A cloud-edge collaborative system and method for intelligent drilling

Abstract

The present invention discloses a cloud-edge collaborative system and method for intelligent drilling, which includes an intelligent drilling cloud decision system and multiple intelligent drilling edge decision systems communicating with the system. When the communication is normal, the edge decision system processes and analyzes the sensor data of the drilling rig and sends it to the cloud decision system, controlling the drilling rig to perform safe drilling according to the cloud decision instructions; when the communication is abnormal, it switches to the offline autonomous mode, generates edge decision instructions based on its own configured model and decision algorithm, and controls the drilling rig to achieve basic safe drilling; the intelligent drilling cloud decision system receives each processing and analysis result, obtains the global optimization result, performs enhanced analysis on the drilling situation to generate cloud decision instructions, and feeds the instructions back to the edge end of the drilling site. The present invention realizes real-time self-optimization decision and control of intelligent drilling when the communication is unobstructed. When the communication is abnormal, the edge end can ensure the stable operation of the automatic drilling rig to avoid risk accidents.

Description

Technical Field

[0001] The present invention belongs to the field of petroleum engineering, and specifically relates to a method and system for collaborative work between a rear cloud decision center and a front-end decision system at a drilling site in intelligent drilling. Background Art

[0002] Drilling engineering began its development in the early 20th century, progressing through a technological embryonic stage (1900-1920), an empirical drilling stage (1920-1950), a scientific drilling stage (1950-1990), and a fully automated drilling stage (1990-present). While the scientific drilling stage laid the theoretical foundation for drilling engineering and established mechanistic models (e.g., geology, rock mechanics, hydraulics, and string mechanics), drilling, as a hidden underground project, presents a vast array of heterogeneity, uncertainty, unstructured, and non-numerical challenges that constitute a "black box" of drilling engineering, severely impacting the accuracy of qualitative and quantitative descriptions of drilling engineering problems. While the advancement of petroleum equipment automation has improved drilling efficiency and resolved some implementation challenges, it has not yet addressed the accuracy issues inherent in qualitative and quantitative descriptions of drilling engineering.

[0003] With the development and application of information technology, big data, and artificial intelligence, intelligent drilling technology has become a core element of oil drilling. The full implementation of intelligent drilling technologies will not only enhance oil drilling efficiency and reduce manual errors, but also enable real-time drilling optimization, reduce operating costs, and control production accidents. Currently, major oil companies and universities at home and abroad have conducted research and applied intelligent drilling technology, and some of them have been put into practical use. For a long time to come, drilling projects will be in the intelligent drilling stage. Summary of the Invention

[0004] One of the technical problems to be solved by the present invention is the need to provide a cloud-edge collaborative system for intelligent drilling. The biggest difference between this cloud-edge collaborative system and previous drilling technologies is that it uses big data, artificial intelligence algorithms, cloud computing and other technologies to integrate, mine and apply massive real-time and historical data of drilling projects, and realize drilling self-optimization through intelligent decision-making.

[0005] In order to solve the above technical problems, an embodiment of the present application first provides a cloud-edge collaborative system for intelligent drilling, which includes an intelligent drilling cloud decision system and multiple intelligent drilling edge decision systems communicating with the system. The intelligent drilling edge decision system is configured on an edge server at the drilling site. When the communication with the cloud network is normal, it processes and analyzes the collected sensor data of the drilling rig, sends the processing and analysis results to the intelligent drilling cloud decision system, and receives cloud decision instructions fed back by the intelligent drilling cloud decision system, and controls the drilling rig to perform safe drilling according to the cloud decision instructions; when the communication with the cloud network is abnormal, it switches to an offline autonomous mode, generates edge decision instructions based on its own configured model and decision algorithm, and combines the drilling design parameters with the current drilling situation corresponding to the processing and analysis results, and controls the drilling rig to achieve basic safe drilling according to the edge decision instructions;

[0006] The intelligent drilling cloud decision system is configured on the cloud server, receives the processing and analysis results sent by each intelligent drilling edge decision system, combines the real-time data and historical data of other edges in the block, conducts global interdisciplinary analysis of the block to obtain global optimization results, and based on the global optimization results, conducts enhanced analysis of the drilling situation according to the real-time data of the drilling site edge, generates cloud-based decision instructions, and feeds back the instructions to the corresponding drilling site edge.

[0007] In one embodiment, the intelligent drilling cloud decision system trains, optimizes and upgrades the model and decision algorithm, and sends the optimized model and decision algorithm to the corresponding intelligent drilling side decision system; the intelligent drilling side decision system receives the updated model and decision algorithm, and updates the functions of the deployed model and decision algorithm.

[0008] In one embodiment, the intelligent drilling cloud decision system optimizes the parameters of the hydraulic calculation model and the friction torque model, optimizes the mechanical drilling speed prediction model based on the neural network, and optimizes the drilling parameter model based on machine learning.

[0009] In one embodiment, the intelligent drilling-side decision-making system uses the processed data to perform basic analysis on drilling condition identification, drilling risk identification, and drilling hydraulic / friction torque calculation.

[0010] In one embodiment, the intelligent drilling cloud decision system integrates real-time data from each edge, basic analysis results, and historical well data within the block to perform global interdisciplinary analysis of the block, including updating geological / reservoir models, calculating block rock mechanical properties, optimizing drilling designs combining geology and engineering, and calculating economic costs.

[0011] In one embodiment, the intelligent drilling cloud decision system is based on the global optimization results, and according to the real-time data of the edge of the drilling site, combined with the drilling conditions of the edge, it performs enhanced analysis on the well leakage risk identified at the edge, including well leakage grade classification, wellbore trajectory optimization, drill tool combination optimization, drilling parameter optimization, and treatment solution optimization.

[0012] According to another aspect of the present invention, a cloud-edge collaboration method for the system as described above is also provided, the method comprising: the intelligent drilling edge decision system determines whether its communication with the cloud network is normal, and if normal, performs the following steps: the intelligent drilling edge decision system processes and analyzes the collected sensor data of the drilling rig, and sends the processing and analysis results to the intelligent drilling cloud decision system; the intelligent drilling cloud decision system receives the processing and analysis results of each intelligent drilling edge decision system, combines the real-time data and historical data of other edges in the block, performs a global interdisciplinary analysis of the block to obtain a global optimization result, and based on the global optimization result, performs an enhanced analysis of the drilling situation according to the real-time data of the drilling site edge to generate a cloud decision instruction, and feeds the instruction back to the corresponding drilling site edge;

[0013] The intelligent drilling side decision system receives feedback from the cloud-based decision instructions and controls the drilling rig to perform safe drilling in accordance with the cloud-based decision instructions. If there is a communication abnormality, the intelligent drilling side decision system switches to an offline autonomous mode and generates side decision instructions based on its own configured model and decision algorithm, combined with the drilling design parameters and the current drilling situation corresponding to the basic analysis results, to control the drilling rig to achieve basic safe drilling in accordance with the side decision instructions.

[0014] In one embodiment, the method further includes: the intelligent drilling-side decision system trains, optimizes and upgrades the model and decision algorithm, and sends the optimized model and decision algorithm to the corresponding intelligent drilling-side decision system; the intelligent drilling-side decision system receives the updated model and decision algorithm, and updates the functions of the deployed model and decision algorithm.

[0015] In one embodiment, the intelligent drilling cloud decision system optimizes the parameters of the hydraulic calculation model and the friction torque model, optimizes the mechanical drilling speed prediction model based on the neural network, and optimizes the drilling parameter model based on machine learning.

[0016] In one embodiment, the intelligent drilling-side decision-making system performs basic analysis on the processed data to identify drilling conditions, identify drilling risks, and calculate drilling hydraulic / friction torque.

[0017] In one embodiment, the intelligent drilling cloud decision system integrates real-time data from each edge, basic analysis results, and historical well data within the block to perform global interdisciplinary analysis of the block, including updating geological / reservoir models, calculating block rock mechanical properties, optimizing drilling designs combining geology and engineering, and calculating economic costs.

[0018] In one embodiment, the intelligent drilling cloud decision system is based on the global optimization result, and according to the real-time data of the edge of the drilling site and the drilling situation of the edge, it performs enhanced analysis on the well leakage risk identified at the edge, including well leakage grade classification, wellbore trajectory optimization, drill tool combination optimization, drilling parameter optimization, and treatment solution optimization.

[0019] Compared with the prior art, one or more embodiments of the above solutions may have the following advantages or beneficial effects:

[0020] (1) Compared with current intelligent drilling related technical solutions, the cloud-edge collaborative operation method designed and applied in the embodiment of the present invention realizes real-time self-optimization decision-making and control of intelligent drilling when communication is smooth. When communication anomalies occur, the edge can form a closed-loop decision-making and control system that meets the minimum standards for safe drilling, ensuring the stable operation of the automatic drilling rig, executing basic safe drilling instructions, and avoiding risk accidents.

[0021] (2) The cloud-based decision-making system of the embodiment of the present invention can utilize its ultra-high computing power, intelligent algorithms, big data processing and other service modules to combine the real-time data sent back by a single edge with the real-time data of other edges in the block, and integrate it with historical well data, comprehensively carry out real-time dynamic optimization of multiple disciplines such as geology, reservoir, development, and investment cost throughout the entire cycle, realize big data sharing and mining analysis, provide enhanced analysis results for the edge and form relevant decision-making control instructions;

[0022] (3) The cloud-based decision-making system of the embodiment of the present invention can also utilize its ultra-high computing power, intelligent algorithms, big data processing and other service modules to train, iterate, update, improve, upgrade and optimize various model modules such as data analysis models, physical mathematical models, and intelligent decision-making models in real time based on drilling data. The improved and optimized model modules can be sent to the edge for update deployment and upgraded application according to the needs of the edge.

[0023] (4) The edge decision-making system of the embodiment of the present invention, when communicating with the cloud, can perform edge computing functions, responsible for the collection, integration, caching and processing of various types of measurement data at the intelligent drilling site, both underground and on the ground, and after performing basic analysis on the data, send the results together with the processed data back to the cloud, which can effectively share the pressure of data processing and analysis on the cloud and save network bandwidth and traffic;

[0024] (5) In the edge decision-making system of the embodiment of the present invention, when there is an abnormality in communication with the cloud, the edge decision-making server also runs offline. Under the original edge computing function, the edge decision-making function can be executed, and the analysis and decision-making model deployed from the cloud can be used to further independently execute the analysis and decision-making functions, thereby realizing closed-loop autonomy that meets the basic needs of the intelligent drilling site, ensuring safe drilling according to the drilling design, and avoiding unexpected risks and accidents.

[0025] Other features and advantages of the present invention will be described in the following description and, in part, will become apparent from the description or be understood through implementation of the technical solutions of the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures and / or processes particularly pointed out in the description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings are used to provide a further understanding of the technical solution of this application or the prior art and constitute a part of the specification. Among them, the drawings that express the embodiments of this application are used together with the embodiments of this application to explain the technical solution of this application, but do not constitute a limitation of the technical solution of this application.

[0027] Figure 1 This is a schematic diagram of the overall structure of a cloud-edge collaborative system for intelligent drilling in an embodiment of the present application.

[0028] Figure 2 This is a functional block diagram of the cloud server and edge server in an embodiment of the present application.

[0029] Figure 3 This is a flow chart of a cloud-edge collaboration method for intelligent drilling according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will describe the implementation methods of the present invention in detail with reference to the accompanying drawings and examples, so that the implementation process of how the present invention applies technical means to solve technical problems and achieve corresponding technical effects can be fully understood and implemented accordingly. The embodiments of this application and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present invention.

[0031] In addition, the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in a different order than here.

[0032] Currently, existing technical solutions involving intelligent drilling mostly focus on the automated integration and deployment of drilling equipment and the application of intelligent methods, but lack methods for building and applying the core intelligent decision-making system in intelligent drilling.

[0033] For example, prior art solution 1 provides an intelligent drilling expert system comprising: a field sensor detection system, an intelligent expert system, and an actuator. The output of the field sensor detection system is connected to the input of the intelligent expert system, which in turn is connected to the input of the actuator, thereby forming an automatic closed-loop drilling control system. Prior art solution 2 also discloses an intelligent drilling expert system comprising: a field sensor detection system, a communication system, an intelligent expert system, and an operating system. The field sensor detection system is connected to the intelligent expert system via the communication system, which in turn is connected to the operating system, thereby forming an automatic closed-loop drilling control system. The field sensor detection system collects data from the entire drilling process and transmits the collected data to the intelligent expert system via the communication system for processing, monitoring, forecasting, analysis, control, and processing. Finally, the operating system executes the operational instructions issued by the intelligent expert system after analysis. This technical solution enables real-time, early detection, early forecasting, on-demand interpretation, and automatic control functions. It not only provides accurate information for drilling projects, but also offers the advantages of reducing drilling costs, increasing drilling speed, eliminating accidents, and enabling precise oil and gas discovery. However, the above two solutions are still based on traditional mechanism calculation models and partial expert models to analyze the drilling process. Big data and artificial intelligence algorithms are not applied for enhanced analysis and decision-making. There is no mention of the deployment location of the system, nor is there any related content such as cloud-edge collaborative processing.

[0034] Existing technical solution three provides an intelligent drilling system and method, comprising a surface system, a downhole system, and an intelligent drilling control platform. The surface system includes a coiled tubing train, a coiled tubing control platform, a coiled tubing drum, a casing mast, an injector head, a rotary control head, and associated blowout prevention equipment. The coiled tubing control platform and coiled tubing drum are mounted on the coiled tubing train, while the casing mast is located above the wellhead. The injector head, rotary control head, and associated blowout prevention equipment are connected sequentially from top to bottom and then positioned at the wellhead. The downhole system includes coiled tubing with a cable, a wet joint, and an intelligent downhole string. One end of the cabled coiled tubing is wound around the coiled tubing drum, and the other end passes through the injector head, rotary control head, and associated blowout prevention equipment, then enters the wellhead and connects to the intelligent downhole string via a wet joint. This technical solution focuses on the coiled tubing hardware system used for intelligent drilling and does not address cloud-edge collaborative processing or the application of big data or artificial intelligence algorithms for enhanced analytical decision-making.

[0035] Intelligent drilling is an inevitable trend in the development of drilling engineering, and its technical core lies in the construction and application of intelligent drilling decision-making. At present, the industry's envisioned trend for intelligent drilling systems is that the rear intelligent decision-making center remotely controls the on-site automated drilling rig to achieve intelligent optimization of drilling operations. However, drilling engineering is a hidden underground project. A large number of heterogeneous, uncertain, non-structural and non-numerical problems constitute the "black box" of drilling engineering, and there are extremely high risks in the drilling process. During the intelligent drilling process, if there is a lack of timely or interrupted communication between the front and rear, the automated drilling rig in the front will lack decision-making and operation instructions, which may lead to risks in the drilling project and ultimately catastrophic consequences (such as blowout of crude oil, hydrogen sulfide causing environmental poisoning, equipment damage, etc.).

[0036] To address the above technical issues, the embodiments of the present invention propose a cloud-edge collaborative system and method for intelligent drilling. The basic principle is to establish a cloud server in the back-end and an edge server at the drilling site. When network communication is normal, the edge server at the drilling site performs edge computing functions to preprocess data and conduct basic analysis, and sends the processed data and results to the cloud server in the back-end. The cloud server in the back-end performs cloud computing, using its computing power and AI algorithms to perform data enhancement analysis, and trains and improves relevant algorithm models. The enhanced analysis results (i.e., automatic drilling rig operation instructions) and the upgraded algorithm model are sent to the edge server at the drilling site for execution and deployment. When network communication is abnormal, the edge server at the drilling site uses the deployed algorithm model to achieve offline autonomy. On the premise of meeting the basic requirements of the intelligent drilling site, it generates operation instructions to ensure that the automatic drilling rig performs safe drilling according to the predetermined design, avoiding unexpected risks and accidents.

[0037] Figure 1 This is a structural diagram of a cloud-edge collaborative system for intelligent drilling in an embodiment of the present application. Figure 2 This is a functional block diagram of the cloud server and edge server in the embodiment of this application. Figure 1 and Figure 2 To illustrate the various components and functions of this system.

[0038] like Figure 1 As shown, the cloud-edge collaborative system for intelligent drilling includes a cloud server 20 and multiple edge servers 1, 2, ..., X set up at drilling sites (well sites 1, 2, ..., X). An intelligent drilling edge decision system (hereinafter referred to as the "edge decision system") is configured in the edge servers 1, 2, ..., X, and an intelligent drilling cloud decision system (hereinafter referred to as the "cloud decision system") is deployed at the cloud server 20. Each edge decision system is connected to the cloud decision system through a well site communication network (not shown). The well site communication network supports the communication and interaction of data, data processing results, instructions, models, etc. between the edge decision system and the cloud decision system.

[0039] In summary, each edge decision-making system preprocesses and performs basic analysis on the collected sensor data from the drilling rig, then transmits the preprocessing and basic analysis results to the cloud decision-making system. The cloud decision-making system then responds with cloud-based decision instructions and / or updated models and decision algorithms based on these data processing results. The cloud decision-making system then controls the drilling rig to safely drill according to the cloud-based decision instructions. The cloud decision-making system receives the preprocessing and basic analysis results from each edge decision-making system and, combined with real-time and historical data from other edges within the block, performs a global, cross-disciplinary analysis of the block to obtain a global optimization result. Based on this global optimization result, it uses real-time data from the drilling site edge to perform enhanced analysis of the drilling situation and generate edge-based decision instructions for the well. These instructions are then fed back to the corresponding drilling site edge. Edge-based decision instructions must meet minimum safe drilling standards, ensuring stable operation of the automated drilling rig and avoiding potential accidents. In addition to meeting minimum safe drilling standards, cloud-based decision instructions must also integrate real-time, dynamic optimization across multiple disciplines, including geology, reservoir management, development, and investment costs, to achieve optimized, safe drilling.

[0040] Reference below Figure 2 To illustrate the functional modules within the edge decision system and the cloud decision system.

[0041] Since the components of each edge decision system are basically the same, only one of them will be described below. Figure 2 As shown, the edge decision-making system includes functional modules such as a data storage module 11, a data preprocessing module 12, a basic drilling computing module 13, a cloud-edge communication and detection module 14, an intelligent drilling basic decision-making service 15, and a command control module 16. The cloud decision-making system not only includes all the functions of the edge decision-making system (not fully illustrated), but also includes a cloud computing service module 21, a big data mining service module 22, an intelligent algorithm service module 23, an intelligent drilling enhanced decision-making service module 24, and a model algorithm optimization module 25. It should be noted that the cloud service side has all the functions of the edge decision-making system, which is equivalent to building an edge-side test environment on the cloud server side, which serves as a verification test. That is, any adjustments, updates, or upgrades to the edge decision-making system by the cloud decision system must first pass verification testing in the corresponding cloud module before being deployed and applied. This ensures that the edge system in the production environment can still operate normally after adjustments, preventing system problems from causing production accidents.

[0042] The functions of each service module of the edge decision-making system are first explained below.

[0043] The cloud-edge communication and detection module 14 detects in real time whether the cloud network communication between edge servers 1, 2, ..., X and cloud server 20 is normal. If communication is normal, it sends the preprocessed data and basic analysis results back to cloud server 20 via the communication interface. In addition, this module 14 also receives cloud decision instructions (which may be called "drilling control instructions") and / or updated models and decision algorithms from cloud server 20.

[0044] The data storage module 11 receives data transmitted by the sensor group and data transmitted through the cloud-edge communication and detection module 14. These data include various ground and downhole sensor measurement data collected from the automated drilling rig, including but not limited to real-time drilling rig equipment status data, fluid property data, logging data, wellbore temperature and pressure data, etc., as well as command data and updated models, decision algorithms, etc. transmitted from the cloud server.

[0045] The data preprocessing module 12 is connected to the data storage module 11 and preprocesses various surface and downhole sensor measurement data related to the automated drilling rig, including but not limited to data cleaning, integration, feature transformation, and reduction.

[0046] The drilling professional basic calculation module 13 is connected to the data preprocessing module 12 and performs basic analysis on the preprocessed data. This basic analysis includes but is not limited to drilling condition identification, drilling risk identification, and drilling hydraulic / frictional torque calculations. The calculation models for drilling hydraulic / frictional torque and other mechanisms utilize existing calculation methods. For analysis of drilling condition identification and drilling risk identification, where traditional methods have low accuracy, trained artificial intelligence algorithms are used, including but not limited to various neural network algorithms, random forest algorithms, and clustering algorithms.

[0047] It should be noted that when the communication connection between the edge decision system and the cloud decision system is normal, the edge decision system performs the edge computing function, that is, the data processing module 12 and the drilling professional basic computing module 13 are in working state, and the local intelligent drilling basic decision service module 15 is disabled.

[0048] When the communication connection is abnormal, the intelligent drilling edge decision-making system implements offline autonomous closed-loop decision-making, and simultaneously executes edge computing functions and the edge-end intelligent drilling basic decision-making service module 15. These functions and services can be initially installed or updated and deployed when its communication with the cloud is not interrupted.

[0049] The intelligent drilling basic decision-making service module 15, which connects to the drilling professional basic calculation module 13 and the data preprocessing module 12, obtains processed data and basic analysis results. Based on the drilling design and the current well data, it makes basic drilling decisions to ensure the safety of the current well. For example, it predicts the wellbore trajectory and generates directional control parameters to ensure the wellbore orientation of the drilling design. Based on the results, it generates drilling rig control instructions and sends them to the automatic drilling rig instruction control module 16. Compared with cloud-based decision-making services, these decision results are not global optimal values ​​(for example, they take into account drilling costs and post-drilling productivity), but they can ensure safe drilling.

[0050] It should be noted that the "basic drilling" mentioned above is to control the drilling rig to automatically connect to the corresponding drilling string to perform drilling operations according to the wellbore structure, wellbore trajectory, and drilling parameters in the drilling design plan, and to passively respond after abnormal risks occur. In this process, the intelligent drilling basic decision service module 15 does not actively optimize and adjust the parameters of the plan, but only adopts certain control strategies after the basic analysis results identify the risk. For example, after the drill is stuck, the module 15 will control the drilling rig to continuously back-mark the hole within the upper limit of the hook load, and try to complete the processing of the stuck drill risk. Once the risk cannot be eliminated, the drill string rotation cycle will be executed to avoid the risk from increasing while waiting for the optimization instructions after the cloud is reconnected or the manual instructions of the on-site monitoring engineer.

[0051] Basic drilling decisions (rig control instructions) primarily involve automatically taking over the pipe string and using directional tools to drill a wellbore structure and wellbore trajectory that conforms to the drilling design according to the designed drilling parameters (displacement / bit weight, rotation speed). These decisions include, at a minimum, drill string selection, automatic taking over the pipe string, mud pump displacement control, bit weight control, rotation speed control, casing running and cementing. The enhanced analysis described below, based on the current drilling situation, proactively adjusts the drilling design, drilling parameters, and used pipe string tools to optimize drilling quality and speed. It also proactively avoids potential drilling risks and recommends the optimal solution for unexpected risks, ultimately achieving efficient and safe drilling.

[0052] The command control module 16 is connected to the intelligent drilling basic decision service module 15, receives drilling control instructions from the module 15 to control the automatic drilling rig D to perform basic safe drilling, or receives drilling control instructions from the cloud server 20 to perform more optimized safe drilling.

[0053] Furthermore, when the edge server receives updated model algorithms / functional modules from the cloud server, it compares the received model algorithms / functional modules, updates the deployed model algorithms / module functions, and deploys and applies the newly added model algorithms / module functions. These models include the hydraulic calculation model, friction torque model, mechanical penetration rate prediction model, drilling parameter model, and drilling risk response model in the drilling professional basic calculation module 13 and the intelligent drilling basic decision service module 15.

[0054] Next, the components and functions of the cloud decision system of the cloud server are explained below.

[0055] like Figure 2 As shown, the cloud decision system includes a data storage module 11 and a cloud-edge communication and detection module 14, which are similar to the edge decision system. The data storage module 11 receives and stores the preprocessing results and basic analysis results (referred to as "processing and analysis results") sent back in real time by each edge from the cloud-edge communication and detection module 14.

[0056] The intelligent drilling enhanced decision-making service module 24 integrates real-time data from various edge nodes, basic analysis results, and historical well data within the block. It utilizes the big data technology of the big data mining service module 22 and the cloud computing power of the cloud computing service module 21 to conduct global, interdisciplinary analysis of the block. This analysis includes, but is not limited to, updating geological / reservoir models, calculating rock mechanical properties within the block, optimizing drilling designs based on the integration of geology and engineering, and calculating economic costs. For example, the big data mining service analysis module 22 can extract rock cuttings logging data from numerous historical wells within the block and, based on their lithologic descriptions, update and improve the geological model of the current block. This in turn corrects the predicted formations for the current well, making subsequent drilling risk and drilling timeline calculations more accurate. The cloud computing service module 21 provides computing power support for some iterative computational models with high computational complexity. It also utilizes a data engine to enable data exchange and timeline synchronization between the parallel computations of various algorithmic models, enabling the cloud decision-making system to rapidly generate analysis results and make decisions.

[0057] The intelligent drilling enhanced decision service module 24 further enhances the basic analysis results of the edge based on the global interdisciplinary analysis results of the block, combined with the real-time data of the target edge, using the cloud-based big data service of the big data mining service module 22, the AI ​​algorithm service of the intelligent algorithm service module 23, and the cloud computing of the cloud computing service module 21, and sends the instructions formed based on the enhanced analysis results to the corresponding edge server. Specifically, the cloud-edge decision instructions can not only ensure safe drilling, but also be the global optimal value (for example, taking into account drilling costs, post-drilling production capacity, etc.). The content of the enhanced analysis includes but is not limited to improving the accuracy of the calculation results (for example, a more specific classification of the well leakage risk identified by the edge), performing drilling-related optimization calculations (further subdivided into wellbore trajectory optimization, drill tool combination optimization, drilling parameter optimization, treatment solution optimization, etc., specifically, for example, calculating the best response and treatment solution for the identified well leakage risk), etc.

[0058] The model algorithm optimization module 25 leverages massive data and the cloud computing power of the cloud computing service module 21 to train, iterate, improve, upgrade, and optimize various models and algorithms, including data analysis models, physical and mathematical models, and intelligent decision-making models. It then distributes the upgraded and optimized model algorithms / functional modules to the corresponding edge servers. Specifically, it optimizes parameters for specialized drilling physical and mathematical models, such as hydraulic calculation models and friction and torque models, and trains, iterates, and optimizes intelligent decision-making models, such as neural network-based ROP prediction models and machine learning-based drilling parameter optimization models.

[0059] The following combination Figure 3 Let’s illustrate the cloud-edge collaboration approach for smart drilling.

[0060] Before implementing the cloud-edge collaboration approach for intelligent drilling, first establish a cloud server in the backend and an edge server at the drilling site. Deploy the intelligent drilling edge decision-making system on the edge server and the intelligent drilling cloud decision-making system on the cloud server. After deployment, the cloud-edge collaboration approach begins.

[0061] Figure 3 The following is a flow chart of a cloud-edge collaboration method for intelligent drilling. Steps S30 to S36 are performed by the intelligent drilling edge server (or edge decision system), and steps S37 to S39 are performed by the intelligent drilling cloud server (or cloud decision system).

[0062] In step S30, the edge server determines whether it has received the optimized model algorithm sent by the cloud server. If so, it updates the deployed model algorithm / module function by comparing it with the received model algorithm / functional module, and deploys and applies the newly added model algorithm / module function. Otherwise, it executes step S31.

[0063] In step S31, the edge server collects and stores various ground and downhole sensor measurement data collected by the automated drilling rig, such as real-time drilling rig equipment status data, fluid property data, logging data, wellbore temperature and pressure data, and other sensor measurement data related to the drilling rig, and uses its deployed data preprocessing algorithms, professional basic algorithms and other models and services to preprocess and perform basic analysis on the data, including but not limited to data cleaning, integration, feature transformation, specification, drilling condition identification, drilling risk identification, drilling friction and torque calculation, etc.

[0064] In step S32, the edge server detects whether the current cloud network communication is normal. If normal, it switches to the networking mode, aggregates the processed data, basic analysis results, and uses the cloud-edge communication service deployed by it, and sends it back to the cloud server via the communication interface.

[0065] Then, in step S38, the cloud server receives and stores the processed data and basic analysis results sent back in real time by each edge end. Further, it integrates the real-time data of each edge end and the historical well data in the block, and uses big data technology and cloud computing power to perform global interdisciplinary analysis of the block. The global interdisciplinary analysis of the block includes but is not limited to geological / reservoir model updates, block rock mechanical property calculations, geological and engineering combined drilling design optimization, economic cost calculations, etc.

[0066] Then, in step S39, based on the global interdisciplinary analysis results of the block and combined with the real-time data of the target edge, the cloud server uses cloud big data services, AI algorithm services, cloud computing, etc. to perform enhanced analysis on the basic analysis results of the edge. The content of the enhanced analysis includes but is not limited to improving the accuracy of the calculation results (for example, a more specific classification of the well leakage risk identified by the edge), performing drilling-related optimization calculations (further subdivided into well trajectory optimization, drill tool combination optimization, drilling parameter optimization, treatment solution optimization, etc., specifically, for example, calculating the best response and treatment solution for the identified well leakage risk), etc. The cloud server then sends the cloud decision instructions formed based on the enhanced analysis results to the edge server. The cloud-edge decision instructions not only ensure safe drilling, but are also the global optimal value (for example, taking into account drilling costs and post-drilling production capacity).

[0067] In step S35, the edge server receives the cloud decision instruction sent back by the cloud server, and controls the automatic drilling rig to perform drilling according to the operation instruction.

[0068] In step S36, the edge server determines whether the drilling rig has completed the drilling operation. If so, the operation ends; otherwise, the process returns to step S30.

[0069] Now returning to step S32, if the cloud network communication is abnormal in step S32, the edge server switches to offline autonomous mode. The edge server's intelligent drilling decision-making system implements offline autonomous closed-loop decision-making, simultaneously executing edge computing functions and basic intelligent drilling decision-making services at the edge. These functions and services can be initially installed or updated and deployed while communication with the cloud is still ongoing.

[0070] In step S33, the edge server sends the preprocessed data and basic analysis results to the basic decision service module of the intelligent drilling edge decision system. The edge basic decision service module executes basic drilling decisions to ensure the safety of the well based on the drilling design plan and the well data, such as predicting the wellbore trajectory direction to form directional control parameters to ensure the realization of the wellbore orientation of the drilling design.

[0071] Next, in step S34, the edge server generates edge decision instructions based on the basic drilling decision results. Furthermore, compared to cloud-based decision services, these decision results are not globally optimal (for example, they take into account drilling costs and post-drilling productivity), but they can ensure safe drilling.

[0072] In step S35, the edge basic decision service module of the edge server sends the generated drilling control instruction to the instruction control module to control the automatic drilling rig to perform basic safe drilling.

[0073] In addition to executing the above steps, the cloud server also needs to update the model algorithm on the edge.

[0074] In step S37, a determination is made as to whether the edge server's model algorithms need to be updated. If so, the cloud server leverages massive data and cloud computing power to train, iterate, improve, upgrade, and optimize various models and algorithms within the intelligent drilling decision-making system, including data analysis models, physical and mathematical models, and intelligent decision-making models. Specifically, these models and algorithms include, but are not limited to, parameter optimization of specialized drilling physical and mathematical models, such as hydraulic calculation models and friction and torque models, and training, iteration, and optimization of intelligent decision-making models, such as neural network-based ROP prediction models and machine learning-based drilling parameter optimization models.

[0075] Then, when the cloud network communication is normal, the updated model algorithm is sent to the edge server, and the edge server is updated.

[0076] It should be noted that although the method of this embodiment is in accordance with the above Figure 3The steps in the process shown are executed, but it is easy to understand that in other embodiments, the order is not limited to the above, and the steps can be changed through reasonable changes. For example, the updated model algorithm and cloud decision instructions can be sent back to the edge server at the same time, the network communication status can be detected first, and then the mode to be adopted can be determined, etc. This application does not limit this.

[0077] In order to better illustrate the present invention, a specific example is given below.

[0078] Example

[0079] In this example, the intelligent drilling cloud-edge collaboration method and system according to an embodiment of the present invention were tested and applied in Well X in a certain area of ​​Shengli Oilfield. The specific implementation process is as follows:

[0080] (1) Establish an edge server at the X-well drilling site and deploy an intelligent drilling edge decision-making system. Establish a cloud server at the rear command center and deploy an intelligent drilling cloud decision-making system. Establish a network link for communication between the two.

[0081] (2) When the intelligent drilling decision-making system communicates normally with the cloud decision-making system, the cloud-edge collaborative mode is successfully applied. After completing data preprocessing and basic analysis, the intelligent drilling decision-making system uploads the processed and analyzed data to the cloud decision-making system. The cloud decision-making system performs enhanced analysis based on the historical data of the block, and then sends the optimized drilling instructions to the X-well decision-making system to control the automatic drilling rig to perform drilling according to the optimized drilling parameters (such as displacement, speed, drilling pressure, etc.). On the other hand, the cloud decision-making system can also train and improve the drilling risk identification model based on a large amount of data, and successfully feed it back to the edge decision-making system for update, upgrade and application.

[0082] (3) After manually interrupting the communication between the intelligent drilling edge decision-making system and the cloud decision-making system, the edge decision-making system successfully switched to offline autonomous mode, realizing the closed-loop process of local data processing, analysis, decision-making instruction generation, and control of drilling rig drilling. The drilling operation of Well X was not affected by the network interruption, and drilling was carried out normally according to the drilling design without any drilling risks.

[0083] The final test results prove that the intelligent drilling cloud-edge collaboration method and system proposed in the embodiment of the present invention is feasible. It can not only realize intelligent self-optimization of drilling under network communication, but also realize basic safe drilling operations after the drilling site edge is abnormally offline, ensuring drilling progress and avoiding the occurrence of drilling accident risks. The above technical solution is applied to the field of petroleum engineering, enabling intelligent drilling operations to realize intelligent self-optimization of drilling under network communication by utilizing the enhanced analysis capabilities of the cloud. It can also continue to perform basic safe drilling operations after the drilling site edge is offline due to network anomalies, ensuring drilling progress and avoiding the occurrence of drilling accident risks.

[0084] In summary, the embodiments of the present invention propose a cloud-edge collaboration method and system for intelligent drilling. By collaborating the rear cloud decision server with the drilling site edge server, when the network communication is normal, the edge server completes the preliminary analysis and processing of the data, and then transmits it to the rear cloud decision server for enhanced analysis. After forming the optimized decision operation instructions, it is sent to the drilling site edge server and sent to the automated drilling rig equipment to perform the drilling operation. Once an abnormality in network communication is detected, the edge server uses the deployed analysis and decision model to independently complete the data analysis and processing and generate decision instructions, and control the automated drilling rig equipment to perform basic normal drilling operations according to the drilling design. In this way, intelligent self-optimization of drilling under network communication can be achieved, and basic normal drilling operations can be achieved after the on-site terminal is abnormally offline, avoiding the occurrence of drilling accident risks.

[0085] It should be understood that the embodiments disclosed herein are not limited to the specific structures and processing steps disclosed herein, but should be extended to equivalent substitutions of these features understood by those skilled in the relevant art. It should also be understood that the terminology used herein is only for the purpose of describing specific embodiments and is not intended to be limiting.

[0086] References in this specification to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Therefore, appearances of the phrases "one embodiment" or "an embodiment" in various places throughout this specification do not necessarily refer to the same embodiment.

[0087] Although the embodiments disclosed herein are as described above, the contents described herein are merely embodiments for facilitating understanding of the present invention and are not intended to limit the present invention. Any person skilled in the art of the present invention may make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed herein. However, the scope of patent protection of the present invention shall still be subject to the scope defined by the appended claims.

Claims

1. A cloud-edge collaborative system for intelligent drilling, characterized in that: The system includes an intelligent drilling cloud decision system and multiple intelligent drilling side decision systems communicating with it, among which, The intelligent drilling edge decision-making system is configured on the edge server at the drilling site. When communication with the cloud network is normal, it pre-processes and performs basic analysis on the sensor data collected from the drilling rig, sends the processing and analysis results to the intelligent drilling cloud decision-making system, and receives cloud decision instructions fed back by the intelligent drilling cloud decision-making system, controlling the drilling rig to drill safely according to the cloud decision instructions. When communication with the cloud network is abnormal, it switches to offline autonomous mode and generates edge decision instructions based on its own configured model and decision algorithm, combined with the drilling design parameters and the current drilling situation corresponding to the processing and analysis results, and controls the drilling rig to achieve basic safe drilling according to the edge decision instructions. The intelligent drilling cloud decision system is configured on the cloud server, receives the processing and analysis results sent by each intelligent drilling edge decision system, combines the real-time data and historical data of other edges in the block, conducts global cross-disciplinary analysis of the block to obtain global optimization results, and based on the global optimization results, conducts enhanced analysis of the drilling situation according to the real-time data of the drilling site edge, generates cloud decision instructions, and feeds back the instructions to the corresponding drilling site edge. The intelligent drilling decision-making system also uses the pre-processed data to perform basic analysis on drilling condition identification, drilling risk identification, and drilling hydraulic / friction torque calculation; The intelligent drilling cloud decision-making system also integrates real-time data from each edge, basic analysis results, and historical well data within the block to perform global interdisciplinary analysis of the block, including updating geological / reservoir models, calculating block rock mechanical properties, optimizing drilling designs combining geology and engineering, and calculating economic costs.

2. The cloud-edge collaborative system for intelligent drilling according to claim 1, characterized in that: The intelligent drilling cloud decision system trains, optimizes and upgrades the model and decision algorithm, and sends the optimized model and decision algorithm to the corresponding intelligent drilling side decision system; The intelligent drilling side decision system receives the updated model and decision algorithm and updates the functions of the deployed model and decision algorithm.

3. The cloud-edge collaborative system for intelligent drilling according to claim 2, characterized in that: The intelligent drilling cloud decision-making system optimizes the parameters of the hydraulic calculation model and the friction torque model, optimizes the mechanical drilling speed prediction model based on the neural network, and optimizes the drilling parameter model based on machine learning.

4. The cloud-edge collaborative system for intelligent drilling according to claim 1, characterized in that: The intelligent drilling cloud decision-making system is based on global optimization results, and according to real-time data from the edge of the drilling site and the drilling situation at the edge, it performs enhanced analysis on the well leakage risk identified at the edge, including well leakage grade classification, wellbore trajectory optimization, drill tool combination optimization, drilling parameter optimization, and treatment solution optimization.

5. A cloud-edge collaboration method according to any one of claims 1 to 4, the method comprising: The intelligent drilling decision-making system determines whether its communication with the cloud network is normal. If normal, it performs the following steps: The intelligent drilling side decision system pre-processes and performs basic analysis on the collected sensor data of the drilling rig, and sends the processing and analysis results to the intelligent drilling cloud decision system; The intelligent drilling cloud decision system receives the processing and analysis results of each intelligent drilling edge decision system, combines the real-time data and historical data of other edges in the block, conducts a global cross-disciplinary analysis of the block to obtain a global optimization result, and based on this global optimization result, conducts an enhanced analysis of the drilling situation according to the real-time data of the drilling site edge, generates cloud-based decision instructions, and feeds these instructions back to the corresponding drilling site edge. The intelligent drilling side decision system receives the feedback cloud decision instructions and controls the drilling rig to perform safe drilling according to the cloud decision instructions; If the communication is abnormal, the intelligent drilling side decision system switches to offline autonomous mode, generates side decision instructions based on its own configured model and decision algorithm, combined with the drilling design parameters and the current drilling situation corresponding to the basic analysis results, and controls the drilling rig to achieve basic safe drilling according to the side decision instructions. The intelligent drilling decision-making system performs basic analysis on the processed data to identify drilling conditions, identify drilling risks, and calculate drilling hydraulic / friction torque; The intelligent drilling cloud decision-making system integrates real-time data from each edge, basic analysis results, and historical well data within the block to perform global interdisciplinary analysis of the block, including updating geological / reservoir models, calculating block rock mechanical properties, optimizing drilling designs combining geology and engineering, and calculating economic costs.

6. The cloud-edge collaboration method according to claim 5, characterized in that: The method further includes: The intelligent drilling side decision system trains, optimizes and upgrades the model and decision algorithm, and sends the optimized model and decision algorithm to the corresponding intelligent drilling side decision system; The intelligent drilling side decision system receives the updated model and decision algorithm and updates the functions of the deployed model and decision algorithm.

7. The cloud-edge collaboration method according to claim 6, characterized in that: The intelligent drilling cloud decision system optimizes the parameters of the hydraulic calculation model and the friction torque model, optimizes the mechanical drilling speed prediction model based on the neural network, and optimizes the drilling parameter model based on machine learning.

8. The cloud-edge collaboration method according to claim 5, characterized in that: Based on the global optimization results, the intelligent drilling cloud decision system performs enhanced analysis on the lost circulation risks identified at the edge, including lost circulation grade classification, wellbore trajectory optimization, drill tool combination optimization, drilling parameter optimization, and treatment solution optimization, according to the real-time data of the drilling site edge and the drilling situation at the edge.

Images