• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    Certain aspects and characteristics relate to a system that effectively determines the optimum set points of an actuator to meet a goal of controlling equipment, such as drilling, production, completion, or other related operations. to the production of oil or gas from a wellbore. A platform can receive data and also use and communicate with multiple algorithms asynchronously and efficiently to project optimal automatic setpoints for controllable parameters. The services can deliver data over a real-time messaging bus. The data can be captured by an orchestrator that aggregates all the data and calls a resolver orchestrator to determine the optimized parameters for a current state over time to send to control systems or display in a dashboard. Figure for the abstract: Figure 1
    公开号:FR3084904A1
    申请号:FR1907264
    申请日:2019-07-01
    公开日:2020-02-14
    发明作者:Matthew Edwin Wise；Egidio Marotta；Keshava Prasad Rangarajan
    申请人:Landmark Graphics Corp；
    IPC主号:
    专利说明:

    Description
    Title of the invention: DISTRIBUTED CONTROL SYSTEM USING ASYNCHRONOUS SERVICES IN A WELLBORE
    Technical Field [0001] The present invention generally relates to devices intended to be used in wells. More particularly, the present invention relates to methods and systems for providing real-time asynchronous adaptive control of a tool used in a well.
    Prior Art A well includes a wellbore drilled through an underground formation. Conditions inside the underground formation in which wellbore tools are used can vary widely. For example, the formation through which a wellbore is drilled exerts a varying force on the drill bit of a drilling tool. This variable force may be due to the rotary movement of the drill bit, the weight applied to the drill bit and the friction characteristics of each layer of the formation. A drill bit can pass through many different materials (rock, sand, shale, clay, etc.) during the wellbore formation and adjustments to various drilling parameters are sometimes made during the drilling process by a drilling operator. drilling to account for observed changes. A similar process can be followed when tools and equipment for completion and production operations are used. The effectiveness of the adjustments made by the operator is determined in the future by the success or failure of the wellbore operations.
    Brief description of the drawings [0003] [fig.l] Figure 1 is a cross-sectional view of an example of a drilling arrangement which includes an asynchronous control system in real time of a drilling tool according to certain aspects of the invention.
    [Fig-2] Figure 2 is a block diagram of an asynchronous control system in real time of a drilling tool according to certain aspects of the invention.
    [0005] [fig.3] Figure 3 is a flow diagram of an asynchronous control process in real time of a drilling tool according to certain aspects of the invention.
    [0006] [fig.4] Figure 4 is a diagram of a software architecture for the asynchronous control in real time of a drilling tool according to certain aspects of the invention.
    FIG. 5 is a diagram showing a data flow for the software architecture represented in FIG. 4, according to certain aspects of the invention.
    [Fig-6] Figure 6 is a flow diagram of another asynchronous control process in real time of a drilling tool according to certain aspects of the invention.
    [0009] [fig.7] Figure 7 is a screen display which can be produced by an asynchronous control system in real time of a drilling tool according to certain aspects of the invention.
    [Fig.8] Figure 8 is a screen display which can be produced by an asynchronous control system in real time of a drilling tool according to certain aspects of the invention.
    [Fig-9] Figure 9 is a screen display that can be produced by an asynchronous real-time control system of a drilling tool according to certain aspects of the invention.
    Description of the embodiments Certain aspects and characteristics relate to a system which effectively determines the optimal set points of an actuator in order to meet an objective of controlling equipment, such as drilling, production, completion or other operations associated with the production of oil or gas from a borehole. For the purposes of some of the examples described here, a digital twin can be an intermediary for the equipment. Optimal controllable setpoints can be calculated, taking into account constraints and information obtained from distributed models, and can be used for real-time closed-loop control and automation or for advisory display .
    Certain aspects and characteristics provide a platform that can receive data via an Internet of Things (loT) interface, use and communicate with several algorithms asynchronously and efficiently to project optimal setpoints for parameters that can be ordered to optimize operations such as drilling, pumping, production or completion with all constraints. The methodology facilitates the quick and efficient calculation of the required set points. The algorithms can include several micro-services and analysis applications, each of which can be qualified as a service. Each service can provide data via a messaging bus in real time asynchronously and the data can be obtained by a central orchestrator which aggregates all the data and calls a resolver engine to determine parameters optimized for a current state in time to send to control systems or to display on a dashboard. The central orchestrator that aggregates data asynchronously can invoke the resolver engine based on a time trigger from an original data source in a real-time stream.
    In some examples, a system includes wellbore equipment and a processing device coupled in communication to the wellbore equipment. A non-transient memory device includes instructions that are executable by the processing device to cause it to perform operations. The operations include asynchronously receiving telemetry on one or more orchestrators coupled in communication to a real-time messaging bus (RTMB), calling a service to obtain results based on telemetry, publishing the results on the messaging bus in real time to be used by the orchestrators, and the reconversion or the update of one or more models distributed between the orchestrators using the results. The operations further include resolving a target using one or more of the models to generate set points for controlling the wellbore equipment and sending an advisory display or well equipment.
    These examples given by way of illustration are intended to familiarize the reader with the general subject treated here and are not intended to limit the scope of the concepts described. The following sections describe various additional features and examples with reference to the drawings, in which the same numbers denote identical elements, and directional descriptions are used to describe the illustrative aspects but, like the illustrative aspects, should not be used to limit the present invention.
    Figure 1 is a cross-sectional view of an example of a well system
    100 which can use one or more principles of the present invention. A wellbore can be created by drilling into the ground 102 using the drilling system 100. The drilling system 100 can be configured to drive a lower hole assembly (BHA) 104 positioned or otherwise disposed at the bottom of a drill string 106 deployed in the soil 102 from a derrick 108 disposed at the surface 110. The derrick 108 includes a square rod 112 used to lower and raise the drill string 106. The BHA 104 may include a drill bit 114 operatively coupled to a tool train 116, which can be moved axially within a drilled wellbore 118 by being attached to the drill train 106. The tool train 116 may include one or more sensors 109 for determining the conditions of the drill bit and the wellbore, and returning values for various parameters to the surface by means of wiring (not shown) or by a wireless signal. The combination of any support structure (in this example, a derrick 108), any motor, all electrical connections and any support for the drill string and the tool train can be referred to herein as the drill arrangement.
    During operation, the drill bit 114 enters the soil 102 and thus creates the wellbore 118. The BHA 104 provides control of the drill bit 114 as it advances in the soil 102. The fluid or the “mud” coming from a mud tank 120 can be pumped downhole using a mud pump 122 supplied by an adjacent power source, such as a motive machine or a motor 124 The mud can be pumped from the mud reservoir 120, through a riser 126, which brings the mud into the drill string 106 and transports it to the drill bit 114. The mud leaves one or more nozzles ( not shown) arranged in the drill bit 114 and, in the method, cools the drill bit 114. After leaving the drill bit 114, the mud returns to the surface 110 via the annular space defined between the wellbore 118 and the drill string 106 and, in the proc dice returns drill cuttings and debris to the surface. The cuttings and the slurry mixture are passed through a flow line 128 and are treated so that a cleaned sludge is returned to the hole again through the riser 126.
    Still with reference to FIG. 1, the drilling arrangement and all the sensors 109 (through the drilling arrangement or directly) are connected to a computer device 140a. In FIG. 1, the computing device 140a is illustrated as being deployed in a vehicle 142, however, a computing device intended to receive data coming from sensors 109 and the control drill bit 114 of the drilling tool can be installed in a building such as a construction site shelter, be portable or be located remotely. In some examples, the computing device 140a can process at least part of the data received and can transmit the processed or unprocessed data to another computing device 140b via a wired or wireless network 146. The other computing device 140b can be off site, for example in a data processing center or located near the computing device 140a. Either or both of the computing devices can execute computer program code instructions that allow a processor to act as an orchestrator, service, or micro-service. The computing devices 140 a and b can include a processor interfaced with other hardware via a bus and a memory, which can include any tangible medium readable by computer (and not transient), such as a random access memory, a read only memory, an EEPROM or the like, may include program components which configure the operation of the computing devices 140a and b. In some aspects, the computing devices 140 a and b may include input / output interface components (eg, screen, printer, keyboard, touchpad, and mouse) and additional storage.
    The computer devices 140 a and b may include communication devices 144 a and b. The communication devices 144 a and b can represent any one or more components facilitating a network connection. In the example shown in FIG. 1, the communication devices 144 a and b are wireless and can include wireless interfaces such as IEEE 802.11, Bluetooth or radio interfaces for accessing cellular telephone networks (for example, transmitter- receiver / antenna to access a CDMA, GSM, UMTS or other mobile communication network). In some examples, the communication devices 144 a and b may use acoustic waves, surface waves, vibrations, optical waves or an induction (for example a magnetic induction) to initiate wireless communications. In other examples, communication devices 144 a and b can be wired and can include interfaces such as an Ethernet, USB, IEEE 1394 interface, or a fiber optic interface. The computing devices 140 a and b can receive wired or wireless communications therebetween and perform one or more communications-based tasks. These communications can include communications over the RTMB, which can be implemented on almost any type of physical communication layer. The computer resources presented by way of examples in the present description can be adapted to multiple arrangements of equipment and can communicate under the control of an orchestrator. The orchestrators are described in more detail below. Transmission between computing devices can be supported by data replication. It cannot be overemphasized that the drilling system presented above is just one example. The distributed system described here can also be used with other equipment. Non-limiting examples include equipment used for the production, completion, exploration or development of reservoirs.
    Figure 2 is a block diagram of an example of a system 200 for implementing all or part of a real-time optimization platform (RTOP) according to certain aspects. For example, system 200 can be used to implement one or more orchestrators. In some examples, the components shown in Figure 2 (for example, the computing device 140, the power source 220 and the communications device 144) can be integrated into a single structure. For example, the components can be in a single housing. The real-time message bus 221 may also be included in the computing device, or alternatively may be separate. The micro-service 222 can also be included in the computer device 140 or be separate. In other examples, most or all of the components shown in Figure 2 can be distributed (for example, in separate housings) and in electrical communication with each other.
    The system 200 includes a computer device 140. The computer device 140 can include a processor 204, a memory 207 and an internal bus 206. The processor
    204 can execute one or more operations of computer program code instructions 210 intended to implement instructions 211 of computer program code or of an orchestrator to execute other operations related to the asynchronous command in real time from wellbore equipment and related to various services, including a remote message queuing server (RMQ). The processor 204 can execute instructions stored in the memory 207 to carry out the operations. Processor 204 may include a processing device or more than one processing device. Non-limiting examples of processor 204 include a matrix of user-programmable doors ("FPGA"), an application-specific integrated circuit ("ASIC"), a microprocessor, etc.
    The processor 204 can be coupled in communication to the memory 207 via the internal bus 206. The non-volatile memory 207 can include any type of memory device which retains the information stored when it is turned off. Nonlimiting examples of the memory 207 include an electrically erasable programmable read-only memory (“EEPROM”), a flash memory or any other type of non-volatile memory. In some examples, at least a portion of the memory 207 may include a medium from which the processor 204 can read instructions. Computer readable media may include electronic, optical, magnetic or other storage devices capable of providing processor 204 with computer readable instructions or other program code. Non-limiting examples of computer readable media include (but are not limited to) magnetic disk (s), memory chip (s), read only memory, random access memory ("RAM"), ASIC, configured processor, optical storage, or any other medium from which a computer processor can read instructions. The instructions may include processor-specific instructions generated by a compiler or an interpreter from code written in an appropriate computer programming language, including, for example, C, C ++, C #, etc.
    The system 200 may include an energy source 220. The energy source 220 may be in electrical communication with the computer device 140 and the communications device 144. In some examples, the energy source 220 may include a battery or an electric cable (for example, a wire cable). In some examples, the power source 220 may include an alternating current signal generator. The computing device 140 can operate the power source 220 to apply a transmission signal to the antenna 228. For example, the computing device 140 can cause the power source 220 to apply a voltage with a frequency within a range frequency specific to antenna 228. This can cause antenna 228 to generate wireless transmission. In other examples, the computing device 140, rather than the power source 220, can apply the transmission signal to the antenna 228 to generate the wireless transmission.
    The system 200 may also include the communications device 144. The communications device 144 may include or may be coupled to the antenna 228. In some examples, part of the communications device 144 may be implemented in a software. For example, the communications device 144 may include instructions stored in memory 207. The communications device 144 may receive signals from remote devices and transmit data to remote devices (for example, the computing device 140b in Figure 1). For example, the communications device 144 can transmit wireless communications that are modulated by data via the antenna 228. In some examples, the communications device 144 can receive signals (for example, associated with data to be transmitted) from processor 204 and amplify, filter, modulate, change frequency and otherwise manipulate signals. In some examples, the communications device 144 can transmit the manipulated signals to the antenna 228. The antenna 228 can receive the manipulated signals and generate in response wireless communications which transport the data.
    The system 200 can receive an input from the sensor or sensors 109, illustrated in FIG. 1. The system 200 in this example also includes an input / output interface 232. The input / output interface 232 can connect to a keyboard, pointing device, display device and other computer input / output devices. An operator can provide input using the input / output interface 232. An operator can also display an advisory display of setpoints or other information such as a dashboard on a screen. display included in the 232 input / output interface.
    FIG. 3 is an example of a flow diagram of a process 300 for asynchronous real-time control of a drilling tool according to certain aspects of the invention. At block 302, the system asynchronously receives telemetry at one of the orchestrators coupled in communication to the real-time messaging bus 221. At block 304, processor 204 calls a service to obtain results based on telemetry . At block 308, the processor publishes the results to the RTMB 221 for use by orchestrators. In block 312, at least one engineering or machine learning model distributed among the orchestrators is updated or reconverted using the results. In some aspects, an engineering model is updated while a machine learning model is converted. At block 314, processor 204 uses the engineering or machine learning model to solve one or more objectives, by generating setpoints to control the equipment. The system can solve a single objective or several objectives simultaneously. At block 316, processor 204 sends the set points to an advisory display, to the equipment, or to its digital twin.
    FIG. 4 is a diagram of a software architecture for the RTOP 400 which can provide real-time asynchronous control of a drilling tool according to certain aspects of the description. In some aspects, RTOP allows various services to use real-time data asynchronously. The result of these different services is used to solve a goal. A platform of this type can be set up to optimize the drilling parameters in order to meet a defined objective such as optimizing the penetration rate (ROP). The platform can also meet several objectives, for example optimizing the ROP and minimizing the specific mechanical energy (MSE). The real-time telemetry data of Figure 4 can be used by digital sensors 402 (DS 1, DS 2, DS N) from various external sources. These sources, for example, may include platform equipment, downhole equipment, surface control equipment or digital representations (digital twins) of this equipment. Data is ingested via the Internet of Things (loT) gateway 404 rather than directly by applications located on the RTOP. Therefore, new data sources can be integrated without modifying the underlying applications. The loT 404 gateway is responsible for standardizing data from any external data source into a common model understood by the applications located on the platform in question. The loT 404 gateway is also responsible for denormalizing data to control systems in the outbound direction. The loT 404 gateway includes control system and internal system drivers.
    Still with reference to FIG. 4, the telemetry motor 405 processes the telemetry data. The engine removes outliers of statistical data points and can also smooth data on various frequencies provided by frequency inputs 406. 1 Hz, 0.2 Hz and 1 point output by 0.1 foot are some examples of frequencies. Higher or lower values can be used. The output of each telemetry operation produces telemetry which is sent to the RTMB. The micro-service repository 407 is coupled in communication to the orchestrators 408 for the 1-N machine learning models and to the orchestrators 410 for the 1-N engineering models. The 407 micro-service repository includes training and forecasting micro-services for 1-N machine learning models and micro-services for 1-N engineering models. All the orchestrators are coupled in communication to the RTMB 221. A connector 412 for a Web application programming interface (API) and a
    Persistence service APIs 414 are coupled in communication to each other, as well as to micro-services (MS) and service repository 416. API 414 also accesses data store 415, where the previous data from the current optimization is cached. The repository 416 provides control and display dashboards similar to those discussed below in relation to FIGS. 7 to 9 as well as micro-services for selecting the best model to use to provide set points, serve the resolver orchestrator 418, and provide forecasting support for machine learning models 408 and engineering models 410. Bridge 420 couples the RTMB into communication with a RTMB to a WebSocket for use in the real-time display dashboard.
    Figure 5 is a diagram showing a data flow 500 for the software architecture shown in Figure 4, in accordance with certain aspects of the invention. Legend 502 indicates which data paths are for sensor data, which data paths are for actuator data, which data paths are for application data, and which data paths are for HTTP data. The loT 404 gateway uses data transmission protocols to send and receive real-time (RT) data to and from devices 504, each of which can be a sensor or an actuator. The RMQ server 506 is managed by the processor 204 using computer program instructions 211 and is coupled in communication to the resolver orchestration routines 508 and to the service orchestration routines 510, which are coupled in communication to the micro-services 512 and 514. Bridge 420 communicates with the user interface dashboard 516, which is part of the micro-service and of the service repository 416. The user interface management dashboards 518 are also part of the micro-service and service repository 416. The processor 204 also manages a reverse proxy 520. The persistence and transmission functions 522 are managed by ΓΑΡΙ of persistence or of service 414.
    FIG. 6 is a flow diagram of another process 600 for real-time asynchronous control of a drilling tool according to certain aspects of the invention. In block 604, the system independently receives data on the orchestrator or orchestrators from the telemetry engine 405 and the loT gateway 404 via the RTMB 221. In block 606, an orchestrator determines whether a service or a micro-service must be called to obtain new results in order to convert or update models. Models can include machine learning models as well as engineering models which can be a physics-based, deterministic, analysis-based, or hybrid model. A hybrid model is based on a machine learning model and one or more other models. If no reconversion or no update is necessary at block 607, the processing returns to block 604. Otherwise, the processing goes to block 608, where the orchestrator calls the service and waits for the results. The orchestrator receives the updated results in block 610 and publishes them to the RTMB for use by other orchestrators or departments. Each orchestrator operates independently and will not block or add latency to other orchestrators or services. Orchestrators form a distributed system for objective-based optimization to resolve one or more objectives, such as optimizing the ROP while minimizing the MSE. Services can also retrieve data from historical files in data store 415. This data can include previous data from the current optimization activity or data from previous activities. This data is useful when the services are online and need to determine the context or when services need additional data to complete the training of their models or their calculation inputs.
    Still with reference to FIG. 6, in block 614, the central orchestrator uses the updated results from the other orchestrators and applies this information to the resolution of the actuator set points. The resolver orchestrator will select the best model to achieve a goal and apply constraints to possible set points based on engineering calculations performed as part of the model orchestration. After resolution, the set points are sent back on the RTMB 221 to block 616 where they can be used by the user interface dashboards for an advisory display or be sent via the loT gateway for command d automation in closed loop, possibly by controlling a digital twin.
    Using a digital twin of the equipment, the forecasts for future moments can be calculated in advance. The central orchestrator can receive requests for data corresponding to future time stamps and use their global knowledge of a combination of current system state, historical information and prospective models to provide estimates of optimal setpoints. In some aspects, these set points can be both sent to a user interface for monitoring (deviation from nominal functional health) and can be sent early to control systems which will check for the possibility of a failure. due to invalid parameters. This global knowledge of the current state of the system and the consideration of the environment allows the digital twin to adapt and learn, thus improving the accuracy of its forecasts for the estimations of optimal set points.
    The uncertainty in the prediction of the model for the optimal setpoint estimates can be quantified by two characteristics of the learning process, namely error and noise. These two characteristics have a significant influence on the forecast accuracy and the learning ability of the digital twin. An error measure can be used to quantify how close each prediction from the hypothesis (for example, the digital twin) approximates to the target function (for example, true value). In some ways, the data generated for the ingestion of the digital twin is not deterministic; they are generated noisily, so the output (the forecast) is not determined solely by the input data. The system can compensate for the latter problem using probabilistic techniques as opposed to deterministic techniques; a digital twin output distribution and an input distribution for digital twin ingestion. Both distributions will have probabilistic effects as you learn with the digital twin.
    Several user interface (UI) dashboards can be used to facilitate the operation of the distributed system. Figure 7 shows a dashboard 700 that can be used as a real-time display, which targets an end user monitoring the activity of applications running on the platform or following advice to manually define control points on the equipment. The 702 virtual gauges show the current values for depth, ROP, speed in rpm, drill bit load (WOB) and mud flow. Historical values are plotted as a function of depth, using different lines for optimized values, drilling continuation values and actual values, as indicated by legend 704. Historical ROP values are shown graphically in box 706 The historical values of the drilling speed in rpm are shown graphically in box 708. The historical values of the flow (Q) in gallons per minute (GPM) are graphically indicated in box 710 and the historical values for the load on the drill bit (WOB) are shown graphically in box 712.
    Figure 8 shows a dashboard 800 which contains entries for system components and the ability to manage available services and orchestrators, as well as commands that have been activated. The 802 combo boxes allow the user to define a "case". A case is a combination of identifying information such as project, training, well, etc. which allows data to be stored and retrieved later. The 804 radio buttons allow the user to set the optimizer mode as a planning mode or an execution mode. Panel 806 allows the user to enter operating ranges for WOB, flow, and revolutions per minute. The panel
    808 allows the user to enter one or more relevant execution parameters. In this case, the depth is the parameter that applies. The inputs provided can be applied with the 810 button.
    Still with reference to FIG. 8, the right side of the dashboard 800 has controls for managing the orchestrators, the constraint services and the objectives. New orchestrators can be added to the dashboard with the 812 button and the 814 button restores the orchestrators included in the default configuration. Panel 816 lists the orchestrators and each of them can be activated by checking a box. New constraint services can be added to the dashboard with the 818 button and the 820 button restores the constraint services included in the default configuration. Panel 822 lists the constraint services and each of them can be activated by checking a box. New objectives can be added to the dashboard with the 824 button and the 826 button restores the objectives included in the default configuration. Panel 828 lists the objectives and each of them can be activated again by checking a box.
    Figure 9 is a screenshot of a user interface display 900 which shows a dashboard that can be used to monitor the status and health of services and orchestrators based on certain aspects of the 'invention. The 900 display includes panels organized around related categories. The model indicators are displayed in panel 902. The constraint indicators are displayed in panel 904. The output indicators are displayed in panel 906 and the resolver indicators in panel 908. Model indicators include the indicator 910 for the linear ROP machine learning (ML) model, the indicator 912 for the non-linear ROP machine learning model, the indicator 914 for a ROP neural network model of machine learning and the indicator 916 for the actual machine learning ROP values applied. The strain indicators include the integrity indicator 918 for the drill string, the indicator 920 for cleaning the hole and the indicator 922 for vibration analysis. The output flags include flag 924 for bridge state 420 and flag 926, which indicates the state of the actuator client in loT 404 gateway. Flag 928 is for a resolver orchestrator that resolves surface parameters. Indicator 930, located in the middle of the display, has been selected for the status display and all the other indicators displayed are linked to drilling activity solutions for the surface parameters determined by Activity Torchestrator. drilling.
    Still with reference to FIG. 9, each indicator includes a status indicator in the lower right corner of the graphic element. The flat line of the 922 vibration analysis indicator indicates a vibration analysis problem. The check mark displayed in the drill string integrity indicator 918 indicates that the condition is normal, but the software that provides the drill string integrity constraint is currently not performing any task. The swivel arrow status indicator, as shown in the 920 hole cleaning indicator, indicates that the software involved in providing this function is currently performing operations.
    The terminology used in this document is for the sole purpose of describing particular embodiments and is not limiting. As used herein, the singular forms "a", "an", "the" and "the" are understood to include forms in the plural as well, unless the context clearly indicates otherwise. It will also be understood that the terms “comprises” or “comprising”, when used in this description, specify the presence of the characteristics, stages, operations, elements or components mentioned, but do not not exclude the presence or addition of one or more other characteristics, steps, operations, elements, components or groups thereof. In addition, comparative quantitative terms such as "above", "below", "less" and "larger" are intended to encompass the concept of equality. Thus, "less" can mean not only "less" in the strictest mathematical sense, but also, "less than or equal to".
    Unless otherwise indicated, it is understood that, throughout this description, terms such as "treatment", "calculation", "determination", "operations" or the like, denote actions or processes of a computer device, such as the control device or the processing device described in this document, which can manipulate or transform data represented in the form of physical, electronic or magnetic quantities in memories, registers or other devices storage of information, transmission or display. The order of the process blocks shown in the examples above can be changed, for example, blocks can be rearranged, combined or broken down into sub-blocks. Certain blocks or certain processes can be carried out in parallel. The use of "configured for" in this document reflects an open and inclusive language that does not exclude devices configured to perform additional tasks or steps. In addition, the use of "on the basis of" is intended to be open and inclusive, in the sense that a process, step, calculation or other action "on the basis of" one or more stated conditions or values may, in practice, be based on additional conditions or values beyond those cited. Elements described as "connected", "connectable" or with similar terms can be connected directly or via intermediate elements.
    In some aspects, a system for providing distributed control using asynchronous services is provided according to one or more of the following examples. As used below, any reference to a series of examples should be understood as a reference to each of these examples in a non-contiguous manner (for example, "Examples 1 to 4" should be understood as "Examples 1, 2 , 3 or 4 ”).
    Example 1. A system includes wellbore equipment which can be positioned in a wellbore, a processing device coupled in communication to the wellbore equipment, and a non-transient memory device including instructions executable by the processing device to cause the processing device to perform operations. The operations include the asynchronous reception of the telemetry by at least one orchestrator of several orchestrators coupled in communication to a messaging bus in real time; calling a service to obtain results based on telemetry, publishing the results on the messaging bus in real time to allow their use by orchestrators, reconversion or updating at least of a distributed model among the plurality of orchestrators using the results, solving a target using the at least one model to generate set points for controlling the wellbore equipment and sending set points to an advisory display or to wellbore equipment via the real-time messaging bus.
    Example 2. The system of Example 1 in which the set points are sent to the wellbore equipment via a digital twin coupled in communication to the messaging bus in real time.
    Example 3. The system of Examples 1 to 2 in which the operations also include the reception of telemetry data at an Internet of Things gateway (loT), the removal of outliers of statistical data points from telemetry data , smoothing telemetry data on multiple frequencies to generate telemetry, and sending telemetry to the messaging bus in real time.
    Example 4. The system of Examples 1 to 3 in which the set points are sent to the wellbore equipment via the loT gateway.
    Example 5. The system of Examples 1 to 4, in which the resolution of the objective includes the resolution of several objectives simultaneously.
    Example 6 The system of Examples 1 to 5 in which the resolution of the objective further includes the reception of the results of the orchestrators at the level of a central orchestrator and the transmission of the results of the central orchestrator to a resolver orchestrator .
    Example 7. The system of Examples 1 to 6 in which the drilling equipment includes a drilling tool and in which the at least one model is a machine learning model, a physics-based model, a deterministic model, an analysis-based model, a hybrid model or a combination of all or part of these models.
    Example 8. A method includes the asynchronous reception of a telemetry by at least one of the multiple orchestrators coupled in communication to a messaging bus in real time, the call, by a processor, of a service for obtain results based on telemetry, publication of results on the messaging bus in real time for use by orchestrators, reconversion or updating, by the processor, of at least one model distributed among the plurality of orchestrators using the results, the resolution, by the processor, of a target using the at least one model to generate set points in order to control the well drilling equipment positioned in a well drilling and sending the set points to an advisory display or to a drilling tool on the messaging bus in real time. Example 9. The method of Example 8, in which the set points are sent to the drilling tool by sending the set points to a digital twin of the drilling tool coupled in communication to the bus. real-time messaging. Example 10. The method of Examples 8 to 9 further includes receiving telemetry data at an Internet of Things (LOT) gateway, removing outliers of outliers from telemetry data, smoothing telemetry data on multiple frequencies to generate telemetry, and sending telemetry to the messaging bus in real time.
    Example 11. The method of Examples 8 to 10, in which the resolution of the objective includes the resolution of several objectives simultaneously.
    Example 12 The method of Examples 8 to 11, in which the resolution of the objective further includes the reception of the results of the orchestrators at the level of a central orchestrator and the transmission of the results from the central orchestrator to an orchestrator of solver.
    Example 13. The method of Examples 8 to 12, in which the at least one model includes a machine learning model, a physics-based model, a deterministic model, an analysis-based model, a hybrid model or a combination of all or part of these models.
    Example 14. A non-transient computer-readable medium includes instructions which are executable by a processor to cause it to perform operations related to an asynchronous control in real time of a wellbore equipment. The operations include the asynchronous reception of the telemetry by at least one of the multiple orchestrators coupled in communication to a messaging bus in real time, the calling of a service to obtain results based on the telemetry, the publication of the results on the messaging bus in real time, to be used by the orchestrators, the reconversion or the updating of at least one model distributed among the plurality of orchestrators using the results, the resolution of a target to using the at least one template to generate setpoints for controlling the wellbore equipment that can be positioned in a wellbore, and sending the setpoints to an advisory display or to the well equipment on the real-time messaging bus.
    Example 15. The non-transient computer-readable medium of Example 14 in which the set points are sent to the wellbore equipment via a digital twin coupled in communication to the messaging bus in real time.
    Example 16. The non-transient computer-readable medium of Examples 14 and 15, in which the operations further include receiving telemetry data at an Internet of Things gateway (loT), removing the dots from outliers of telemetry data, smoothing of telemetry data on multiple frequencies to generate telemetry and for sending telemetry to the messaging bus in real time.
    Example 17. The non-transient computer-readable medium of Examples 14 to 16, wherein the set points are sent to the wellbore equipment via the loT gateway.
    Example 18. The non-transient computer-readable medium of Examples 14 to 17, in which the resolution of the objective includes the resolution of several objectives simultaneously.
    Example 19. The non-transient computer-readable medium of Examples 14 to 18, in which the resolution of the objective further includes the reception of the results of the orchestrators at the level of a central orchestrator and the transmission of the results of the central orchestrator to a resolver orchestrator.
    Example 20. The non-transient computer-readable medium of Examples 14 to 19, wherein the at least one model includes a machine learning model, a physics-based model, a deterministic model, and a model based on analysis, a hybrid model, or a combination of all or part of these models.
    The foregoing description of examples, including illustrated examples, has been presented for purposes of illustration and description only, and is not intended to be exhaustive or to limit the subject to the specific forms described. Many modifications, combinations, adaptations, uses and installations of these can be obvious to a person skilled in the art without departing from the scope of the present invention. The illustrative examples described above are intended to present to the reader the general subject matter discussed here and are not intended to limit the scope of the concepts described.
    权利要求:
    Claims (1)
    [1" id="c-fr-0001]
    claims [Claim 1] System comprising:drilling equipment that can be positioned in a wellbore;a processing device coupled in communication with the wellbore equipment; anda non-transient memory device comprising instructions which are executable by the processing device to cause it to carry out operations comprising:asynchronously receiving telemetry by at least one orchestrator of a plurality of orchestrators coupled in communication to a messaging bus in real time;calling a service to get results based on telemetry; publication of the results on the messaging bus in real time for use by the plurality of orchestrators;reconversion or updating of at least one model distributed among the plurality of orchestrators using the results;solving a goal using at least one model to generate setpoints for controlling wellbore equipment; andsending setpoints to an advisory display or sink equipment on the real-time messaging bus. [Claim 2] The system of claim 1, wherein the set points are sent to the wellbore equipment via a digital twin coupled in communication to the messaging bus in real time. [Claim 3] The system of claim 1 or claim 2, wherein the operations further include:reception of telemetry data on an Internet of Things (LOT) gateway;the removal of outliers from the telemetry data;smoothing telemetry data over a plurality of frequencies to generate telemetry; andsending telemetry to the messaging bus in real time. [Claim 4] The system of claim 3, wherein the set points are sent to the wellbore equipment via the
    LoT gateway. [Claim 5] A system according to claim 1 or claim 2, wherein the resolution of the objective comprises the resolution of several objectives simultaneously. [Claim 6] The system of claim 1 or claim 2, wherein the resolution of the objective further comprises:receiving the results of the plurality of orchestrators at a central orchestrator; andtransmission of the results from the central orchestrator to a resolver orchestrator. [Claim 7] The system of claim 6, wherein the wellbore equipment comprises a drilling tool and wherein the at least one model comprises at least one of a machine learning model, a physics-based model, a deterministic model, an analysis-based model or a hybrid model. [Claim 8] Process comprising:asynchronously receiving telemetry by at least one orchestrator of a plurality of orchestrators coupled in communication to a messaging bus in real time;the call, by a processor, of a service to obtain results based on telemetry;publication of the results on the messaging bus in real time for use by the plurality of orchestrators;the reconversion or updating, by the processor, of at least one model distributed among the plurality of orchestrators using the results;processor resolution of a target using at least one model to generate setpoints for controlling wellbore equipment positioned in a wellbore; and sending setpoints to an advisory display or drill tool on the real-time messaging bus. [Claim 9] The method of claim 8, wherein the set points are sent to the drilling tool by sending the set points to a digital twin of the drilling tool coupled in communication to the messaging bus in real time. [Claim 10] A method according to claim 8 or claim 9, comprising
    outraged :
    reception of telemetry data on an Internet of Things (LOT) gateway;the removal of outliers from the telemetry data;smoothing telemetry data over a plurality of frequencies to generate telemetry; andsending telemetry to the messaging bus in real time. [Claim 11] The method of claim 10, wherein the setpoints are sent to the wellbore equipment via the loT gateway. [Claim 12] The method of claim 8 or claim 9, wherein solving the objective comprises solving several objectives simultaneously. [Claim 13] The method of claim 8, wherein solving the objective further comprises:receiving the results of the plurality of orchestrators at a central orchestrator; andtransmission of the results from the central orchestrator to a resolver orchestrator. [Claim 14] The method of claim 8, claim 9 or claim 13, wherein the at least one model comprises at least one of a machine learning model, a physics-based model, a deterministic model, a model based on analysis or a hybrid model. [Claim 15] A non-transient computer-readable medium which includes instructions executable by a processor to cause it to perform operations related to asynchronous real-time control of wellbore equipment, the operations comprising the method of claim 8, the claim 9 or claim 13.
    1/9
    类似技术:
    公开号 | 公开日 | 专利标题
    US10991248B2|2021-04-27|Parking identification and availability prediction
    FR3084904A1|2020-02-14|DISTRIBUTED CONTROL SYSTEM USING ASYNCHRONOUS SERVICES IN A WELLBORE
    US20210166166A1|2021-06-03|Wellsite report system
    US10706483B2|2020-07-07|Well planning and drilling service
    US20210017838A1|2021-01-21|Rescheduling one or more tasks of a digital plan associated with subsystems of a wellsite based on the wellsite's state
    EP2575089A1|2013-04-03|Customizable user interface for real-time oilfield data visualization
    FR3070180A1|2019-02-22|NEURON NETWORK MODELS FOR REAL-TIME OPTIMIZATION OF DRILLING PARAMETERS DURING DRILLING OPERATIONS
    CN111279050A|2020-06-12|Well planning system
    FR3081026A1|2019-11-15|LEARNING-BASED BAYESIAN Optimization to Optimize CONTROLLED Drilling Parameters
    CA3040959A1|2019-10-19|Computer platform for the aggregation and visualization of digital data
    FR3072412A1|2019-04-19|DETECTION OF BLOCKED PIPING
    WO2021007291A1|2021-01-14|Identification and validation of roads using aerial imagery and mobile location information
    FR3073555A1|2019-05-17|AUTOMATIC DETECTION OF ABNORMAL DRILL DATA ABNORMAL TREND FOR PREVENT RISK
    CN111655966A|2020-09-11|System and method for real-time data quality analysis in a drilling apparatus
    US10626714B2|2020-04-21|Wellsite performance system
    US20210285316A1|2021-09-16|Real-Time Well Construction Process Inference Through Probabilistic Data Fusion
    FR3086779A1|2020-04-03|MATCHING AN AUTOMATED PRODUCTION HISTORY USING BAYESIAN OPTIMIZATION
    FR3084906A1|2020-02-14|OPERATION OF A WELLBORE EQUIPMENT USING A DISTRIBUTED DECISION-MAKING FRAMEWORK
    FR3070179A1|2019-02-22|OPTIMIZATION OF PENETRATING SPEED FOR WELLBARS USING MACHINE LEARNING
    FR3070182A1|2019-02-22|REAL-TIME ITERATIVE GUIDANCE OF A DRILL BIT
    FR3034232A1|2016-09-30|
    FR3074834A1|2019-06-14|SIMULATED RECOVERY OPTIMIZATION FOR REAL-TIME DRILLING
    US20210302612A1|2021-09-30|Dynamic field operations system
    CN110268132A|2019-09-20|System, method and apparatus for the optimal tool-face control in the directed drilling of subsurface formations
    CA3135848A1|2020-10-08|Local/hybrid blockchain for oil and gas operations integrity
    同族专利:
    公开号 | 公开日
    US20210332696A1|2021-10-28|
    NO20201426A1|2020-12-22|
    GB2589472A|2021-06-02|
    GB202019536D0|2021-01-27|
    WO2020027861A1|2020-02-06|
    CA3099529A1|2020-02-06|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    CA2417074C|2003-01-24|2009-07-21|Pratt & Whitney Canada Corp.|Method and system for trend detection and analysis|
    WO2011043764A1|2009-10-05|2011-04-14|Halliburton Energy Services, Inc.|Integrated geomechanics determinations and wellbore pressure control|
    WO2016118979A2|2015-01-23|2016-07-28|C3, Inc.|Systems, methods, and devices for an enterprise internet-of-things application development platform|
    CN106156389A|2015-04-17|2016-11-23|普拉德研究及开发股份有限公司|For the well planning automatically performed|
    WO2018106277A1|2016-12-07|2018-06-14|Landmark Graphics Corporation|Intelligent, real-time response to changes in oilfield equilibrium|WO2021251982A1|2020-06-12|2021-12-16|Landmark Graphics Corporation|Controlling wellbore equipment using a hybrid deep generative physics neural network|
    RU2743685C1|2020-07-07|2021-02-24|Общество с ограниченной ответственностью "Тюменский нефтяной научный центр" |Method for intellectualization of gas and gas-condensate fields|
    法律状态:
    2021-04-09| ST| Notification of lapse|Effective date: 20210306 |
    优先权:
    申请号 | 申请日 | 专利标题
    US201862713789P| true| 2018-08-02|2018-08-02|
    US62/713,789|2018-08-02|
    IBPCT/US2018/064504|2018-12-07|
    PCT/US2018/064504|WO2020027861A1|2018-08-02|2018-12-07|Distributed control system using asynchronous services in a wellbore|
    [返回顶部]