Detection method for pumping stop of pumping unit and related equipment

Abstract

The invention discloses a detection method for pumping stopping of an oil pumping unit and related equipment, relates to the field of intelligent detection of oil pumping units, and mainly aims to solve the problem that the detection of pumping stopping of the oil pumping unit is not accurate and intelligent enough at present. The method comprises the following steps: determining a horse head pumping stopping first parameter based on an AI visual analysis image of a target pumping unit; determining a second parameter of pumping stopping of the horsehead based on the data acquired by the internet of things of the target pumping unit; and on the basis of the horse head pumping stopping first parameter and the horse head pumping stopping second parameter, pumping stopping data of the target pumping unit are determined. The device is used for the detection process of pumping stop of the pumping unit.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent detection of pumping units, and in particular to a method for detecting stop pumping of a pumping unit and related equipment. BACKGROUND

[0002] At present, pumping units are mainly used to exploit oil at home and abroad. As of now, there are more than 210,000 pumping unit wells in China. With the oilfield exploitation entering the middle and late stages, the formation liquid supply capacity decreases, and the number of low-yield and low-efficiency wells increases. However, continuous low-efficiency production of a large number of oil wells will inevitably cause dry grinding of pumping unit equipment, and heating of the polished rod of the pumping unit will accelerate the aging of the equipment, thereby causing the pumping unit to stop pumping due to failure. At present, the stop pumping of the pumping unit still relies on unilateral or manual measurement, and there is still a lack of a more accurate and intelligent method for detecting stop pumping of the pumping unit. SUMMARY

[0003] In view of the above problems, the present application provides a method for detecting stop pumping of a pumping unit and related equipment, and the main purpose is to solve the problem that the current detection of stop pumping of the pumping unit is not accurate and intelligent.

[0004] To solve the above at least one technical problem, in a first aspect, the present application provides a method for detecting stop pumping of a pumping unit Methods The method comprises:

[0005] determining a first parameter of stop pumping of a horse head based on AI visual analysis of an image of a target pumping unit;

[0006] determining a second parameter of stop pumping of the horse head based on data collected by Internet of Things of the target pumping unit;

[0007] determining stop pumping data of the target pumping unit based on the first parameter of stop pumping of the horse head and the second parameter of stop pumping of the horse head.

[0008] Optionally, the method for determining the first parameter of stop pumping of the horse head based on AI visual analysis of the image of the target pumping unit comprises:

[0009] determining real-time video data of the target pumping unit collected by an image collection device;

[0010] determining a position coordinate of a horse head of the target pumping unit based on the real-time video data, wherein the position coordinate of the horse head of the target pumping unit is used to determine the first parameter of stop pumping of the horse head

[0011] Optionally, the method for determining the position coordinate of the horse head of the target pumping unit based on the real-time video data, wherein the position coordinate of the horse head of the target pumping unit is used to determine the first parameter of stop pumping of the horse head, comprises:

[0012] acquiring AI visual analysis images of the target pumping unit at different times within a preset time of the real-time video data;

[0013] perform target frame aggregation comparison analysis on the AI vision analysis images of the target pumping units at different time instants to obtain horsehead position coordinates of the target pumping unit at different time instants;

[0014] determine an overlap degree by comparing the horsehead position coordinates at different time instants;

[0015] determine a horsehead pumping stop first parameter in a case where the overlap degree meets a preset threshold.

[0016] Optionally, the method further includes:

[0017] perform target frame deduplication in a case where the horsehead pumping stop first parameter reflects that the target pumping unit is stopped pumping.

[0018] Optionally, the horsehead pumping stop parameter includes well station information of a production plant operation area of the target pumping unit.

[0019] Optionally, the horsehead pumping stop second parameter is determined based on Internet of Things (IoT) collection data of the target pumping unit, and includes:

[0020] in a case where the horsehead pumping stop first parameter reflects that the target pumping unit is stopped pumping, call IoT collection data of the target pumping unit based on well station information of a production plant operation area of the target pumping unit corresponding to the horsehead pumping stop first parameter;

[0021] determine a horsehead pumping stop second parameter based on IoT collection data of the target pumping unit.

[0022] Optionally, the IoT collection data includes real-time production data, and the horsehead pumping stop second parameter is determined based on the IoT collection data of the target pumping unit, and includes:

[0023] determine a horsehead pumping stop second parameter of the target pumping unit based on real-time production data of the target pumping unit;

[0024] in a case where the horsehead pumping stop second parameter reflects that the target pumping unit is stopped pumping, determine a pumping stop reason based on real-time production data of the target pumping unit.

[0025] In a second aspect, an embodiment of the present application further provides a pumping unit stop pumping detection device, including:

[0026] a first determination unit configured to determine a horsehead pumping stop first parameter based on AI vision analysis images of a target pumping unit;

[0027] a second determination unit configured to determine a horsehead pumping stop second parameter based on IoT collection data of the target pumping unit;

[0028] A third determining unit is configured to determine the stop pumping data of the target pumping unit based on the first parameter of the stop pumping of the horse head and the second parameter of the stop pumping of the horse head.

[0029] To achieve the above object, according to a third aspect of the present application, a computer readable storage medium is provided, which comprises a stored program, wherein the steps of the method for detecting the stop pumping of the pumping unit are implemented when the program is executed by a processor.

[0030] To achieve the above object, according to a fourth aspect of the present application, an electronic device is provided, which comprises at least one processor and at least one memory connected to the processor; wherein the processor is configured to invoke program instructions in the memory to execute the steps of the method for detecting the stop pumping of the pumping unit.

[0031] By means of the above technical solution, the method for detecting the stop pumping of the pumping unit and the related device provided by the present application can solve the problem that the detection of the stop pumping of the pumping unit is not accurate and intelligent enough. The first parameter of the stop pumping of the horse head is determined based on the AI visual analysis of the image of the target pumping unit; the second parameter of the stop pumping of the horse head is determined based on the data collected by the Internet of Things of the target pumping unit; and the stop pumping data of the target pumping unit is determined based on the first parameter of the stop pumping of the horse head and the second parameter of the stop pumping of the horse head. In the above solution, the AI visual analysis is used to identify the abnormal state of the stop pumping of the pumping unit, and the data collected by the Internet of Things is used to make a joint judgment. The accuracy of the judgment of the abnormal operation of the pumping unit is improved, and the time for fault positioning is shortened.

[0032] Correspondingly, the detection device, the electronic device and the computer readable storage medium for detecting the stop pumping of the pumping unit provided by the embodiments of the present application also have the above technical effects.

[0033] The above description is only a summary of the technical solutions of the present application. In order to make the technical solutions of the present application more clearly understood and implemented, and to make the above and other purposes, characteristics and advantages of the present application more apparent and easy to understand, the following will specifically describe the embodiments of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0034] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are included to provide a description of preferred embodiments, and are not meant to limit the present application. Moreover, the same reference numerals are used throughout the accompanying drawings to represent the same components. In the drawings:

[0035] Figure 1 A flowchart of a method for detecting the stop pumping of a pumping unit is shown;

[0036] Figure 2 Fig. 1 shows a real scene picture of a donkey head recognition frame provided by an embodiment of the present application;

[0037] Figure 3 Fig. 2 shows another real scene picture of a donkey head recognition frame provided by an embodiment of the present application;

[0038] Figure 4 Fig. 3 shows still another real scene picture of a donkey head recognition frame provided by an embodiment of the present application;

[0039] Figure 5 Fig. 4 shows a real scene picture of a donkey head stop pumping result provided by an embodiment of the present application;

[0040] Figure 6 Fig. 5 shows a composition schematic block diagram of a detection device for pumping unit stop pumping provided by an embodiment of the present application;

[0041] Figure 7 Fig. 6 shows a composition schematic block diagram of a detection electronic device for pumping unit stop pumping provided by an embodiment of the present application. DETAILED DESCRIPTION

[0042] Exemplary embodiments of the present application will be described herein below with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present application can be more thoroughly understood and so that the scope of the present application can be completely conveyed to those skilled in the art.

[0043] In order to solve the problem that the detection of pumping unit stop pumping is not accurate and intelligent enough, an embodiment of the present application provides a detection method for pumping unit stop pumping, as shown in Figure 1 The method comprises the following steps.

[0044] S101, determining a donkey head stop pumping first parameter based on AI visual analysis of an image of a target pumping unit;

[0045] The step S101 further comprises S1011 and S1012.

[0046] S1011, determining real-time video data of the target pumping unit collected by an image collection device;

[0047] Determining a donkey head position coordinate of the target pumping unit based on the real-time video data, wherein the donkey head position coordinate of the target pumping unit is used to determine the donkey head stop pumping first parameter.

[0048] Exemplarily, the AI visual analysis can monitor a well station in real time through a video camera and analyze and process video data through an AI recognition algorithm model.

[0049] Specifically, the determination of the donkey head position coordinates of the target pumping unit based on the real-time video data, wherein the donkey head position coordinates of the target pumping unit are used to determine the first parameter for stopping pumping, including:

[0050] The system acquires AI visual analysis images of the target pumping unit at different times within a preset time period from the real-time video data; performs target bounding box aggregation and comparison analysis on the AI ​​visual analysis images of the target pumping unit at different times to obtain the donkey head position coordinates of the target pumping unit at different times; compares the donkey head position coordinates at different times to determine the overlap; and determines the first parameter for stopping pumping when the overlap meets a preset threshold.

[0051] For example, such as Figures 2-4 As shown, this application first uses AI visual analysis to analyze real-time video data captured by a video camera. An AI visual analysis algorithm model is used to identify the donkey's head in the video footage.

[0052] Furthermore, the donkey head event of the oil pumping unit identified by the algorithm model is analyzed using a target bounding box aggregation strategy. The approach is to perform target bounding box aggregation and comparative analysis on several images at different times within five minutes (the specific preset time can be flexibly adjusted and is not specifically limited). First, the position coordinates of the donkey head in the image are identified, and then the overlap information of the donkey head position coordinates of several images is judged.

[0053] It should be noted that, after repeated verification, setting the overlap ratio too low leads to an increase in false alarms when identifying the donkey head stopping the sampling, while setting the overlap ratio too high leads to a decrease in positive alarms when identifying the donkey head stopping the sampling. The precision and recall are optimal only when the overlap of the coordinates of the donkey head's location is greater than 95% (the specific preset threshold can be flexibly adjusted and is not specifically limited). That is, an overlap ratio of 95% or higher is used as the basis for judging whether the donkey head stops sampling.

[0054] S1012. When the first parameter feedback of the donkey head stopping pumping indicates that the target pumping unit has stopped pumping, deduplication of the target frame is performed.

[0055] This application takes into account that when the target box aggregation strategy determines that the pumping unit is in a stopped state, it adopts a target box deduplication strategy to deduplicate the target boxes, so as to prevent multiple alarm messages from being generated due to one problem and limit the number of problem alarms.

[0056] This application's fault warning and rapid response reduce production downtime and avoid economic losses caused by prolonged abnormal shutdowns. By promptly sending alarm messages to locate and address problems, the production process becomes more efficient, improving overall production effectiveness.

[0057] In one embodiment, the donkey head stopping parameters include well station information of the oilfield operating area of ​​the target pumping unit.

[0058] S102. Determine the second parameter for stopping pumping by the donkey head based on IoT data collected from the target pumping unit;

[0059] The above-mentioned step S102 also includes S1021:

[0060] S1021. When the first parameter of the donkey head stopping pumping reflects that the target pumping unit has stopped pumping, the IoT data collected by the target pumping unit is called based on the well station information of the oilfield operation area of ​​the target pumping unit corresponding to the first parameter of the donkey head stopping pumping; and the second parameter of the donkey head stopping pumping is determined based on the IoT data collected by the target pumping unit.

[0061] For example, this application considers the construction of an industrial control Internet of Things (ICIoT) to achieve real-time acquisition, remote transmission, and video monitoring of production data (pressure, temperature, flow rate, liquid level, load, electrical parameters, etc.).

[0062] like Figure 5 As shown, based on the above-mentioned AI visual analysis platform, the platform information of the well station in the oilfield operation area where the corresponding donkey-head stop pumping video camera is located is determined by the first parameter of the donkey-head stop pumping. This information is then transmitted to the data analysis platform through an interface push. The data analysis platform uses the platform information of the video camera to map the data with the pumping unit information.

[0063] In one embodiment, the IoT-collected data includes real-time production data, and the determination of the second parameter for the stop pumping head based on the IoT-collected data of the target pumping unit includes: determining the second parameter for the stop pumping head of the target pumping unit based on the real-time production data of the target pumping unit; and, if the second parameter for the stop pumping head reflects that the target pumping unit has stopped pumping, determining the reason for the stop pumping based on the real-time production data of the target pumping unit.

[0064] Specifically, the data analysis platform obtains information about pumping units that have stopped pumping, retrieves real-time production data from the oil and gas production IoT system to analyze the pumping unit's status, and uses designed analytical algorithms to comprehensively analyze data such as oil pressure, wellhead temperature, three-phase current, three-phase voltage, stroke, and stroke count to confirm the specific cause of the pumping unit's stoppage. The following is a diagnostic table for pumping unit stoppage status jointly detected by AI visual analysis and IoT data collection.

[0065] Table 1. Diagnostic Table for Pumping Unit Shutdown Status Detected by Joint Detection of AI Visual Analysis and IoT Data Collection

[0066]

[0067]

[0068] The above solution first considers identifying normal well shutdown operations and intermittent well production shutdowns, preventing false alarms. Secondly, it sends clearly defined abnormal status data to an alarm visualization platform for alert push, while normal pumping unit shutdown information is fed back to the visual analysis platform, avoiding repeated detection within a certain period. This significantly optimizes the inspection and maintenance process in actual production, reducing the need for multiple on-site confirmations of problem / fault points compared to existing technologies.

[0069] S103. Determine the stop-pumping data of the target pumping unit based on the first parameter and the second parameter of the donkey head stopping pumping.

[0070] Therefore, this invention creates a pumping unit shutdown detection model that uses a combination of AI visual analysis and IoT data collection to accurately distinguish between normal production status and abnormal shutdown faults, reducing false alarms. This application is highly practical for the production scenario of pumping unit shutdown, with a rationally designed detection method. It optimizes the problem of high false alarm rates in abnormal states due to insufficient single-judgment analysis, achieving high fault location accuracy. It reduces the workload of regular inspections for production management personnel, allowing them to focus on resolving identified faults and lowering maintenance time and labor costs associated with delayed detection or feedback.

[0071] By employing the above technical solution, the method and related equipment for detecting pumping unit stoppage provided by this invention address the problem of insufficient accuracy and intelligence in current pumping unit stoppage detection methods. This invention determines a first parameter of pumping unit stoppage based on AI visual analysis of the target pumping unit image; determines a second parameter of pumping unit stoppage based on IoT-collected data of the target pumping unit; and determines the stoppage data of the target pumping unit based on the first and second parameters of pumping unit stoppage. In this solution, AI visual analysis is used to identify the abnormal state of pumping unit stoppage, combined with IoT-collected data for linked judgment. A double-verification method is used for secondary analysis, improving the accuracy of judging abnormal pumping unit operation and shortening the fault location time.

[0072] It is understandable that this application can also determine abnormal generator operation by first analyzing IoT-collected data, and then combining the results of the IoT-collected data with the results of AI visual analysis. Specifically:

[0073] The data analysis platform first analyzes the pumping unit status by retrieving real-time single-well production data from the oil and gas production IoT system. It then uses designed analytical algorithms (oil pressure, wellhead temperature, three-phase current, three-phase voltage, stroke, stroke count, etc.) to determine the pumping unit's real-time operating status. When an abnormal status is detected, the information of the abnormal pumping unit is requested via an interface to the visual analysis platform for secondary analysis.

[0074] Then, the visual analysis platform retrieves the corresponding video data through the received interface request to identify the donkey head of the pumping unit; it uses the donkey head stop pumping algorithm model of AI visual analysis to determine the target box aggregation strategy; when the target box aggregation strategy determines the real-time operating status of the pumping unit, it pushes the result information to the data analysis platform.

[0075] Finally, the data analysis platform performs joint detection and judgment based on the pushed results. Abnormal pumping stoppages detected by the joint detection are sent to the alarm visualization platform for alarm push, while normal pumping stoppages are fed back to the visual analysis platform, and are not repeated for a certain period of time.

[0076] Furthermore, as a response to the above Figure 1 In addition to the implementation of the method shown, this embodiment of the invention also provides a detection device for detecting the shutdown of an oil pumping unit, used to detect the above-mentioned... Figure 1 The method shown is implemented accordingly. This device embodiment corresponds to the foregoing method embodiment. For ease of reading, this device embodiment will not repeat the details of the foregoing method embodiment, but it should be clear that the device in this embodiment can implement all the contents of the foregoing method embodiment. Figure 6 As shown, the device includes: a first determining unit 21, a second determining unit 22, and a third determining unit 23, wherein...

[0077] The first determining unit 21 is used to determine the first parameter for stopping pumping at the donkey head based on the AI ​​visual analysis image of the target pumping unit;

[0078] The second determining unit 22 is used to determine the second parameter for stopping pumping by the donkey head based on the IoT data collected by the target pumping unit;

[0079] The third determining unit 23 is used to determine the stop pumping data of the target pumping unit based on the first stop pumping parameter of the donkey head and the second stop pumping parameter of the donkey head.

[0080] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and by adjusting kernel parameters, a method for detecting the cessation of pumping unit operation can be implemented, addressing the current problem of insufficient accuracy and intelligence in detecting pumping unit cessation.

[0081] This invention provides a computer-readable storage medium including a stored program that, when executed by a processor, implements a method for detecting when a pumping unit stops pumping.

[0082] This invention provides a processor for running a program, wherein the program executes a method for detecting when the pumping unit stops pumping.

[0083] This invention provides an electronic device, which includes at least one processor and at least one memory connected to the processor; wherein the processor is used to call program instructions in the memory to execute the detection method for stopping pumping in an oil pumping unit as described above.

[0084] This invention provides an electronic device 30, such as... Figure 7 As shown, the electronic device includes at least one processor 301, and at least one memory 302 and bus 303 connected to the processor; wherein, the processor 301 and the memory 302 communicate with each other through the bus 303; the processor 301 is used to call program instructions in the memory to execute the above-mentioned detection method for stopping the pumping unit.

[0085] The smart electronic devices mentioned in this article can be PCs, tablets, mobile phones, etc.

[0086] This application also provides a computer program product that, when executed on a process management electronic device, is suitable for executing a program that initializes the detection method steps for stopping the pumping unit as described above.

[0087] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0088] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0089] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0090] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0091] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0092] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to perform actions such as... Figure 1 The control flow of the memory in the corresponding embodiment.

[0093] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0094] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0096] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0097] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0098] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0099] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for detecting the cessation of pumping in an oil pumping unit, characterized in that, include: The first parameter for stopping pumping at the donkey head is determined based on the AI ​​visual analysis image of the target pumping unit; The second parameter for stopping pumping is determined based on IoT data collected from the target pumping unit. The stop-pumping data of the target pumping unit is determined based on the first parameter and the second parameter of the donkey head stopping pumping.

2. The method according to claim 1, characterized in that, The AI ​​visual analysis image based on the target pumping unit is used to determine the first parameter for stopping pumping at the donkey head, including: Determine the real-time video data of the target pumping unit acquired by the image acquisition equipment; The donkey head position coordinates of the target pumping unit are determined based on the real-time video data, wherein the donkey head position coordinates of the target pumping unit are used to determine the first parameter for stopping pumping at the donkey head.

3. The method according to claim 2, characterized in that, The determination of the donkey head position coordinates of the target pumping unit based on the real-time video data, wherein the donkey head position coordinates of the target pumping unit are used to determine the first parameter for stopping pumping, including: AI visual analysis images of the target pumping unit at different times within a preset time period are obtained from the real-time video data. AI visual analysis images of the target pumping unit at different times are subjected to target bounding box aggregation and comparison analysis to obtain the donkey head position coordinates of the target pumping unit at different times. The degree of overlap is determined by comparing the coordinates of the donkey's head at different times. If the overlap meets a preset threshold, determine the first parameter for stopping pumping at the donkey head.

4. The method according to claim 1, characterized in that, Also includes: When the first parameter feedback of the donkey head stopping pumping indicates that the target pumping unit has stopped pumping, the target frame is deduplicated.

5. The method according to claim 1, characterized in that, The donkey-head stop pumping parameters include information on the target pumping unit's oil production plant, oil production area, oil production station, well site, and pumping unit well.

6. The method according to claim 5, characterized in that, The determination of the second parameter for stopping pumping by the donkey head based on IoT-collected data from the target pumping unit includes: When the first parameter of the donkey head stopping pumping reflects that the target pumping unit has stopped pumping, the IoT data collected by the target pumping unit is called based on the oil production plant, oil production area, oil production station, well site and pumping unit information of the target pumping unit corresponding to the first parameter of the donkey head stopping pumping; The second parameter for stopping pumping is determined based on IoT-collected data from the target pumping unit.

7. The method according to claim 6, characterized in that, The IoT-collected data includes real-time production data. The IoT-collected data based on the target pumping unit determines the second parameter for stopping pumping, including: The second parameter for stopping pumping at the donkey head of the target pumping unit is determined based on the real-time production data of the target pumping unit. When the second parameter indicating that the target pumping unit has stopped pumping reflects that the pumping unit has stopped pumping, the reason for the stoppage is determined based on the real-time production data of the target pumping unit.

8. A detection device for the cessation of pumping in an oil pumping unit, characterized in that, Also includes: The first determining unit is used to determine the first parameter for stopping pumping at the donkey head based on the AI ​​visual analysis image of the target pumping unit; The second determining unit is used to determine the second parameter for stopping pumping by the donkey head based on the IoT-collected data of the target pumping unit; The third determining unit is used to determine the stop-pumping data of the target pumping unit based on the first parameter of the donkey head stopping pumping and the second parameter of the donkey head stopping pumping.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed by a processor, it implements the steps of the detection method for stopping pumping by a pumping unit as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, The electronic device includes at least one processor and at least one memory connected to the processor; wherein the processor is configured to call program instructions in the memory to execute the steps of the detection method for stopping pumping by the pumping unit as described in any one of claims 1 to 7.

Images