BACKGROUND

Cross Reference Paragraph

[0001] This application claims the benefit of U.S. Provisional Application No. 62/902550 entitled “Smart Dust Cap,” filed September 19, 2019, the disclosure of which is incorporated herein by reference.

Field

[0002] Embodiments herein generally relate to well drilling tools, and specifically to electronic communication of data and signals amongst such tools.

Description of the Related Art

[0003] One of the biggest challenges for the oil and gas companies is Non-Productive Time (NPT) due to wellbore instability, unplanned events, and equipment failures, especially during downhole operations. NPT adversely impacts the efficiency of drilling and producing wells. Operators are driven to increase production efficiency and reduce the cost of development and production. NPT that arises while drilling, testing, and producing oil or gas wells can result in the escalation of well drilling and construction costs (capital expenditures - CAPEX) and lifting or production costs (operational expenditure - OPEX). In addition to the running cost of the hired rigs and equipment during drilling, completion, and testing delays, NPT can result in overexposure of equipment and formations to drilling fluids (water-based mud or synthetic oil-based mud). Overexposure to drilling fluids can cause equipment failure and/or formation damage, which will later impact reservoir productivity.

[0004] Sources of NPT include, for example, surface and downhole tool failures, rig repairs, waiting on weather, pulling of dulled bits, running and cementing casings, and waiting on logistics. Sources of NPT generally fall into four categories:

• Logistics issues

• Hole issues • Tool failure; and

• Weather effects.

[0005] Weather effects and hole issues are considered external factors. Repetitive operations done manually by engineers and operators to configure and prepare tools prior to a job can lead to human mistakes that can cause downhole failures. In every case, NPT resulting from such failures has a high financial impact because the time required for troubleshooting can include pulling the string and Bottom Hole Assembly (BHA) out of hole.

[0006] Regarding logistics, with assets and people spread throughout the operations and in constant flux, efficient logistics can also reduce NPT. Commonly, logistics delays can be traced to how equipment is tracked. The use of manual and often obsolete tracking methods makes operations planning and forecasting cumbersome. Using traditional approaches, managers and engineers send emails and make phone calls to locate equipment and then try to estimate transit and delivery times, often inaccurately. In addition, equipment is frequently shipped on a rush or expedited bases, and nobody remembers to update the tracking system, leading to further confusion and delay, and negatively impacting operations planning.

[0007] To manage the effect of equipment failure on NPT, current practices typically employ two basic types of maintenance management: reactive maintenance (RM), or the “run-to-failure” approach, and preventive maintenance (PM), also called time-based maintenance (TBM).

[0008] The philosophy behind Reactive Maintenance (RM) is straightforward. No action is taken until an equipment failure occurs. RM management incurs no cost until a machine or system fails to operate. It is also the most expensive method of maintenance management. Major expenses associated with this maintenance methodology are the cost of spare parts inventory, cost of overtime labor, and cost of equipment downtime. For downhole equipment, NPT is an inevitable associated cost, since the ongoing operation will stop and the tool will be pulled out of hole, which results in high NPT. [0009] Unlike run-to-failure management, TBM methods are time-driven. Maintenance tasks are based on elapsed time or hours of operation. Fig. 1 is a graph that illustrates an example of the statistical life of a manufactured equipment. The mean- time-between-failures (MTBF) trend line 100, or bathtub curve, indicates that a new machine has a high probability of failure because of installation problems during an initial period 102 of the first few weeks of operation. After this initial period 102, the probability of failure is relatively low for an extended period of operation 104. Thereafter, the probability of failure typically increases sharply with elapsed time during an end-of-life period 106. Using historical data, the time at which the probability of failure starts to increase sharply can be estimated statistically. In TBM preventive management, equipment repairs or rebuilds are scheduled based on the MTBF statistic. Taking the example of oil field equipment, some companies perform periodic maintenance campaigns every six months, at which time the tool is completely disassembled for lubrication, O-rings change, and sensors calibration. It is hoped that this approach will allow all outages to be carefully planned and optimized. The problem with this approach is that the mode of operation and system variables directly affect the normal operating life of the equipment. The MTBF is not the same for a pump that handles water and one that handles abrasive slurries, or is not the same for a downhole gauge and a packer. When using MTBF statistics to schedule maintenance, the normal result is either unnecessary repairs, where a repair is made before it is needed, or catastrophic failure where a repair is made after it is needed. For example, a packer may not need a rebuild after six months, hence the labor and material used to make the repair was wasted. The second option when using TBM is even more costly — if the pump fails before six months, it must be repaired using the run-to-failure management process. Better maintenance methods are needed to minimize unit downtime.

SUMMARY

[0010] Embodiments described herein provide a protective component for a downhole tool, the protective component comprising a coupling for attaching the protective component to the downhole tool; and a wireless networking circuit for communicating data retrieved by the downhole tool to a surface data repository. [0011] Other embodiments described herein provide a downhole tool, comprising a well instrument; and a protective component for the instrument, the protective component having a wireless networking circuit for communicating data retrieved by the well instrument to a surface data repository.

[0012] Other embodiments described herein provide a method of operating a downhole well instrument, comprising connecting a protective component to the well instrument, the protective component comprising a wireless networking circuit, a rechargeable battery, and a wireless charging circuit electrically connected to the battery.

BRIEF DESCRIPTION OF THE DRAWINGS

[0013] So that the manner in which the above recited features of the present disclosure can be understood in detail, a more particular description of the disclosure, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only exemplary embodiments and are therefore not to be considered limiting of its scope, may admit to other equally effective embodiments.

[0014] Fig. 1 is a graph that illustrates an example of the statistical life of a manufactured equipment.

[0015] Fig. 2 is an activity diagram illustrating an MoT implementation in an oil and gas environment.

[0016] Fig. 3 is s schematic diagram of a smart tool according to one embodiment.

[0017] Fig. 4 is a functional diagram of a smart dust cap according to one embodiment.

[0018] Fig. 5 is an activity diagram illustrating a peering scheme according to one embodiment.

[0019] Fig. 6 shows communication architecture according to one embodiment. [0020] Fig. 7 is an activity diagram illustrating a use case of the smart dust caps described herein.

[0021] Fig. 8 is an activity diagram illustrating how charging may be performed at a workshop location according to one embodiment.

[0022] Fig. 9 is an activity diagram illustrating how charging may be performed at a well site location according to another embodiment.

[0023] Fig. 10 is a table summarizing capabilities enabled by the apparatus and methods described herein.

[0024] Fig. 11 is an isometric view of a partially assembled smart tool according to another embodiment.

[0025] Fig. 12 is a schematic architecture diagram showing an edge processing application using the smart tools described herein.

[0026] To facilitate understanding, identical reference numerals have been used, where possible, to designate identical elements that are common to the figures. It is contemplated that elements and features of one embodiment may be beneficially incorporated in other embodiments without further recitation.

DETAILED DESCRIPTION

[0027] This development tackles two major sources of NPT — logistics delays (waiting) and downhole tool failures. Condition based maintenance is a predictive maintenance methodology that uses the actual operating condition of equipment and systems to optimize total asset utilization. Instead of relying on average-life statistics to schedule maintenance activities, predictive maintenance uses direct monitoring data to determine the actual MTBF or loss of efficiency for each asset and system. The common premise of CBM is that regular monitoring of the actual mechanical and electrical conditions, software status, operating efficiency, and other indicators of the operating equipment or system are required to achieve the maximum interval between repairs and minimize the number of unscheduled outages resulting from failures and thus minimize the associated costs. The CBM approach, enriched by active learning algorithms, applied to the continuously-acquired data will provide a detailed insight about the status of the equipment and trigger actions if a failure pattern is detected. A considerable amount of equipment-condition data is usually timestamped, where a set of sensor readings are collected at the same time as timestamps and includes device identifiers. CBM algorithms predict the expected time of failure “t” by using the historical data related to the condition of the tools and the operation. Machine learning algorithms can be formulated in one of two ways: the classification approach or the regression approach. The classification approach predicts whether there is a possibility of failure in the next n-steps. The regression approach predicts how much time remains before the next failure. The regression approach is also called the remaining-useful-life (RUL) approach. The classification approach typically provides a “yes” or “no” answer, but can provide greater accuracy with less data. The regression approach needs more data, although it provides more information about when the failure is predicted to happen.

[0028] To enable the CBM approach, the targeted tools can be transformed into connected objects using the Industrial Internet of Things. The Internet of Things (loT) paradigm allows “things”, including personal electronic devices, vehicles, and home appliances, such as medical devices, refrigerators, cameras, and sensors, part of the internet environment. Connected items can broadcast their status, context, or any other needed information publicly or privately. The MoT paradigm provides a basis for innovations that will enable interactions among things and humans, and will enable the creation of smart cities, factories, infrastructures, and intelligent industrial machines to ultimately enhance the quality and utilization of resources. MoT is mostly about human interaction with objects/devices. Connected objects can alert users when certain events or situations occur such that people can monitor activities and conditions from anywhere. MoT additionally monitors activities and conditions and provides remote control functions, but these capabilities can extend far beyond what MoT provides. MoT technology can be used to monitor and control industrial production processes while capturing detailed data for quality management and documentation. Manufacturing execution systems can use lloT technology to closely monitor more parameters, resulting in the capability to control processes and quality in a more sophisticated and effective manner.

[0029] Fig. 2 is an activity diagram 200 illustrating an lloT implementation in an oil and gas environment. Oil and gas equipment 202, the “things” to be connected to the internet, are fitted with sensors that monitor operating condition, for example position, of the equipment. Other sensors 204 monitor environmental conditions such as temperature and pressure. The sensor data is collected electronically, using Ethernet, Bluetooth, or RFID communication standards. The sensor data is provided to a gateway 206 that stores the data in a repository 208, which may be local or remote. Flere, the data is stored in a data “cloud,” which is a metaphor for remote, on-demand, data storage and retrieval.

[0030] As shown in Fig. 2, to become a smart object or thing, the physical objects need to enable three capabilities:

• Sensing/actuating

• Processing/transforming; and

• Communication without human interaction (wired or wireless).

[0031] A server can be employed, as part of the gateway 206, repository 208, or as a separate installation, to analyze the data and generate information for users. The sensors act as data gatherers, cloud computing can be a platform for storing and analyzing the data, and Big Data analytics can be used to convert the raw data into knowledge or insights.

[0032] When considering downhole equipment, a majority of tools are developed and deployed during drilling, formation evaluation, well control, testing, and production of oil and gas wells. All the tools used for those activities share several characteristics. First, the harsh, downhole working conditions, such as high pressure and temperature (HPHT) and high shock/vibration levels, impact the cost of electronics and materials used for the tools. Second, the tools usually have a set of embedded sensors (temperature, pressure, shock, radioactivity, etc.). Finally, the tools usually have protective (dust) caps used to protect the threads used for connecting tools into drill strings, and the tools are normally identified by a unique identifier (serial number) for tracking. Telemetry tools for well testing are examples.

[0033] Taking advantage of the NoT paradigm, an NoT module is integrated into downhole equipment to connect the equipment to a communication network for transmitting and receiving signals and data using internet protocol. The MoT module (either standard or customized) must provide connectivity (cellular, Wi-Fi, and Bluetooth). In addition to the sensors already integrated in the existing tools, the MoT module can integrate new sensors, such as:

• GPS chip for geolocalization

• RFID tag for base entrance/exit tracking

• Temperature/pressure sensors

• Thickness sensors to monitor aging of critical mechanical parts

• Shock sensor to measure shock level during transport and operations

• Humidity sensors to confirm that tool is sealed and watertight.

[0034] Fig. 3 is s schematic diagram of a smart tool according to one embodiment. The smart tool of Fig. 3 has a data acquisition and transmission cap 302. The data acquisition and transmission cap 302 is a protective cap of the kind typically used at the end of downhole tools in oil and gas environments, commonly referred to as a “dust cap.” This “dust cap” includes circuitry to enable acquisition, storage, and transmission of data obtained while in a well. Thus, in the sense that the cap 302 includes data acquisition, storage, and transmission features, the cap 302 can be referred to as a “smart dust cap.” A conventional dust cap 3 is shown for comparison.

[0035] The smart dust cap 302 has a long-duration battery 304 to power electronics within the smart dust cap 302, sensors (not shown) to sense operating and environmental parameters, and an MoT circuit board 306 to facilitate communication. The MoT circuit board may contain Bluetooth, RFID, cellular telephone, and/or Ethernet circuitry to facilitate communication between the smart dust cap 302 and surface components, such as gateways, servers, routers, hubs, and the like. Two-designs are shown in Fig. 3, a linear design 300A in which the long-duration battery 304 is aligned with the circuitry and sensors along a single tool axis 308, and a compact design 300B where the long-duration battery 304 is located beside other components of the smart dust cap 302, and the MoT circuit board 306 is located at the end of the smart dust cap 302 for connection to the sensors and to the battery. The sensor module and MoT circuit board are integrated into the smart dust cap 302 removable section. As shown in Figure 3, the smart dust cap 302 includes an embedded MoT board and a set of sensors, which may be integrated into the MoT board, all of which are powered by the long-duration battery. This new embodiment is then connected to the downhole tool to communicate with the tool wirelessly or through wires.

[0036] The dust cap is used to house the electronics for data storage and communication so that the electronics do not need to be further hardened for the downhole environment. The dust cap protects the sensors and electronics from the downhole environment increasing the functionality that can be provided by the electronics and reducing the cost and complexity of the electronics.

[0037] The downhole asset connected to the smart dust cap will periodically generate data about the status of the tool (e.g., battery voltage/current, pressure, temperature, humidity, embedded software logs, GPS position, and thickness level) using the embedded sensors. Data generated by the downhole asset can be transmitted to the smart dust cap 302 or stored on the asset. The sensors of the smart dust cap 302 can also generate their own data within the smart dust cap 302. Depending on the sampling frequency, data collection may be effectively continuous. At least some of the data is stored locally on the MoT circuit board 306, and once the smart dust cap 302 is out of hole and it has internet connectivity, the stored data will be streamed automatically and seamlessly to the repository and/or analysis server for data analytics and failure pattern detection used to plan the maintenance strategy based on the data. Data can be streamed from storage on the MoT circuit board 306, and/or data stored on the downhole asset can be transmitted, in live stream or in batch, to the smart dust cap 302, which can then stream the data to the repository. [0038] The smart dust cap 302 is matched to the downhole asset so that data collected by the smart dust cap 302 is registered to the proper downhole asset. If data is mis-registered to the wrong downhole asset, the data may be assigned an improper location within the formation or time, and may be improperly associated with other time- and location-stamped data. Fig. 5 is a flow diagram summarizing a peering method 500 used to peer a smart tool to a downhole asset.

[0039] At 502, a smart tool is connected to a downhole asset. The downhole asset typically includes a circuit that connects to the smart tool to provide the identification signal to the smart tool. The circuit of the downhole asset connects to the MoT circuit board of the smart tool by connecting with circuitry in the smart tool. The circuit of the downhole asset may receive power from the long-duration battery of the smart tool, or may be separately powered, for example by wires deployed along the drill string.

[0040] At 504, the smart tool connected to a downhole asset initiates communication with the downhole asset and receives an identification signal from the downhole asset. The downhole asset retrieves a saved identification and sends a signal through the circuit of the downhole asset to the circuit in the smart tool. One way of communicating an identification from the downhole asset to the smart tool is to use a near-field communication device such as an RFID device. The smart tool can signal the RFID device to broadcast the identification, which can be received wirelessly by the smart tool using an RFID transceiver electrically connected to the MoT circuit board.

[0041] At 506, the smart tool attempts to match the identification signal with a predefined identification for the smart tool. If the match is successful, the successful match is registered by the smart tool. The smart tool includes a processor, located on the MoT circuit board or in another circuit and configured, at least, to compare the received identification signal to the predefined identification. The predefined identification may be obtained from a memory, such as a ROM or EPROM memory, included with the MoT circuit board, and when the processor compares the received identification signal with the identification obtained from the memory, the processor is configured to output a signal to produce an indicator at 508. The indicator can provide a human user real-time confirmation that a connected smart tool is the correct smart tool for the downhole asset. The indicator can be local, for example a colored light (red/green), or the indicator can be remote, such as a signal sent to a terminal or display device configured to receive the signal and paint a display representing the signal for a human user.

[0042] Fig. 4 is a functional diagram 400 of a smart dust cap according to one embodiment. The dust cap 400 has a plurality of functional units housed in a process and environment resistant housing. A power unit 402 provides power to the other functional units. The power unit 402 may be a rechargeable battery unit, such as a lithium battery pack, or another convenient power unit. In some embodiments, the power unit is not part of the dust cap, so the dust cap receives power from another object connected to the dust cap electrically. In this case, the power unit 402 is part of the smart dust cap 400 to enable the smart dust cap 400 to function in the absence of a connected power source.

[0043] The smart dust cap 400 has a sensor unit 404 that includes sensors beyond those typically found in a downhole tool. For example, many downhole tools include telemetry sensors and environmental sensors, such as accelerometers, pressure and temperature sensors, position sensors, moisture sensors, radiation sensors (i.e. gamma ray sensors), acoustic sensors or transducers, and flow sensors. The sensor unit 404 can include position sensors, temperature sensors, pressure sensors, flow sensors, orientation sensors, electrical property sensors, and the like to supplement data gathering downhole. Some of the sensors may generally sense a property similar to a sensor of the downhole tool, but with a different sensitivity, sampling rate, range, or other property that supplements the data gathered by the sensors of the downhole tool.

[0044] The smart dust cap 400 has a storage unit 406 for storing data gathered by the sensors of the smart dust cap 400. The storage unit 406 can also store data gathered by sensors of the downhole tool connected to the smart dust cap 400. As will be further explained below, the smart dust cap 400 forms an electrical connection with the downhole tool, enabling data transfer between the smart dust cap 400 and the downhole tool. The smart dust cap 400 has a local communication unit 408 that performs the data transfer function within the smart dust cap 400 and between the smart dust cap 400 and the downhole tool. The local communication unit 408 may be, or include, a bus for data, control, and/or addressing to support communication among the units of the smart dust cap 400. The local communication unit 408 may be, or include, an I/O device for electrically connected communication with another unit, such as a downhole tool, upload unit, configuration unit, or another unit that may be connected to the smart dust cap 400.

[0045] The smart dust cap 400 has a networking unit 410 that performs a networking function with other units. The networking unit 410 forms communication connections with any desired networks, such as TCP/IP networks or near-field communication networks such as RFID and Bluetooth networks. The networking unit 410 may support other protocols, such as Z-Wave, CAN bus, MQTT, and CoAP. In one embodiment, the networking unit 410 includes a Bluetooth transceiver and a WiFi transceiver for wireless communication at different rates and quantities. The networking unit 410 can be configured to any desired networking architecture or standard.

[0046] The smart dust cap 400 has a processing unit 412 that performs data manipulation and configuration for the other units of the smart dust cap 400. The processing unit may be configured to prepare data from the sensor unit 404 for storage in the storage unit 406, to control the sensor unit 406 to generate sensor signals, to control the local communication unit 408 to send and receive signals and data, to control the networking unit 410 to send and receive signals and data, to prepare data from the sensor unit 404 or the storage unit 406 for sending along the local communication unit 408 or the networking unit 410, to interpret signals from the sensor unit 404, the local communication unit 408, or the networking unit 410 as data or configuration and apply the data or configuration appropriately, and other processing functions.

[0047] The processing unit 412 includes a peering unit 414 that performs a peering function between the smart dust cap 400 and a downhole tool to which the smart dust cap 400 is connected. Fig. 4 is a communication diagram 400 describing the peering function of the smart dust cap 400 in connecting to the downhole tool. As shown in Fig. 4, the smart dust cap is peered with the downhole tool. The smart dust cap 400 has a peering identification stored in the storage unit 406. The downhole tool has an identification, for example a serial number or other identifying code. When the smart dust cap 400 forms an electrical connection with the downhole tool, the local communication unit 408 is engaged to communicate with circuits of the downhole tool. The peering unit 414 sends a signal to the downhole tool through the local communication unit 408 requesting the identification of the downhole tool. The downhole tool delivers the identification to the local communication unit 408, which in turn delivers the identification to the peering unit 414. The peering unit 414, before, during, or after receiving the identification, retrieves the peering identification from the storage unit 406. The peering unit 414 then compares the identification of the downhole tool with the peering identification, attempting to match the two codes. If the two codes match, the peering unit 414 sends a match signal. If the two codes do not match, the peering unit 414 sends a non-match signal. The match and non-match signals may be physical signals such as colored LEDs that are activated by the peering unit 414, or may be electromagnetic signals received by a terminal unit, such as a computer console or mobile communication unit, for displaying the result of the peering process.

[0048] The processing unit 412 has a configuration unit 416 that applies configuration signals to the units of the smart dust cap 400 and to the downhole tool. The configuration unit 416 is, itself, configured to output signals that change the operation of the downhole tool and the other units of the smart dust cap 400. The configuration unit 416 may be configured to translate instructions received from an external configuration unit into signals that can be applied to the units of the smart dust cap 400 and the downhole tool in the event, for example, that the communication protocols of the smart dust cap 400 and the downhole tool are proprietary or non-standard. The configuration unit 416 can configure the units of the smart dust cap 400 and the downhole tool with scheduling or sequencing configurations, operating programs, and data gathering/storage cycles, for example, or other configurations.

[0049] The processing unit 412 can have a data storage unit 418 that receives signals from sensors in the sensor unit 406 or from the downhole tool via the local communication unit 408, interprets the signals as digital data, perhaps computes parameters from the digital data or the signals, prepares the digital data and any computed parameters for storage, time-stamps the prepared data, and sends the prepared data to the storage unit 406. For this purpose, the processing unit 412 has a control unit 422 that controls interoperation of the other units with the downhole tool. Here, the control unit 422 may have a timing routine that provides the time-stamp for the prepared data. The timing routine can also provide timing for execution of the various configurations applied by the configuration unit 416.

[0050] The processing unit 412 can also have a data upload unit 418 that performs the function of uploading data from the smart dust cap 400 to an external data repository, such as a server or cloud installation. The data upload unit 418 is configured to engage when a network connection is established by the networking unit 410. In one embodiment, the smart dust cap 400 continuously attempts to establish a connection using the Bluetooth transceiver of the networking unit 410. When such a connection is established, for example when the downhole tool with the smart dust cap 400 is retracted from a well to the surface, the networking unit 410 signals the processing unit 412. The processing unit 412 then performs a registration procedure to register the smart dust cap 400 with the Bluetooth server, which is typically a surface server configured to establish Bluetooth connection with many smart dust caps such as the smart dust cap 400. A local application, at a local endpoint, can allow users to function test and check status of downhole tools before and after running in a well, using a smart dust cap 400 for each downhole tool.

[0051] When the registration procedure is complete, the processing unit 412 controls the networking unit 410 to establish a data transfer connection, such as a WiFi connection or other high-volume transfer protocol. Fig. 6 shows a system architecture 600 according to one embodiment. Gateways and/or data brokers 604 can connect to a WiFi network 606 that now includes one or more smart dust caps 602 to act as an aggregation point and coordinate connectivity of the smart dust caps, or other connected local endpoint devices 608, to each other and to the network to manage data messaging, network latency, and offline modes. The gateways and/or data brokers thus manage upload of data from a collection of smart dust caps to a repository 610, which may be a server, or cloud platform. The repository 610 may include storage 612. Where the repository 610 is a cloud platform, the repository 610 may include monitoring applications or systems 614, analysis applications or systems 616, and mobile devices 618, including supporting architecture for the mobile devices.

[0052] The gateways and/or data brokers can also manage download of configuration profiles and data to the smart dust caps for operation of each smart dust cap, or for the downhole tool. For example, the smart dust caps can be used to update firmware on the downhole tool. The download process can be performed while the smart dust cap is connected to the downhole tool, so that updates to the downhole tool are performed immediately, or the download process can be performed while the smart dust cap is disconnected, and when the smart dust cap is later connected to a downhole tool, after the peering process is complete, the firmware and/or configuration update of the downhole tool can be performed immediately thereafter.

[0053] Fig. 7 is an activity diagram 700 illustrating a use case of the smart tools described herein. In Fig. 7, a smart tool 702 is paired to a telemetry repeater tool 704. A plurality of such pairings is shown in Fig. 7, all digitally connected to a user device 706 for communicating with the smart-tool paired repeaters 704. By introducing apparatus and methods described herein in the management of the repeaters, each repeater 704 is peered with the corresponding smart tool 702 so that a field engineer/operator can automatically:

• Scan and detect all the available tool-repeater pairs from the user device 706, for example a mobile device such as a phone or tablet, using Bluetooth protocol.

• From the software controlling the telemetry system configured on the user device 706, the operator launches the configuration for all the repeaters 704 in parallel via the Bluetooth connection, saving a considerable amount of time for the repeater.

• The repeaters continue to stream their position and status to a data lake 708, configured with transceivers for wireless communication, for maintenance purposes. The user device 706 is also able to access the data lake 708 via any wireless protocol, using the telemetry tool software or another application, to inform the configuration and updating of the repeaters 704.

• At the end of the downhole job, the smart tool fetches data from the repeater’s memory and uploads them to the data lake for further engineering and maintenance processing.

[0054] Conventionally, downhole tool data is retrieved, and firmware and configuration updates are performed, by connecting a wire to the downhole tool from a terminal device, such as a tablet or laptop. The downhole tool must be positioned in a location for wired connection, and a wire must run from the terminal device to the downhole tool. The wireless capabilities of the smart tools described herein remove the requirement for physical staging of downhole tools for communication purposes.

[0055] Rechargeable batteries can be used in the smart tool. A plurality of such tools can be configured for wireless recharging at any convenient location. When downhole equipment is in storage at a workshop or in the field for deployment downhole, the smart tools can be wirelessly charged. Fig. 8 is an activity diagram illustrating how charging may be performed at a workshop location. At the workshop, downhole tools 802 are stored in a customized rack 804 that features a wireless inductive charging plate 806. A smart tool 808, any of the smart tools described herein, is coupled to each downhole tool 802. The wireless charging circuit of each smart tool 808 coupled with the charging plate 806 to recharge all the smart tools 808 positioned on the rack 804. This mechanism will remove or reduce the usage of cables, decreasing Health and Safety (HSE) hazards.

[0056] Fig. 9 is an activity diagram illustrating how charging may be performed at a well site location 900. Here, a well 902 is shown in operation with one or more downhole tools 904 deployed in the well. The downhole tools 904 may include one or more smart tools 906 in downhole operation. At the same time, a plurality of smart tools 912 are in storage at the well site location 900 undergoing charging, and potentially data transfer. A container 908 is provided at the well site location 900 for storage of the smart tools 912 and 906. The container 908 has one or more inductive charging pads 910. The smart tools are gathered and set on top of the wireless inductive charging pad 910 in the container 908 to charge the long duration batteries. In this way, a smart tool 912 can be retrieved from the charged inventory and installed on its peered tool for deployment downhole, and used smart tools 906 retrieved from downhole can be placed on the charging pad 910. As noted above, while the smart tools 912 are recharging, the communication circuitry of the smart tools 912 can be engaged to upload data to a repository and to download configuration information.

[0057] Fig. 10 is a table summarizing capabilities enabled by the apparatus and methods described herein. Use of the smart dust caps described herein will provide the means to reduce or eliminate unnecessary repairs, prevent catastrophic failures, and reduce the negative impact of routine maintenance operations on tool performance, especially in challenging well conditions. The MoT-based solution offer significant benefits.

[0058] Introducing a CBM solution enabled by MoT and ML capabilities to monitor real time evolution of parameters that affect tool operation will allow the engineers and technical experts to be in constant touch with their equipment data, which will be streamed directly to technology centers to monitor the health status of the equipment, by using collected parameters and quality alerts, and to monitor the overall operation of the equipment, by tracking equipment usage, embedded software update, energy consumptions and idle time. Based on real-time and historical data derived from the equipment, machine learning algorithms are continuously enriched to predict any imminent equipment failure by considering frequency, randomness of failures, correlation between the failures, the conditions exposed to the equipment and the cumulated time usage of the equipment.

[0059] Considering an unforgiving downhole, predictive maintenance using the MoT methods and apparatus described herein allows up-to-the-minute evaluation of equipment, such as downhole valves, gauges, triggers, etc., the unplanned failure of which would create a prolonged, unscheduled NPT, delaying drilling, testing, or production schedules. Reducing such unplanned outages also reduces risk of damaging reservoir formations due to overexposure to processing fluids [0060] Optimized drilling campaign, resulting from saving rig time due to avoided downtime (NPT)

[0061] Reduced risk of damaging the reservoir formation due to overexposure to drilling fluids (water-based mud or synthetic oil-based mud) in case of downhole equipment failure

[0062] Operational visibility and analysis that proactively reduces equipment failures, controls cost, and increases production availability

[0063] Improved accuracy of the operations forecast and planning by reducing waiting on logistics

[0064] Ensured compliance and safety by providing a comprehensive method, reducing human intervention for data collection.

[0065] Fig. 11 is an isometric view of a partially assembled smart tool 1100 according to another embodiment. A detachable lid 1112 of the tool 1100 is removed and shown to one side of the rest of the tool 1100. The smart tool 1100 is similar to the smart tools 302 described in connection with Fig. 3, with a more compact construction. Flere, the MoT circuit board 306 is mounted inside a case 1102 that allows the MoT circuit board 306 and the battery 304 to be arranged in parallel and overlapping relation to minimize overall size of the case 1102. An optional coax connector 1104 is disposed adjacent to the battery 304 in one plane, and the MoT circuit board 306 is disposed adjacent to the battery 304 and the coax connector 1104 in a different plane parallel to the plane defined by the battery 304 and the coax connector 1104. A wireless communication component 1110, for example a wifi card, can be located between the MoT circuit board 306 and the lid 1112, when assembled. The coax connector 1104 provides an alternative wired connection to the smart tool 1100 for power, data, and signal transfer at higher rates. The MoT circuit board 306 is located adjacent to an end 1106 of the case 1102 such that a digital connector 1108, such as a USB connector, can be located on the MoT circuit board 306 and ported to the exterior of the case 1102. If the higher transfer rates of a coax connection are not needed, the digital connector can be used for power, data, and signal transfer. A wireless charging coil 1106 is disposed in the lid 1112 electrically connected to the rechargeable battery 304. The wireless charging coil 1106 may also be electrically connected to the MoT circuit board 306 to allow program control of wireless charging.

[0066] The compact design of the smart tool 1100 allows use of such tools in any conceivable setting, above ground, below ground, under water, and airborne. In oil and gas applications, the smart tool 1100 can be paired with tools and sensors used in above ground operations, such as vibration monitors, environmental monitors, process sensors, imaging equipment, and the like, to collect and transmit data to a local or remote repository. For example, vibration monitors often used at sensitive locations in piping that conducts multiphase materials, which may contain for example sand, can be paired with the smart tool 1100 to store and transmit vibration data real-time to local or remote repositories and control systems for real-time monitoring and troubleshooting.

[0067] The smart tools described herein enable edge processing applications in oil and gas processing environments. As noted above, the processor disposed in the smart tool can be configured to perform calculations using data obtained from sensor in the smart tool and from connected well instruments. The results of the calculations can be used directly by the smart tool that performed the calculations. Additionally, the smart tool that performed the calculations may be configured to network directly with other smart tools in the vicinity, for example using Bluetooth functionality, to share the results of the calculations with the other smart tools.

[0068] Fig. 12 is a schematic architecture diagram showing an edge processing application using the smart tools described herein. A plurality of downhole tools 1202, each having a well instrument 1204 paired to a smart tool 1206, are shown. A first downhole tool 1202A, in this situation, is observed to experience an anomaly of some sort reflected in the data obtained from the corresponding well instrument 1204A. Flere, each smart tool 1206 is configured with a machine learning application that applies a model to analyze data obtained from the well instrument 1204. The machine learning application calculates one or more situation parameters that can be used to make decisions about the downhole tool 1202A, for example whether the tool is operable or not. The machine learning application can be configured to update training data as new data becomes available from operation of the well instrument. An updated training data set from the smart tool 1206A can be broadcast to the other smart tools 1206 in the vicinity using the Bluetooth functionality of each smart tool 1206. The machine learning application in each smart tool 1206 can be configured to recompute model parameters when new training data is absorbed from another smart tool 1206. The machine learning application may also include standard data set validation protocols, such as blockchain protocols or other validation protocols, to ensure that all the smart tools 1206 are using the most valid training data. In this way, processing for monitoring the operation of downhole tools can be performed locally in the field by the tools themselves, shared on a local ad hoc network, and when a central network or repository is detected by any of the tools the data and updated models can be uploaded to the repository. Until the central network or repository is available, however, the tools operate and make determinations about data and operations autonomously.

[0069] While the foregoing is directed to embodiments, other and further embodiments of the present disclosure may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.