45, 0.45 - 0.50, less than 0.5, 0.5 - 0.55, 0.55 - 0.6, 0.6 - 0.65, 0.65 - 0.7, 0.7 - 0.75, less than 0.75, 0.75 - 0.8, 0.8 - 0.85, 0.85 - 0.9 or 0.9 - 0.95.

[00136] In another example, pre-processing the transient pressure wave interaction signal at step

825 comprises at step 920 pre-processing the transient pressure wave interaction signal to remove signal artefacts introduced or arising from the original generation of the transient pressure wave in the pipeline. In one embodiment, the signal artefacts removed are based on those identified by an ANN sensitivity analysis.

[00137] Referring now to Figure 11, there is shown a plot 1000 of the results of a sensitivity analysis conducted on an ANN trained to detect an anomaly to in turn identify a region of interest in the transient pressure wave interaction signal. In this example, the anomaly is a leak in a pipeline and the associated characteristic being tested for sensitivity is the leak location. Plot 1000 shows the results of successive testing of the ANNs where the transient pressure wave interaction signal that is being processed by the ANN has been perturbed at each point along the transient pressure trace 1050. In this example, a 0.1 m perturbation has been applied to the measured pressure head at each pressure perturbation location and five ANNs each trained on the original training dataset (with no noise modulated data) are applied to these perturbed input pressure traces to provide a distribution of errors in leak location 1010.

[00138] As can be seen from inspection, the plotted errors in leak location 1010 show that perturbations in a region 1020 defined by the first 60 points of the transient pressure head trace, which corresponds to the steady state pressure head before the generation of the transient pressure wave which in this case results from the closure of valve G (see Figure 3), induce a considerably larger error in the distribution of the leak location predictions. After the valve closure, the ANN predictions of leak location are more consistent, although errors are also present due to the perturbation. This sensitivity analysis demonstrates that the pressure variation in a region of interest defined by the initial steady state portion of the measured transient pressure wave interaction signal from prior to generation of the transient pressure wave will potentially induce the largest errors in the overall ANN performance. Based on this sensitivity analysis, this implies that in this example a region of interest 1020 of the measured transient pressure wave interaction signal corresponding to the steady state condition prior to the generation of the transient pressure wave should be a focus of any pre-processing, as variations in this region of interest can induce larger errors in the determination of the anomaly.

[00139] Referring now to Figure 12, there is shown a plot 1100 of a measured transient pressure wave interaction signal 1110 following the generation of a transient pressure wave 1111 showing in detail the pr5essure fluctuations before and after the transient event according to an illustrative embodiment. In this figure, two segments of the transient pressure wave signal are enlarged as shown preserving the same scale. Subplot a) shows the pressure fluctuations before the generation of the transient pressure wave, corresponding to region of interest 1020 illustrated in Figure 11, by in this case valve closure, and subplot b) shows the pressure fluctuations after the dissipation of the transient event created by the generated transient pressure wave. As can be seen from inspection, there are clear differences in the pressure fluctuations or variations before and after the transient event corresponding to the generated pressure wave as the pressure fluctuations before the transient event are greater in magnitude.

[00140] In this example, the increased pressure fluctuations prior to the generated pressure wave relative to the pressure fluctuations after the pressure event are due to the interaction that the transient or pressure wave generator, ie, in this example an open valve initially allowing fluid to exit the pipeline, has with the pipeline. As such, the operating characteristics of the pressure wave generator, being an open valve that is suddenly shut, contributes an initial pressure fluctuation to the transient pressure wave interaction signal prior to the generation of the transient pressure wave which is independent of the leak. As determined by the sensitivity analysis, pressure fluctuations or artefacts in this region of interest prior to the generation of the transient pressure wave additionally have an enhanced capability to cause errors in the ANNs determination of the anomaly. [00141] In this example, the artefacts introduced or arising from the original generation of the transient pressure wave in the pipeline correspond to an additional pressure fluctuation or “noise” in the transient pressure wave interaction signal that are assumed to have a constant standard deviation. In this case, pre-processing at step 920 to remove the artefacts comprises reducing the pressure fluctuation or variation in a region of interest or portion of the transient pressure wave interaction signal so that fluctuations or variations in pressure are those associated with the presence of the anomaly, ie in this case a leak in the pipeline.

[00142] Referring now to Figure 13, there is shown a plot 1200 of the distributions of pressure head 1210, 1220 for the (a) and (b) regions shown in Figure 12 as fitted with corresponding normal distributions having mean and standard deviations of ( i _a , s _a ) and (ji _b , a _b ) respectively. As can be seen, the (b) region following stabilisation after the transient pressure wave has a larger mean fi _b given that the pipeline pressure will stabilise at a higher pressure head value due to the reduction in total flow in the pipeline following the closure of the discharge valve, but still overall has a smaller standard deviation a _b when compared to the pressure fluctuation or s _a before generation of the transient pressure wave, which as discussed above results from the flow through the discharge valve prior to the closure.

[00143] In accordance with the present disclosure, the pressure fluctuation in the region of interest having characteristics ( i _a , s _a ) is processed to have a similar pressure fluctuation characteristics to region (b) corresponding to when the transient pressure wave interaction signal goes back to the steady state following generation of the transient pressure wave.

[00144] Referring now to Figure 14, there is shown a plot 1300 of the cumulative distribution function (CDF) 1310 for the (a) region shown in Figure 12 having characteristics (m _a , s _a ) and a modified or transformed CDF 1320 having the same mean but with the standard deviation of the (b) region, ie having characteristics (c¾). This means that the modified CDF 1320 preserves the mean value of the pressure fluctuations before the generation of the transient pressure wave but its distribution is modified to match the pressure fluctuations after the transient test.

[00145] The region of interest is then processed by selecting a pressure value from the region of interest prior to the generation of the transient pressure wave and then computing the cumulative probability based on original CDF 1310. With this value of probability, a new value for the pressure is found using the modified CDF 1320. These two steps are then repeated for each value of pressure in the region of interest.

[00146] In this manner, the pressure fluctuations caused by the combined effect of the pressure wave generator and the leak may be transformed to show only the fluctuations due to the presence of the leak. [00147] Referring back to Figure 10, in another example pre-processing the transient pressure wave interaction signal at step 825 comprises at step 930 pre-processing the transient pressure wave interaction signal by shifting or offsetting the initial pressure of the measured transient pressure wave interaction signals in line with the initial pressure of the ANNs training samples. This shifting includes determining the difference between the mean pressure in the measured transient pressure wave interaction signal before the generation of the transient pressure wave and the steady state pressure used in the training of the anomaly detection ANNs and then transformation of the transient pressure head traces by adding or subtracting this difference.

[00148] Referring back to Figure 9, method 800 also comprises an optional verification of the results of the anomaly detection at step 850. In one example, verification of the results of the anomaly detection involves determining whether the determined associated characteristics are physically consistent with the pipeline. In one example, this verification could include determining whether a location of the anomaly is consistent with a length of pipeline.

[00149] In another example, verification of whether the anomaly has been detected in the transient pressure wave interaction signal comprises numerically generating a theoretical transient pressure signal based on the detected anomaly and the associated anomaly characteristics and then comparing the measured transient pressure wave interaction signal with the numerically generated theoretical transient pressure signal to determine a comparison measure. A comparison threshold may then be applied to the comparison measure to verify that the anomaly has been detected in the transient pressure signal.

[00150] Referring now to Figure 15, there is shown a pipeline arrangement 1400 for experimental confirmation of the methods and systems disclosed the present disclosure. In this example, a pipeline 1410 having a length of 37.24 metres and an internal diameter of 22.14 mm with a wall thickness of 1.63 mm is originally connected at both ends to two pressurized tanks 1460, 1465. This corresponds to a wave speed a for the pipe of 1305 m/s and a corresponding L _T /a time of 0.029 s.

[00151] An inline valve 1420 has been closed on the downstream of the pipeline to allow flow only through a solenoid valve 1440 installed right before the end of the pipeline at location Gl.

[00152] In this example, a circular orifice of size 2.2 mm has been installed at 28.52 m downstream of source tank 1465 to simulate a leak. The transient pressure wave in the fluid is generated by the fast closure of the solenoid valve Gl with a closure time of 5 ms and the pressure has been measured with a PDCR 810 pressure sensor or detector at point 1440 with a 10 kHz sampling rate. [00153] Referring now to Figure 16, there is shown a plot 1500 of the measured transient pressure wave interaction signals obtained from the pipeline arrangement 1400 illustrated in Figure 15 according to an illustrative embodiment. In this example, a total of 14 transient pressure waves were generated in the fluid carried along the pipeline and a corresponding 14 transient pressure wave interaction signals corresponding to respective responses from the anomaly (ie, in this case a leak) to the generated transient pressure wave were measured as can be seen in Figure 16.

[00154] Each of the transient pressure waves was generated and measured using the same pipeline configuration and under the similar initial conditions. The initial pressure at the end of pipeline 1410 was set between 20.0 and 23.9 m and the transient pressure wave interaction signal has been measured from almost 7 L _T /a (0.2 seconds) before the generation of the transient pressure wave (ie, valve closure) for a duration of 103L _r /a (3 seconds) following generation. As shown in Figure 16, the time window has been limited to a duration of 1 second.

[00155] As the next step involves the processing the transient pressure wave interaction signals by a series of ANNs each trained on respective sets of noise modulated training data the question arises as to what is the appropriate level of noise modulation that should be adopted.

[00156] In this example, a 1-D convolutional ANNs has been adopted in accordance with the architecture previously described having four convolutional layers, 20 to 30 filters and three dense layers. A total of 50,000 numerically generated transient pressure wave interaction signals were generated based on a MOC based computation hydrodynamic model by modelling 10 leaks at random locations each 7.45 mm along pipeline 1410 with different diameters ranging between 0.4 and 3.5 mm.

[00157] In this example, the total simulation time was set to 0.09 s which corresponds to 3.15L/a seconds, ie, L/a seconds before the generation of the transient pressure wave and 2.15 L/a seconds after transient pressure wave have been generated to account for the effects of in this case the valve closure curve in the computed pressure. To obtain different transient pressure wave signals, the time resolution of the MOC hydrodynamic model is required to be at least 0.006 ms; therefore, the total size of the input dataset before any downsampling process would be 788 million transient pressure head values where each time window has almost 16,000 pressure head values.

[00158] In this example, and consistent with the size of the measured transient pressure wave interaction signals, the transient pressure wave signals are downsampled to generate a downsampled transient pressure wave interaction signal. In this example, a downsampling frequency of 5 kHz is selected. This downsampling frequency is selected based on a consideration of the dimensions of pipeline 1210 and the potential number of weights to train in the resulting ANNs. [00159] As would be appreciated, an overly small downsampling frequency would create a very small ANN that would not be able to learn enough information from the transient pressure head traces forming the training dataset. Smaller downsampling frequencies may be selected for larger pipelines with larger L/a characteristics. Based on the downsampled frequency of 5 kHz, the resulting number of weights for the anomaly detection ANNs is 13,868 and the input dataset contains 8.55 million individual transient pressure head values for the 50,000 transient pressure wave signals.

[00160] Referring again to Figure 4, the next step is the generation of noise modulated training data for the ANNs. Once the initial training data has been generated at step 410 then at step 420 a representative pressure fluctuation is determined based on the pipeline configuration and the type of anomaly. In this case, the smallest leak drop ( h ₀ as shown in Figure 5) corresponding to the smallest leak considered was determined to be 0.1238 m. To characterise the effect of different noise intensities, six different noise intensities were considered in accordance with Equation 2 and the selected values of k _n and resulting standard deviation s _h are presented in Table 1.

TABLE 1 - SELECTED NOISE INTENSITIES FOR GAUSSIAN NOISE DISTRIBUTION

[00161] These noise intensities were selected considering that the objective was to obtain trained

ANNs with the ability to find leaks across the complete defined leak size range without significantly decreasing performance with the addition of noise. As would be appreciated, the number of different noise intensities that may be analysed will be determined depending on the pipeline system and potentially the available computing resources. [00162] The selection of the number of noise intensities in this example and their magnitude is defined based on observations of the pressure noise in the system, the normal operational changes in the pipeline that might create pressure fluctuations and the expected background noise.

[00163] Based on the noise intensities shown in Table 1, six additional noise modulated training datasets were created where each dataset contained a total of 250,000 transient pressure wave signals for each of the five ANNs to be trained for each of the above defined noise intensities.

[00164] Referring now to Figure 17, there is shown a figurative view of the different series of

ANNs trained on respective datasets of noise modulated training dataset of noise modulated training data according to an illustrative embodiment. In this case, s ₀ = 0 corresponds to the original training dataset and the values for noise intensity range from n = 1 to 6 in accordance with Table 1. This results in the training and testing of a total of 35 ANNs where 5 ANNs are trained on the original training data and the remaining 30 ANNs are trained in series of 5 ANNs on respective sets of noise modulated training data with six levels of increasing noise intensity. In this example, each dataset of 250,000 transient pressure wave signals was divided into a training dataset of 125,000 transient pressure wave signals for training and a second testing dataset for testing of the respective trained anomaly detector ANN. This division process is repeated for each of the 5 ANNs trained with the noise modulated training data with six level of noise intensity. Thus, each ANN is trained and tested with a different dataset.

[00165] Referring now to Figures 18a-g, there is shown a series of plots illustrating the percentage of exceedance associated with the absolute average error for the location of a leak following training and testing for each noise intensity according to an illustrative embodiment. In this case, a single ANN for each noise intensity is shown from the five trained and tested ANNs as the distribution of errors was found to be consistent across the five ANNs for each noise intensity.

[00166] Each plot shows two lines. The solid line corresponds to the distribution of the absolute average leak location error on the dataset used for the ANN training while the dotted line shows the leak location error for the dataset used during the ANN testing. The percentage of exceedance can be interpreted as the proportion of the total trained or tested samples that the average leak location exceeded a certain error size. An average error in the predictions is presented because in some cases two or more traces with the same leak location and size have been used either for the training or the testing.

[00167] It is important to notice that the maximum percentage shown in the figure is 10% (x-axis) meaning that 90% of the times that these ANNs are used with numerically generated transient pressure wave interaction signals, the obtained absolute average leak location error is smaller than the minimum absolute average error visible in these plots. In addition, the y-axes in plots (a) to (e) of Figure 18 are presented on the same scale to facilitate the analysis. [00168] As can be seen from inspection, as the standard deviation for the Gaussian distributed noise increases, the absolute average leak location errors also increase due to the noise added to the training and testing samples. It is also evident that the ANNs trained and tested with transient pressure wave interaction signal without any noise performed better than the rest. However, for all the considered noise intensities, 90% of the times the absolute average leak location error is 0.12 m or smaller indicating a successful result from the training of these ANNs.

[00169] Results from Figure 18 demonstrate that the ANN training methodology using noise modulated data was successful when tested with numerical data. However, the selection of a noise modulated ANN to predict the location and characteristics of an anomaly depends on the performance of the ANN when tested with transient pressure wave interaction signal obtained from the analysed pipeline, not from numerical data. These results demonstrate that the range of noise intensities was selected appropriately and ANNs can still learn about the presence of anomalies despite the background noise.

[00170] In accordance with the present disclosure, the transient pressure wave interaction signals are processed to reduce any pressure fluctuations associated with the generation of the transient pressure wave (see step 920 of Figure 10). In this example, pressure fluctuations arising from the flow through the solenoid valve installed at the end of the pipeline prior before it is closed to generate the transient pressure wave are reduced.

[00171] In this example, two 0.2-second segments were analysed for each of the 14 measured transient pressure wave signals corresponding to a first segment before the solenoid valve closure and a segment corresponding to the end of the 3 second recorded time window. Two normal distributions were then fitted to the pressure fluctuations before and after the solenoid valve closure for each transient test with the respective normal distributions having an average standard deviation before the transient test of 0.0392 m and an average standard deviation after the transient test of 0.0097 m.

[00172] Following pre-processing to reduce pressure fluctuations associated with the generation of the transient pressure wave, the resulting transient pressure wave interaction signals have been further processed by being shifted to be aligned to one initial average steady state pressure (see step 930 of Figure 10). As shown in Figure 16, the initial pressure value of each time window was slightly different in a 3.9 m range; therefore, all transient pressure wave signals have been aligned to an average steady state pressure of 21.16 m, which corresponds to the initial pressure considered for the numerically generated transient pressure wave interaction signals. Additionally, in this example, the resulting shifted transient pressure signals are also trimmed to select only the region of interest corresponding to L/ a seconds before the generation of the transient pressure wave and 2.15 L/a seconds after the generation of the pressure wave. [00173] Referring now to Figure 19, there is shown a plot 1800 of transient pressure wave interaction signals illustrated in Figure 16 following pre-processing according to an illustrative embodiment. As can be seen, the initial steady state pressure 1810 for the transient pressure wave interaction signals has been shifted to the same value. As each transient pressure signal had a different steady state, the increase in pressure 1820 after the generation is different. This is expected due to the small differences in the resulting flow in the pipeline given different initial steady state pressures, however, in this example there was no further pre-processing except for downsampling of the original transient pressure signal to a downsampled frequency of 5 kHz to match the input size of the trained anomaly detection ANNs.

[00174] Referring now to Figures 20 to 26, there are shown plots of the distribution of predictions for determining the location of a leak for each of the transient pressure wave interaction signals illustrated in Figure 19 following processing by a series of ANNs trained on noise modulated training each having different noise intensities according to an illustrative embodiment. In this example, there are seven different noise intensities, ranging from 0 (ie, s ₀ ) to the six noise intensities s ₁ to s ₆ referred to in Table 1. Each of the plots indicates the end of the pipeline 1910 as well as the location 1920 of the leak in the pipeline at 28.05 m.

[00175] As can be seen from Figure 20, where the series of ANNs comprises five ANNs that are trained on the original training data having no noise component, except for two outliers 1930 in the predictions for transient pressure signal #13 and #14, none of the leak location predictions is within the physical limits of the pipeline and so these predictions are not depicted in Figure 20.

[00176] Since the ANNs have been trained with smooth numerical samples, the predictions when the analysed transient pressure head traces have some pressure fluctuations result in illogical predictions for the leak location. Depending on the analysed pipeline and the existent anomaly that exists, the ANNs trained with the original training data might not be able to locate the anomaly without the addition of noise in the training samples. However, if the analysed pipeline is not exposed to significant magnitudes of background noise, the ANNs trained with the original data will be able to accurately predict the location of the anomaly.

[00177] Moving through Figures 21 to 26, the significant effect of noise modulating the original training data for the anomaly detection ANNs on the resultant determination of the leak location can be seen on the resulting distribution of leak location predictions. The addition of a Gaussian distributed noise with a standard deviation of 6.2 mm (ie, s _{1 )} has a significant effect in the resulting leak location predictions (see Figure 21) as most of these can now be found within the physical limits of the pipeline 1910. It is important to note that pressure fluctuations having a standard deviation of 6.2 mm are significantly smaller in magnitude than the observed background pressure fluctuations in the pipeline, but still its introduction in the dataset for the training of the ANNs has proven to be highly effective in improving the obtained leak location predictions.

[00178] Despite the clear advantages of applying a Gaussian noise distributed noise, the results presented in Figure 21 also demonstrate that the addition of noise with a very small standard deviation in this example is not enough for a satisfactory prediction of the location of the leak. Figures 21 to 26 demonstrate that as the noise intensity s _h increases the distribution of the leak locations are more compact and are, in general, closer to the actual leak location. Predictions from ANNs trained with noise intensities s ₂ and s ₃ (see Figures 22 and 23) are within the length of the pipeline but vary considerably between the different measured transient pressure signals. In addition, leak location predictions obtained from the last three noise intensities (s _4-6 ) (see Figures 24 to 26) oscillate between 26.05 and 31.85 m with a couple of predictions outside the physical length of the pipelines for s ₄ .

[00179] In this example setup, although most of the determinations of the anomaly by the respectively trained ANNs provided similar distributions of predictions for a particular noise intensity, transient pressure wave interaction signals #1 and #12 generally resulted in more scattered leak location predictions. Leak location predictions for time window #1 are less satisfactory as there is a more significant difference between the initial steady state pressure and the resulting pressure increase after the generation of the transient wave as it can be seen in Figure 19 (see pressure trace 1840).

[00180] On the other hand, even though transient pressure wave interaction signal #12 does not present with any particular differences in comparison with the other transient tests, it has produced less consistent results for all the noise intensities indicating that there might have been additional noise during this test. Considering these results, conducting multiple tests are likely to provide additional information about the performance of the performance of the trained ANNs for a selected noise intensity for the noise modulated training data and may be recommended.

[00181] It is important to note that a perfect distribution of leak location predictions would imply that each of the five ANNs trained for a particular noise intensity predicts exactly the same leak location and that this location is very close to the real location of the leak in the pipeline. However, given that each ANN has a different set of resulting weights after the training process, this result would be very hard to accomplish in a real configuration. In accordance with the present disclosure, the effectiveness or performance of a group of ANNs may be assessed by determining a performance measure that characterises the detection of the anomaly that is based on the results from each of the ANNs where there is a higher performance when the results from each of the ANNs are consistent with each other.

[00182] Referring now to Figure 27, there is a plot 2600 of the performance of the trained ANNs on the measured and processed transient pressure wave signals #1 to #14 illustrated in Figure 19 for each noise intensity according to an illustrative embodiment. In plot 2600 the average of the absolute median predicted leak location error computed for transient pressure wave signals #1 to #14 is shown for each corresponding noise intensity (as indicated by the respective associated standard deviation on the x-axis) (eg, 2610) as well as the distribution of the absolute median predicted leak location error (eg, 2620). For this example, the median predicted leak location for a given noise intensity and a given measured transient pressure wave signal will be determined from the five ANNs trained on the corresponding noise modulated training set having that noise intensity.

[00183] As can be seen from inspection, the absolute median error in the leak location for the

ANNs trained without any noise (ie, standard deviation of zero in Figure 27) is not visible in the scale of the plot given that all of the median predicted leak locations for these ANNs are outside the length of the pipeline (see Figure 20). Similarly, this plot demonstrates that the addition of a very small noise in the training samples (s ₁ = 0.0062 m) drastically improves the performance of the ANNs to obtain a distribution of absolute mean location errors that oscillates between 1 and 8 m (see Figure 21). However, for this particular application an 8 m error is still not acceptable for the location of a leak in a 37.24 m long pipeline (which represents a 21.48% error considering the length of the pipeline).

[00184] As the standard deviation or intensity of the noise increases, it is clear that the distribution of the absolute median error narrows comprises errors that vary between 0.02 and 1.09 m (0.05-2.93% error) for the largest standard deviation considered (s ₆ = 0.1857 m). Analysing only the distribution of the absolute median location errors in Figure 27, it would seem logical to select the predictions of the ANNs trained with the largest noise intensity; however, another consideration is the consistency of the ANNs performance between training and testing.

[00185] Referring now to Figure 28, there is shown a plot 2700 of the median values (in circles) and distributions of the Root Mean Square Error (RMSE) for the training (in lighter shade) and the testing (in black) of the trained anomaly detector ANNs for each noise intensity as shown in Table 1. In this example, the distribution of the RMSE has been computed using the leak location error from each of the 125,000 samples used for the training of the ANNs (or 25,000 for the case of the ANNs trained without any noise). It is expected that good ANN performance would correspond to obtaining low values of RMSE and consistent magnitudes between the training and the testing RMSE.

[00186] Referring now to Figure 29, there is shown a plot 2800 of the average error in RMSE (in circles) and the range for the prediction of a leak location (whiskers) for the training (in lighter shade) and the testing (in black) of the trained anomaly detector ANNs for each noise intensity as shown in Table 1.

[00187] As can be seen from inspection, the ANNs trained with noise modulated training data having large noise intensities will result in larger values for the RMSE and a significantly larger ranges of possible leak location errors during training and testing. Both of these metrics are considerably larger for the last two sets of ANNs (corresponding to s ₅ = 0.1238 m. and s ₆ = 0.1857 m) with significantly different results for the training and the testing of these ANNs for both these values of noise intensities. These results indicate that in this example the ANNs trained with large noise intensity datasets are not able to predict the location of the leak when exposed to new data from the testing dataset, a phenomenon known as overfitting. This is undesirable because it shows that the ANN’s final weights are only accommodating to the training dataset and are not able to generalise to new transient pressure wave interaction signal.

[00188] Accordingly, in this example, to select a noise intensity for noise modulation of the training data, a combined analysis of the distribution of the predicted leak locations and the RMSE of the training and testing of the ANNs was conducted.

[00189] For this reason, and for this application, the optimum noise intensity for the noise modulated training data for training of the leak detection ANN is obtained when the noise has a Gaussian noise distribution having a standard deviation of 0.0619 m (ie, s ₄ ) as the median leak location prediction for this set of ANNs was 28.74 m compared to an actual leak location of 28.52 m and the median predicted leak size was 2.32 mm compared to an actual leak size of 2.2 mm. These results represent a 0.59 % error in the location of the leak and a 5.45 % error in the size of the leak.

[00190] As such, and in accordance with this example embodiment of the present disclosure, the relevant trained ANNs that would be adopted for anomaly detection would be those that have been trained on a respective sets of noise modulated training date where the noise intensity would correspond to a standard deviation of 0.0619 m.

[00191] The selection of the relevant trained group of ANNs that is adopted for anomaly detection depends on the distribution of the anomaly locations and the performance of the ANNs during training and testing. In one example, all ANNs trained have a successful performance during training and testing (with no evidence of overfitting). In this case, the group of ANNs adopted for anomaly detection is the one with the smallest distribution of anomaly locations. In another example, some ANNs trained do not present with a successful training because the testing stage demonstrates overfitting. In this case, these groups of ANNs are discarded and the group of ANNs adopted for anomaly detection is the one with the smallest distribution of anomaly locations from the remaining groups. In another example, all ANNs trained have a successful performance during training and testing (with no evidence of overfitting) but the distribution of the anomaly locations is not satisfactory. In this case, a new range of noise intensities may need to be explored. [00192] In one example, the determined anomaly is then subject to a further verification stage where the determined characteristics of the anomaly form the inputs for numerically generating a transient pressure wave interaction signal responsive to a generated transient wave which can then be compared to the measured transient pressure wave signal.

[00193] Referring now to Figure 30, there is shown a plot 2900 comparing the predicted transient pressure wave signal 2910 obtained by numerically generating the expected trace based on the determined anomaly characteristics with the measured transient pressure wave signal 2920 used to determine the anomaly characteristics according to an illustrative embodiment. In this example, measured transient pressure wave signal 2920 corresponds to transient pressure wave signal #8. It can be observed in this figure that there is reasonable concordance between the pressure values for the measured and predicted transient pressure wave signals pointing to a successful prediction of the location and size of the leak using the series of ANNs trained on noise modulated data with a standard deviation of 0.0619 m (ie, s ₄ ) as described above. The Normalised Root Mean Square Error (NRMSE) has been computed between these two transient pressure head traces obtaining a value of 2.06% demonstrating again the accuracy of the methodology proposed.

[00194] As would be appreciated, method and systems in accordance with the present disclosure for detecting anomalies in a pipeline where noise modulated training data are employed to train a series of ANNs not only improve the results but also provide a performance measure that allows the performance of the detection task to be characterised more fully. In one example, the results from the series of ANNs may concentrate around two different values and then the verification step may then be used to determine which set of results are correct. In addition, methods and systems in accordance with the present disclosure have the advantage that a generated characteristic pressure noise signal may be added to the training data for the ANNs without the requirement to specifically replicate the background noise of the pipeline system.

[00195] Throughout the specification and the claims that follow, unless the context requires otherwise, the words “comprise” and “include” and variations such as “comprising” and “including” will be understood to imply the inclusion of a stated integer or group of integers, but not the exclusion of any other integer or group of integers.

[00196] The reference to any prior art in this specification is not, and should not be taken as, an acknowledgement of any form of suggestion that such prior art forms part of the common general knowledge.

[00197] It will be appreciated by those skilled in the art that the invention is not restricted in its use to the particular application described. Neither is the present invention restricted in its preferred embodiment with regard to the particular elements and/or features described or depicted herein. It will be appreciated that the invention is not limited to the embodiment or embodiments disclosed, but is capable of numerous rearrangements, modifications and substitutions without departing from the scope of the invention as set forth and defined by the following claims.