Intelligent identification system and method for operation state of offshore shut-in equipment, medium and equipment

Abstract

The invention relates to the field of offshore oil and gas intelligent well shut-in, and discloses an intelligent recognition system and method for the operation state of offshore well shut-in equipment, a medium and the device.The method comprises the steps that real-time logging data of a well drilling site and a drilling tool detail table of the opening time are obtained, and data characteristics of the well shut-in equipment in the on-off state are analyzed; meanwhile, image data of the throttling control box and the blowout preventer remote console are obtained in real time; comprehensively judging the extracted data characteristics according to a preset logic judgment condition so as to obtain the on-off states of a slurry pump and a top drive and whether a drill rod joint is in a blowout preventer or not in real time, and obtaining the real-time state of well shut-in equipment; a machine vision model is trained through the image data, an intelligent recognition module is obtained to recognize the on-off state of the throttle valve and the blowout preventer in real time, and the on-off state and the real-time state of the well shut-in equipment are summarized and then transmitted to a driller station. Worsening of overflow accidents can be effectively avoided, and the well control risk is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of offshore oil and gas intelligent well shut-in, and in particular to an intelligent identification system, method, medium and equipment for the operating status of offshore well shut-in equipment. Background Art

[0002] As the trend of oil and gas resources becoming inferior becomes increasingly obvious, deepwater and ultra-deepwater oil and gas have become important areas for oil and gas development. The characteristics of this type of oil and gas reservoirs are complex geological conditions and narrow safety density windows, which lead to frequent complex situations such as downhole overflows and well kicks. The premise for dealing with overflows is to shut in the well. According to the well control equipment, the operating status when the overflow occurs, etc., the well shut-in methods are divided into "soft well shut-in" and "hard well shut-in". No matter what well shut-in method is adopted, it is inseparable from the coordinated control of engineers in different positions. At present, well shut-in generally adopts traditional manual operation and gesture signals to carry out well shut-in operations. This process requires real-time coordination of multiple engineers. Operational errors are prone to occur in emergency situations, which affects the timeliness of well shut-in and increases the risk of well control.

[0003] In order to improve the efficiency of shut-in and optimize the shut-in operation mode, the multi-person collaborative control of shut-in is improved to one-button shut-in, which can avoid misoperation and reduce well control risks, and achieve accurate, fast and efficient shut-in. In recent years, many scholars and research institutions have gradually carried out relevant research on automated shut-in control methods. Carlsen took the lead in proposing the steps and implementation ideas for automated shut-in during overflow, using a dynamic multiphase flow model to evaluate whether to perform automated shut-in, and completing automated shut-in operations by controlling pumps and throttle valves, providing ideas for the research of automated shut-in control methods. SafeInflux Company determines the occurrence of overflow and well kick by monitoring the mud pool increment during drilling. If the mud pool increment is greater than the set threshold, the developed automated shut-in system will send a one-button shut-in signal to control the drill string to lift, shut down the top drive, mud pump, and close the blowout preventer and throttle valve, realizing automated shut-in during drilling. According to the current status and characteristics of the existing well control equipment, the transformation ideas of realizing automatic well shut-in were proposed. The existing electrical control and wireless remote control systems were integrated and controlled by software to realize the control of the well shut-in equipment. The steps of automatic well shut-in during drilling, tripping drill pipe, tripping drill collar, casing, empty well and logging were summarized, and they were successfully applied in Shengli Oilfield and Tarim Oilfield. The transformation ideas of automatic well shut-in were summarized for land oil wells, gas wells and deepwater oil wells respectively. On the basis of the original automatic control winch, mud pump, top drive and blowout preventer, it was proposed to realize the automatic connection of internal blowout prevention tools by mechanical control, such as the check valve of drilling tools and the short joint of plug valve, etc., which improved the process of automatic well shut-in and further ensured the efficiency and safety of well shut-in.

[0004] Through the above investigation, it can be found that the current well-shut-in equipment is not highly intelligent. The current well-shut-in equipment or system has realized automatic control of well-shut-in equipment such as blowout preventer groups and throttling manifolds, but the overall intelligent linkage still has room for improvement, such as real-time identification and feedback of the status of each well-shut-in equipment before well-shut-in and during the entire well-shut-in process, so as to achieve faster well-shut-in. Summary of the invention

[0005] In view of the above problems, the purpose of the present invention is to provide an intelligent identification system, method, medium and equipment for the operating status of offshore well shut-in equipment, which uses data mining and machine vision algorithms to construct an intelligent identification system for the operating status of well shut-in equipment, which can intelligently identify the operating status of top drive, mud pump, throttle valve, blowout preventer and drill pipe joint inside the blowout preventer during automated well shut-in and manual well shut-in processes, so as to ensure the efficient implementation of well shut-in operations.

[0006] To achieve the above-mentioned purpose, in the first aspect, the technical solution adopted by the present invention is: a method for intelligently identifying the operating status of offshore shut-in equipment, which includes: obtaining real-time logging data at the drilling site and a detailed table of drilling tools for the drilling operation, and analyzing the data characteristics of the shut-in equipment in the switch state; simultaneously obtaining image data of the throttling control box and the blowout preventer remote control console in real time; making a comprehensive judgment on the extracted data characteristics according to preset logical judgment conditions, so as to obtain the switch status of the mud pump and top drive and whether the drill pipe joint is in the blowout preventer in real time, and obtain the real-time status of the shut-in equipment; training a machine vision model through image data, obtaining an intelligent recognition module to identify the switch status of the throttle valve and the blowout preventer in real time, and transmitting it to the driller's platform after being summarized with the real-time status of the shut-in equipment.

[0007] Furthermore, real-time logging data and the drilling tool details table of the drilling site are obtained, and the data characteristics of the shut-in equipment in the on / off state are analyzed, including:

[0008] Collect the "well depth", "speed", "pump pressure", "displacement", "torque" and drilling tool combination information in the on-site real-time logging data and the drilling tool details table of the drilling operation;

[0009] According to the changing trends of the operating status parameters of the top drive, drawworks and mud pump, the approximate ranges of "speed", "torque", "pump pressure" and "displacement" of the top drive and mud pump in the switching state are obtained.

[0010] Furthermore, a comprehensive judgment is made on the extracted data features according to preset logical judgment conditions, including:

[0011] The method for judging the operating status of the top drive is as follows: when the speed is 0, it is preliminarily judged that the top drive has stopped working, and the top drive status is checked by torque. If the torque is also 0 or close to 0 at this time, it is finally judged that the top drive is in a stopped working state;

[0012] The method for judging the status of the mud pump is as follows: when the pump pressure is 0, it is preliminarily judged that the mud pump has stopped working, and the mud pump status is checked by the displacement. If the displacement is 0 or close to 0, it is finally judged that the mud pump is in a stopped working state;

[0013] The method for determining the position of the drill pipe is: the drill pipe currently at the wellhead can be calculated by the current "well depth" and the accurate length of each drill pipe in the drill pipe details table, so as to determine whether there are joints and couplings for the drill pipe inside the blowout preventer group.

[0014] Furthermore, image data of the throttling control box and the BOP remote console are obtained in real time, including: installing optical sensors in front of the BOP remote console and in front of the throttling control box of the driller's platform, and obtaining real-time image data of the BOP remote console operating lever and the throttle valve opening gauge through the optical sensors.

[0015] Furthermore, the machine vision model is trained through image data, including:

[0016] The image data is converted into pictures, the real-time images are annotated, and the annotated pictures are used as training sets to train the YOLO machine vision model, and the visual recognition model of the blowout preventer and throttle valve switch status is obtained as an intelligent recognition model.

[0017] Furthermore, the real-time images obtained are annotated with status, specifically: "Annular BOP—Open", "Annular BOP—Closed", "Fully Enclosed Gate BOP—Open", "Fully Enclosed Gate BOP—Closed", "Semi-Enclosed Gate BOP—Open", "Semi-Enclosed Gate BOP—Closed", "Throttle Valve Opening—Fully Open", "Throttle Valve Opening—High Opening", "Throttle Valve Opening—Medium Opening", "Throttle Valve Opening—Low Opening", "Throttle Valve Opening—Fully Closed".

[0018] Furthermore, an intelligent recognition module is obtained to identify the switch status of the throttle valve and the blowout preventer in real time, including: obtaining real-time images of corresponding instruments through on-site optical sensors, inputting them into the intelligent recognition model, and judging the switch status of each blowout preventer and the switch status of the throttle valve in real time.

[0019] In the second aspect, the technical solution adopted by the present invention is: an intelligent identification system for the operating status of offshore shut-in equipment, which includes: obtaining real-time logging data at the drilling site and a detailed table of drilling tools for the drilling operation, and analyzing the data characteristics of the shut-in equipment in the switch state; simultaneously obtaining real-time image data of the throttling control box and the blowout preventer remote control console; performing a comprehensive judgment on the extracted data characteristics according to preset logical judgment conditions to obtain in real time the switch status of the mud pump and top drive and whether the drill pipe joint is in the blowout preventer, and obtain the real-time status of the shut-in equipment; training the machine vision model through image data to obtain an intelligent identification module to identify the switch status of the throttle valve and the blowout preventer in real time, and transmit it to the driller's platform after being summarized with the real-time status of the shut-in equipment.

[0020] In a third aspect, the technical solution adopted by the present invention is: a computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, and when the instructions are executed by a computing device, the computing device executes any one of the above methods.

[0021] In a fourth aspect, the technical solution adopted by the present invention is: a computing device, comprising: one or more processors, a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the above methods.

[0022] The present invention adopts the above technical solution, which has the following advantages:

[0023] The present invention can effectively make up for the deficiency that the operating status of key well-shut-in equipment cannot be obtained in real time and accurately during the well-shut-in process. During the manual and automated well-shut-in process, the switch status of the top drive, the switch status of the mud pump, the switch status of the blowout preventer group, the switch status of the throttle valve, and whether the drill pipe joint and the coupling are inside the blowout preventer group are judged in real time and the results are fed back to the driller's platform. The present invention can feed back the above status to the driller's platform in real time without the need for engineers to read relevant instruments and observe relevant instruments. Its application in manual and automated well-shut-in processes can effectively shorten the time required for well-shut-in, effectively avoid the deterioration of overflow accidents, and effectively reduce well control risks. It has a very broad prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a schematic diagram of the overall structure of the intelligent identification system for the operating status of offshore well shut-in equipment in an embodiment of the present invention;

[0025] Figure 2 It is an overall flow chart of the intelligent identification method of the operating status of offshore well shut-in equipment in an embodiment of the present invention;

[0026] Figure 3 It is a detailed identification flow chart of the intelligent identification method of the top drive, mud pump and winch operating status of the intelligent identification system of the operating status of the offshore well shut-in equipment in the embodiment of the present invention;

[0027] Figure 4 It is a detailed identification flow chart of the intelligent identification method of the blowout preventer and throttle valve operating status of the intelligent identification system of the operating status of the offshore well shut-in equipment in the embodiment of the present invention. DETAILED DESCRIPTION

[0028] With the urgent need for the transformation of major oil fields to automated control, in view of the current reality that the operating status of each well-shut-in equipment cannot be obtained in real time before shutting in the well, the present invention provides an intelligent identification system, method, medium and equipment for the operating status of offshore well-shut-in equipment, which improves the efficiency of manual and automated well-shut-in, and can identify and feedback the status of each well-shut-in equipment in real time before the well-shut-in construction and during the entire well-shut-in process. Based on real-time logging data, drilling tool details table and optical sensor, the present invention uses mathematical logic and machine vision algorithms to construct an intelligent identification system for the operating status of well-shut-in equipment. Before shutting in the well at the drilling site, the present invention intelligently identifies the status of the mud pump, top drive, blowout preventer, throttle valve and winch, and transmits the identification results to the driller's platform in real time to assist the driller in completing the well-shut-in; at the same time, during the well-shut-in construction process, the system can also continuously and real-time obtain the operating status of the well-shut-in equipment, which can not only prevent well-shut-in operation errors, but also ensure well-shut-in safety.

[0029] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0030] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0031] In one embodiment of the present invention, an intelligent recognition system for the operating status of offshore well shut-in equipment is provided. The construction of the present invention refers to data mining and computer vision theory, has reliable principles and high recognition accuracy, and can provide guidance for drilling well control as a prerequisite for promoting efficient well shut-in or even automated well shut-in, and has broad application prospects. In this embodiment, Figure 1 As shown, the system includes:

[0032] The data acquisition and monitoring module obtains the real-time logging data and the drilling tool details table of the drilling site, and analyzes the data characteristics of the shut-in equipment in the on-off state; at the same time, it obtains the image data of the throttling control box and the blowout preventer remote control console in real time; among them, the shut-in equipment includes the top drive, mud pump and winch.

[0033] The data processing module pre-processes the extracted data features and then makes a comprehensive judgment on the processed data features according to the preset logical judgment conditions, so as to obtain the switch status of the mud pump and top drive and whether the drill pipe joint is in the blowout preventer in real time, and obtain the real-time status of the well shut-in equipment.

[0034] The intelligent model and intelligent recognition module trains the machine vision model through image data to identify the switch status of the throttle valve and blowout preventer in real time, and transmits it to the driller's platform after summarizing it with the real-time status of the well shut-in equipment and visualizing it to provide a basis for the well shut-in operation.

[0035] In the above embodiment, the real-time logging data of the drilling site and the detailed table of the drilling tools of the drilling are obtained, and the data characteristics of the shut-in equipment in the on / off state are analyzed, specifically:

[0036] Collect the "well depth", "speed", "pump pressure", "displacement", "torque" and drilling tool combination information in the on-site real-time logging data and the drilling tool details table of the drilling operation;

[0037] According to the changing trends of the operating status parameters of the top drive, drawworks and mud pump, the approximate ranges of "speed", "torque", "pump pressure" and "displacement" of the top drive and mud pump in the switching state are obtained.

[0038] In this embodiment, the extracted data features are comprehensively judged according to preset logical judgment conditions, specifically:

[0039] The method for judging the operating status of the top drive is as follows: when the speed is 0, it is preliminarily judged that the top drive has stopped working, and the top drive status is checked by torque. If the torque is also 0 or close to 0 at this time, it is finally judged that the top drive is in a stopped working state;

[0040] The method for judging the status of the mud pump is as follows: when the pump pressure is 0, it is preliminarily judged that the mud pump has stopped working, and the mud pump status is checked by the displacement. If the displacement is 0 or close to 0, it is finally judged that the mud pump is in a stopped working state;

[0041] The method for determining the position of the drill pipe is: the drill pipe currently at the wellhead can be calculated by the current "well depth" and the accurate length of each drill pipe in the drill pipe details table, so as to determine whether there are joints and couplings for the drill pipe inside the blowout preventer group.

[0042] In this embodiment, the data processing module performs preprocessing, such as field capture, normalization, video frame extraction, etc., to extract the current "well depth", "rotation speed", "pump pressure", "displacement", and "torque" from the logging data, and extract the current drilling tool combination and the precise length of each drilling tool from the drilling tool details table.

[0043] In the above embodiment, the image data of the throttling control box and the BOP remote console are obtained in real time, specifically: optical sensors are installed in front of the BOP remote console and in front of the throttling control box of the driller's platform, and real-time image data of the BOP remote console operating lever and the throttle valve opening meter are obtained through the optical sensors.

[0044] In the above embodiment, the machine vision model is trained by image data, specifically: the image data is converted into pictures, the obtained real-time images are annotated with states, and the annotated pictures are used as training sets to train the yolo machine vision model, and the visual recognition model of the blowout preventer and throttle valve switch state is obtained as an intelligent recognition model.

[0045] Among them, the real-time images obtained are annotated with status, specifically: "Annular BOP - Open", "Annular BOP - Closed", "Fully Enclosed Gate BOP - Open", "Fully Enclosed Gate BOP - Closed", "Semi-Enclosed Gate BOP - Open", "Semi-Enclosed Gate BOP - Closed", "Throttle Valve Opening - Fully Open", "Throttle Valve Opening - High Opening", "Throttle Valve Opening - Medium Opening", "Throttle Valve Opening - Low Opening", "Throttle Valve Opening - Fully Closed".

[0046] In this embodiment, the real-time image of the corresponding instrument is obtained by the on-site optical sensor, and is input into the intelligent recognition model to determine the switch status of each blowout preventer and the switch status of the throttle valve in real time.

[0047] In one embodiment of the present invention, a method for intelligently identifying the operating status of offshore well shut-in equipment is provided. Figure 2 As shown, the method comprises the following steps:

[0048] 1) Obtain real-time logging data and drilling tool details of the drilling site, analyze the data characteristics of the shut-in equipment in the on / off state; and simultaneously obtain real-time image data of the throttling control box and the BOP remote control console;

[0049] 2) Preprocess the extracted data features, and make a comprehensive judgment on the processed data features according to the preset logical judgment conditions, so as to obtain the switch status of the mud pump and top drive and whether the drill pipe joint is in the blowout preventer in real time, and obtain the real-time status of the well shut-in equipment;

[0050] 3) The machine vision model is trained through image data to identify the switch status of the throttle valve and blowout preventer in real time, and the real-time status of the well shut-in equipment is summarized and transmitted to the driller's platform and visualized to provide a basis for the well shut-in operation.

[0051] In the above step 1), real-time logging data of the drilling site and the drilling tool details table of the drilling are obtained, and the data characteristics of the shut-in equipment in the on / off state are analyzed, including the following steps:

[0052] 1.1) Collect the "well depth", "speed", "pump pressure", "displacement", "torque" and drilling tool combination information in the drilling tool details table of the drilling operation in the real-time logging data on site;

[0053] 1.2) According to the change trend of the operating status parameters of the top drive, drawworks and mud pump, the approximate range of the "speed", "torque", "pump pressure" and "displacement" of the top drive and mud pump in the switch state is summarized. Then, according to the "well depth" and the accurate length of each drilling tool in the drilling tool details table, it is calculated and judged whether the joints and couplings of the drill pipe are inside the blowout preventer group.

[0054] In this embodiment, at the drilling sites of different drilling companies, the present invention will obtain real-time logging data by linking with the on-site logging instrument and obtain the drilling tool details table of the current drilling session through the drilling design system.

[0055] In the above step 2), based on the processing result of step 1), the extracted data features are comprehensively judged according to the preset logical judgment conditions, such as Figure 3 The specific judgment method is as follows:

[0056] 2.1) The method for judging the operating status of the top drive is as follows: when the speed is 0, it is preliminarily judged that the top drive has stopped working, and the top drive status is checked by torque. If the torque is also 0 or close to 0 at this time, it is finally judged that the top drive is in a stopped working state;

[0057] 2.2) The method for judging the status of the mud pump is as follows: when the pump pressure is 0, it is preliminarily judged that the mud pump has stopped working, and the mud pump status is checked by the displacement. If the displacement is 0 or close to 0, it is finally judged that the mud pump is in a stopped working state;

[0058] 2.3) The method for determining the position of the drill pipe is: the drill pipe currently at the wellhead is calculated by the current "well depth" and the accurate length of each drill pipe in the drill pipe details table, so as to determine whether there are joints and couplings of the drill pipe inside the blowout preventer group, so as to avoid the joints and couplings that prevent the blowout preventer from being completely closed when closing the blowout preventer, resulting in a failure to shut down the well.

[0059] In this embodiment, data preprocessing, including, for example, field capture, normalization, video frame extraction, etc., extracts the current "well depth", "rotation speed", "pump pressure", "displacement", and "torque" from the logging data, and extracts the current drilling tool combination and the precise length of each drilling tool from the drilling tool details table.

[0060] In the above step 1), the image data of the throttling control box and the BOP remote console are obtained in real time. The specific method is: an optical sensor is installed in front of the BOP remote console and the throttling control box of the driller's platform, and the real-time image data of the BOP remote console operating lever and the throttle valve opening meter are obtained through the optical sensor.

[0061] In the above step 3), the machine vision model is trained by image data, such as Figure 4 As shown, specifically: convert the image data into pictures, annotate the status of the obtained real-time images, and use the annotated pictures as training sets to train the YOLO machine vision model, and obtain the blowout preventer and throttle valve switch status visual recognition model as an intelligent recognition model.

[0062] In this embodiment, the obtained real-time image is annotated with status, specifically: "Annular BOP—open", "Annular BOP—closed", "Fully enclosed ram BOP—open", "Fully enclosed ram BOP—closed", "Semi-enclosed ram BOP—open", "Semi-enclosed ram BOP—closed", "Throttle valve opening—fully open", "Throttle valve opening—high opening", "Throttle valve opening—medium opening", "Throttle valve opening—low opening", "Throttle valve opening—fully closed".

[0063] In the above step 3), an intelligent recognition module is obtained to identify the switch status of the throttle valve and the blowout preventer in real time, including: before and during the well closing, the real-time image of the corresponding instrument is obtained through the on-site optical sensor, input into the intelligent recognition model, and the switch status of each blowout preventer and the switch status of the throttle valve are judged in real time to guide the well closing operation. Among them, the real-time identification of the switch status of the throttle valve and the blowout preventer includes real-time identification of the current top drive, mud pump and drill pipe position.

[0064] The present invention is based on the logging data of the drilling site, the detailed table of drilling tools of a certain opening, the remote control console of the blowout preventer and the image information of the throttle valve opening meter, and uses mathematical statistics and machine vision theory to realize the intelligent identification of the operating status of the offshore well-closing equipment. By interconnecting with the relevant sensors at the drilling site to realize data collection, data processing, intelligent modeling and intelligent identification, the operating status and drill pipe position of the top drive, mud pump, each blowout preventer and throttle valve can be identified in real time before and during the well-closing process, which effectively solves the defect that the operating status of each key well-closing equipment cannot be obtained in real time in the current manual and automatic well-closing. The present invention can feed back the above-mentioned equipment status to the driller's platform in real time without the need for engineers to read relevant instruments and observe relevant instruments. It can be used in the manual and automatic well-closing process to effectively shorten the time required for well-closing, which will effectively avoid the deterioration of overflow accidents and effectively reduce well control risks. It has a very broad prospect.

[0065] In one embodiment of the present invention, a computing device is provided, which may be a terminal, and may include: a processor, a communication interface, a memory, a display screen, and an input device. Among them, the processor, the communication interface, and the memory communicate with each other through a communication bus. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory, and the non-volatile storage medium stores an operating system and a computer program. When the computer program is executed by the processor, the method in each of the above embodiments is implemented; the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a management network, NFC (near field communication) or other technologies. The display screen may be a liquid crystal display screen or an electronic ink display screen, and the input device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computing device, or an external keyboard, touchpad or mouse, etc. The processor may call the logic instructions in the memory.

[0066] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0067] In one embodiment of the present invention, a computer program product is provided, wherein the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided by the above-mentioned method embodiments.

[0068] In one embodiment of the present invention, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores server instructions, and the computer instructions enable a computer to execute the methods provided in the above embodiments.

[0069] The above embodiment provides a computer-readable storage medium, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0070] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0071] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligently identifying the operating status of offshore well shut-in equipment, characterized in that: include: Obtain real-time logging data and drilling tool details at the drilling site, and analyze the data characteristics of the shut-in equipment in the on / off state; At the same time, real-time image data of the throttling control box and the remote control console of the blowout preventer are obtained; Comprehensively judge the extracted data features according to the preset logical judgment conditions to obtain the switch status of the mud pump and top drive and whether the drill pipe joint is in the blowout preventer in real time, and obtain the real-time status of the well shut-in equipment; The machine vision model is trained by image data to obtain an intelligent recognition module to identify the switch status of the throttle valve and blowout preventer in real time, and then transmit it to the driller's platform after being summarized with the real-time status of the well shut-in equipment.

2. The method for intelligently identifying the operating status of offshore well shut-in equipment according to claim 1, characterized in that: Obtain real-time logging data and drilling tool details of the drilling site, and analyze the data characteristics of the shut-in equipment in the on / off state, including: Collect the "well depth", "speed", "pump pressure", "displacement", "torque" in the real-time logging data on site and the drilling tool combination information in the drilling tool details table of the drilling operation; According to the changing trends of the operating status parameters of the top drive, drawworks and mud pump, the approximate ranges of "speed", "torque", "pump pressure" and "displacement" of the top drive and mud pump in the on-off state are obtained.

3. The method for intelligently identifying the operating status of offshore well shut-in equipment according to claim 2, characterized in that: Comprehensively judge the extracted data features according to the preset logical judgment conditions, including: The method for judging the operating status of the top drive is as follows: when the speed is 0, it is preliminarily judged that the top drive has stopped working, and the top drive status is checked by torque. If the torque is also 0 or close to 0 at this time, it is finally judged that the top drive is in a stopped working state; The method for judging the status of the mud pump is as follows: when the pump pressure is 0, it is preliminarily judged that the mud pump has stopped working, and the mud pump status is checked by the displacement. If the displacement is 0 or close to 0, it is finally judged that the mud pump is in a stopped working state; The method for determining the position of the drill pipe is to calculate the drill pipe currently at the wellhead through the current "well depth" and the accurate length of each drill pipe in the drill pipe details table, so as to determine whether there are joints and couplings for the drill pipe inside the blowout preventer group.

4. The method for intelligently identifying the operating status of offshore well shut-in equipment according to claim 1, characterized in that: Real-time acquisition of image data of the throttling control box and the remote control console of the blowout preventer includes: installing optical sensors in front of the remote control console of the blowout preventer and in front of the throttling control box of the driller's platform, and acquiring real-time image data of the operating lever and the throttle valve opening gauge of the remote control console of the blowout preventer through the optical sensors.

5. The method for intelligently identifying the operating status of offshore well shut-in equipment according to claim 1, characterized in that: Training machine vision models using image data, including: The image data is converted into pictures, the real-time images are annotated, and the annotated pictures are used as training sets to train the YOLO machine vision model, and the visual recognition model of the blowout preventer and throttle valve switch status is obtained as an intelligent recognition model.

6. The method for intelligently identifying the operating status of offshore well shut-in equipment according to claim 5, characterized in that: The real-time images obtained are annotated with status, specifically: "annular blowout preventer - open", "annular blowout preventer - closed", "fully enclosed ram blowout preventer - open", "fully enclosed ram blowout preventer - closed", "semi-enclosed ram blowout preventer - open", "semi-enclosed ram blowout preventer - closed", "throttle valve opening - fully open", "throttle valve opening - high opening", "throttle valve opening - medium opening", "throttle valve opening - low opening", "throttle valve opening - fully closed".

7. The method for intelligently identifying the operating status of offshore well shut-in equipment according to claim 5, characterized in that: An intelligent recognition module is obtained to identify the switch status of the throttle valve and the blowout preventer in real time, including: obtaining the real-time image of the corresponding instrument through the on-site optical sensor, inputting it into the intelligent recognition model, and judging the switch status of each blowout preventer and the switch status of the throttle valve in real time.

8. An intelligent identification system for the operating status of offshore well shut-in equipment, characterized in that: include: Obtain real-time logging data and drilling tool details at the drilling site, and analyze the data characteristics of the shut-in equipment in the on / off state; At the same time, real-time image data of the throttling control box and the remote control console of the blowout preventer are obtained; Comprehensively judge the extracted data features according to the preset logical judgment conditions to obtain the switch status of the mud pump and top drive and whether the drill pipe joint is in the blowout preventer in real time, and obtain the real-time status of the well shut-in equipment; The machine vision model is trained by image data to obtain an intelligent recognition module to identify the switch status of the throttle valve and blowout preventer in real time, and then transmit it to the driller's platform after being summarized with the real-time status of the well shut-in equipment.

9. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions, which, when executed by a computing device, cause the computing device to perform any one of the methods of claims 1 to 7.

10. A computing device, characterized in that include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any one of the methods described in claims 1 to 7.

Images