One-key intelligent video automatic inspection method and system for offshore unmanned platform, medium and equipment

Abstract

The invention relates to the field of inspection of offshore oil and gas production platforms, and discloses a one-key intelligent video automatic inspection method, system, medium and equipment for an offshore unmanned platform, and the method comprises the steps: obtaining the field video data of an inspection route, carrying out the intelligent video analysis according to different inspection contents on the inspection route, judging whether an abnormal image exists or not, and if yes, sending the abnormal image to a server; in an abnormal state, an alarm is given and a work order is sent to an electronic work order system; a platform fire and gas system, a central control system and equipment abnormal alarm signals correspond to nearby on-site video monitoring equipment in a soft docking mode, position information of the alarm signal equipment is read, the corresponding video monitoring equipment is linked, video window popup and alarm are carried out, and a work order is sent to an electronic work ticket system; embedding an IP address of a field video monitoring device in each point position of the platform three-dimensional model, and giving an alarm and sending a work order to an electronic work order system in an abnormal state; and performing on-site abnormity checking according to the abnormal state information, and forming an inspection analysis report according to a checking or maintenance result.

Description

Technical Field

[0001] The present invention relates to the technical field of offshore oil and gas production platform inspection, and in particular to a one-key intelligent video automatic inspection method, system, medium and equipment for an offshore unmanned platform. Background Art

[0002] Offshore oil and gas production is a high-risk, high-intensity operation. Daily inspections of offshore platforms generally rely on manual inspections, and the inspection contents mainly include meter reading, leakage detection, and environmental safety status detection. With the continuous advancement of technology, manual inspections have gradually shifted to digitalization. At present, most offshore platforms are equipped with handheld mobile inspection terminals as auxiliary equipment for manual inspections. The data transmission network is mainly based on the platform's super wireless network platform. Inspection personnel still need to go to the site to upload on-site inspection pictures and accident pictures to the inspection platform through handheld inspection terminals. However, traditional manual inspections have natural bottlenecks: safety issues for inspection personnel in dangerous environments, large workload for manual inspections, and low efficiency. With the arrival of the trend of less-manned / unmanned operations, labor costs are high, and inspection and maintenance personnel are decreasing. There are differences in judgment standards for manual inspections, inspection blind spots, and errors and omissions. With the current development trend of unmanned offshore platforms, it is necessary to improve the level of inspection intelligence as soon as possible to replace or partially replace manual inspections to meet the inspection needs under special environments of offshore oil fields.

[0003] At present, there are two relatively advanced intelligent inspection methods: one is wheeled robots, which carry infrared thermal imagers, high-definition cameras, laser methane leak monitoring cameras and other front-end hardware equipment on wheeled robots to inspect the pointer pressure gauges, pointer temperature gauges, pipelines, valves, and various pumps of production process equipment such as compressors, air compressors, pumps, control panels, and tanks, and monitor the on-site environmental gas (methane concentration), noise, and temperature to identify and judge abnormal situations. The wheeled robot inspection method is more flexible, but it is necessary to deploy a wireless network inside the platform to achieve real-time upload of video data. At the same time, due to the small space and compact equipment layout of the offshore platform, the steep stairs between the floors, and the wheeled robots cannot climb the slope, and can only realize the inspection of this floor. If inspection robots are set up on each floor, there will be great challenges in terms of project cost and equipment maintenance. The second is the track-type robot, which is mainly used for the inspection of important rooms such as the main electrical switch room and the emergency switch room, real-time monitoring of equipment operation and uploading of key data. The track-mounted intelligent robot is equipped with a variety of sensors, such as temperature, humidity, air pressure, video, etc., which can provide real-time feedback on the operation and environmental conditions of electrical and instrumentation equipment, realize comprehensive detection of equipment and environment, and effectively reduce the workload of on-site personnel inspections, but it is limited to indoor inspections.

[0004] In recent years, with the emphasis on safety, video surveillance technology for offshore platforms has developed rapidly, and the number and types of cameras on offshore platforms have shown explosive growth. Platform video surveillance has achieved full coverage and has rich video data. However, the current video surveillance function is single and can only complete daily production monitoring and evidence collection functions. Some intelligent analysis software is mainly used for illegal intrusion and personnel behavior identification, and does not fully utilize video data and intelligent analysis methods to monitor and patrol the platform's abnormal status. At the same time, there are many cameras, and the pressure of personnel identification is high. Summary of the invention

[0005] In view of the above problems, the purpose of the present invention is to provide a method, system, medium and equipment for one-key intelligent video automatic inspection of unmanned offshore platforms, which can make full use of various types of existing cameras on offshore platforms, develop intelligent video analysis operators for industrial scenarios and multi-source data linkage algorithms, and build automatic inspection models. The present invention can also realize video linkage warning, timely locate production problems and safety hazards, improve inspection quality and efficiency; ensure the safe production of production facilities on unmanned offshore platforms, and reduce the frequency of unmanned platform personnel boarding for inspections.

[0006] To achieve the above-mentioned purpose, in the first aspect, the technical solution adopted by the present invention is: a one-key intelligent video automatic inspection method for an unmanned offshore platform, which comprises: obtaining the on-site video data of the inspection route in real time by various on-site video surveillance equipment deployed on the inspection route, performing intelligent video analysis according to different inspection contents on the inspection route, performing image detection to determine whether there are abnormal images, and alarming in abnormal state and sending work orders to the electronic work ticket system; matching the platform's fire and gas system, central control system and equipment abnormal alarm signals with nearby on-site video surveillance equipment by soft docking, reading the alarm signal equipment location information and linking the corresponding video surveillance equipment, performing video pop-up windows and alarms, and sending work orders to the electronic work ticket system; embedding the IP address of the on-site video surveillance equipment at each point of the platform's three-dimensional model, so as to view the operating status of the equipment at the specified location in real time through the platform's three-dimensional model, and alarming in abnormal state and sending work orders to the electronic work ticket system; conducting on-site abnormality inspection according to the abnormal state information received by the electronic work ticket system, and forming an inspection analysis report based on the inspection or maintenance results.

[0007] Furthermore, intelligent video analysis includes: remote meter reading, leakage monitoring, high temperature identification, oil spill monitoring, flame identification, gas leak identification and valve opening identification.

[0008] Further, image detection is performed to determine whether there is an abnormal image, including: Perform image recognition based on the results of intelligent video analysis, extract effective information from the image recognition results, and determine whether there is an abnormal state; After all video streams are analyzed, if there is no abnormality, the inspection is completed and an inspection analysis report is generated; If there is an alarm anomaly, the video stream of the corresponding video surveillance device is retrieved, and image frame recognition is continued for at least five consecutive time points to confirm the anomaly information again; If the abnormality is confirmed again, an alarm signal will be output and a work order will be sent to the electronic job ticket system.

[0009] In the second aspect, the technical solution adopted by the present invention is: a one-key intelligent video automatic inspection system for an unmanned offshore platform, the system comprising: an intelligent video inspection module, in which various types of on-site video surveillance equipment deployed on the inspection route obtain real-time on-site video data of the inspection route, perform intelligent video analysis according to different inspection contents on the inspection route, perform image detection to determine whether there are abnormal images, alarm in abnormal state and send work orders to the electronic work ticket system; a multi-source data linkage alarm module, which uses a soft docking method to match the platform's fire and gas system, central control system and equipment abnormal alarm signals with nearby on-site video surveillance equipment, reads the alarm signal equipment location information and links the corresponding video surveillance equipment, performs video pop-ups and alarms, and sends work orders to the electronic work ticket system; a real-scene mapping module, which embeds the IP address of the on-site video surveillance equipment at each point of the platform's three-dimensional model, so as to view the operating status of the equipment at the specified location in real time through the platform's three-dimensional model, alarm in abnormal state and send work orders to the electronic work ticket system; an inspection report module, which performs on-site abnormality investigation according to the abnormal state information received by the electronic work ticket system, and forms an inspection analysis report based on the investigation or maintenance results.

[0010] Furthermore, the intelligent video inspection module includes: various video surveillance equipment, video surveillance system, video analysis server, inspection management server, electronic work ticket system and inspection module display terminal; Various video surveillance devices store the real-time on-site video data on the inspection route in the storage unit of the video surveillance system; The inspection management server sends inspection instructions to the video analysis server regularly according to the set time; The video analysis server retrieves real-time video from the storage unit of the video surveillance system, divides the functions according to the inspection content of various video surveillance devices on the inspection route, and the video stream enters the corresponding intelligent analysis operator of the video analysis server for image recognition; After all video streams are analyzed, if there is no abnormality, the inspection is completed and an inspection analysis report is generated; if there is an alarm abnormality, the video stream of the corresponding video surveillance device is retrieved, and image frame recognition is continued for at least five consecutive time points to reconfirm the abnormal information; If the abnormality is confirmed again, an alarm signal will be output on the inspection management server, and a corresponding video window will pop up on the inspection module display terminal for manual confirmation; After manual confirmation, the work order is sent to the electronic work ticket system through the production network, and the inspection or maintenance results are uploaded to the inspection management server.

[0011] Furthermore, the multi-source data linkage alarm module includes: on-site instrument valves and other equipment, on-site fire and gas detection equipment, central control system, fire and gas system, OPC server and switch; On-site instrument valves and other equipment and on-site fire and gas detection equipment transmit the collected or monitored data to the central control system and fire and gas system for analysis and processing, and then transmit the central control and fire and gas alarm signals to the OPC server via the switch; The OPC server transmits the alarm signal to the inspection management server of the production network through the industrial control network; On the inspection management server, through soft docking, IP addresses of on-site instrument valves and other equipment, on-site fire and gas detection equipment and nearby video surveillance equipment are mapped to achieve alarm signal and video linkage between the central control system, each equipment status monitoring system, and fire and gas system; A video window corresponding to the alarm signal area pops up on the inspection module display terminal and is manually confirmed. After manual confirmation, the work order information is sent to the electronic work ticket system, and the troubleshooting or maintenance results are uploaded to the inspection management server to form an inspection analysis report.

[0012] Furthermore, a one-way isolation gateway and a protocol converter are deployed between the industrial control network and the production network; the OPC server transmits the alarm signal to the production network through the industrial control network and the one-way isolation gateway, and performs security control on the data interaction between networks through the one-way isolation gateway; the alarm signal is then converted to the IP / TCP protocol through the protocol converter and transmitted to the inspection management server.

[0013] Further, the reality mapping module includes a three-dimensional model of the platform; The platform's three-dimensional model is mapped to the video surveillance equipment through virtual and real scenes, and the IP address of the on-site video surveillance equipment is embedded in each point of the platform's three-dimensional model.

[0014] In a third aspect, the technical solution adopted by the present invention is: a computer-readable storage medium storing one or more programs, characterized in that 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.

[0015] 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.

[0016] The present invention adopts the above technical solution, which has the following advantages: 1. The one-key intelligent inspection system of the present invention constructs a full-process system of video data collection, intelligent analysis, and safety decision-making, realizes autonomous, regular, and full-process automatic inspection of offshore platforms, and provides safety protection for offshore platforms.

[0017] 2. The present invention can give full play to the one-key video inspection function on offshore oil and gas platforms, especially unmanned platforms, and can realize industrial scene video analysis operators, such as long-distance meter reading, personnel behavior monitoring, harmful gas detection, leakage detection, and intelligent early warning.

[0018] 3. The present invention can realize daily inspection of manned platforms and remote one-key video inspection of unmanned platforms, focus on industrial production processes, analyze the production status of platform production processes such as leakage in real time, quickly locate abnormal alarms, and greatly reduce the frequency of offshore platform inspections.

[0019] 4. The present invention realizes the linkage between the alarm signals and videos of the DCS system, the equipment status monitoring systems, and the fire and gas systems through soft docking. When an abnormality occurs, the video screen of the corresponding area will be automatically popped up for verification and confirmation, which greatly improves the efficiency of confirming the status of abnormal alarm points.

[0020] 5. The present invention is based on a video surveillance system, does not require high-cost hardware replacement, fully develops intelligent analysis operators, and realizes three-dimensional and virtual-real mapping to facilitate rapid search for videos in designated areas and conduct real-time viewing and monitoring of on-site production.

[0021] 6. The present invention establishes a complete closed-loop management mechanism, cooperates with the electronic work ticket, generates inspection reports, fault dispatch, maintenance, feedback to form fault cause analysis, and completes closed-loop management. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is an overall flow chart of the one-key intelligent video automatic inspection method for an unmanned offshore platform in an embodiment of the present invention; Figure 2 It is a schematic diagram of the overall structure of a one-key intelligent video automatic inspection system for an unmanned offshore platform in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to solve the problems of the existing video surveillance function being single, the video data and intelligent analysis means not being fully utilized for monitoring and patrolling the abnormal status of the platform, the large number of cameras, and the high pressure of personnel identification, the present invention provides a method, system, medium and equipment for automatic one-key intelligent video inspection of an unmanned offshore platform, which constructs a full-process system of video data acquisition, intelligent video analysis, and safety decision-making, and can give full play to the one-key video inspection function on the unmanned platform to realize long-distance meter reading, personnel behavior monitoring, harmful gas detection, leakage detection, and intelligent early warning. And through the soft docking method, multi-source alarm alarm signals and video linkage are realized, abnormal alarms are quickly located, and the frequency of offshore platform inspections is reduced. Inspection reports are generated and cooperated with electronic work tickets to establish a complete closed-loop management mechanism. The present invention can be widely used in remote one-key intelligent video inspections of unmanned offshore platforms.

[0024] The present invention formulates a video inspection route according to the on-site inspection content of the offshore unmanned platform, and builds a one-key intelligent video inspection model according to the inspection requirements, which mainly includes: inspection process and inspection logic mode, intelligent analysis algorithm, algorithm calling software, alarm conditions, sample library establishment and model training, etc. Different types of cameras are configured for key process pipelines, mechanical equipment, electrical equipment, instrument panels and cabinets, platform landing points, platform external transmission pipelines, and dangerous operation areas on the inspection route; track robots are configured in important electrical rooms. Relying on existing network communication facilities, with the help of front-end hardware equipment such as video monitoring systems and track robots, a comprehensive video data analysis and processing center is established, and the real-time video stream collected by the front-end hardware equipment is connected for intelligent analysis and processing. Intelligent video analysis mainly includes flame recognition, leakage monitoring, oil spill on the sea surface, abnormal status of instrument / electrical panels, important valve status monitoring, illegal placement, and failure to return the wellhead cover, etc. An alarm is issued in the abnormal state and a video screen pops up for manual review, and corresponding treatment measures are taken to realize the remote one-key intelligent video inspection function of the unmanned platform.

[0025] At the same time, combined with the third-party alarm data source, through multi-source data linkage identification, the DCS system, various online monitoring systems, fire and gas alarm signals and video linkage are realized, and the corresponding area video screen is automatically popped up for verification and confirmation when an abnormality occurs. After the linkage warning, the warning information is saved and the fault warning processing process is started. Through third-party alarm source information and video analysis, the preliminary cause of the fault or abnormality is predicted; and it is pushed to the operation and maintenance platform to give a maintenance strategy in combination with various monitoring data. And design three-dimensional and virtual-real mapping, and perform three-dimensional and real-scene mapping based on the video surveillance network topology structure, so as to facilitate the rapid search of the designated area video in daily or emergency situations.

[0026] 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.

[0027] 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.

[0028] In one embodiment of the present invention, Figure 1 As shown, a one-key intelligent video automatic inspection system for an unmanned offshore platform is provided, which includes: Intelligent video inspection module, which uses various video surveillance devices 6 deployed on the inspection route to obtain real-time on-site video data of the inspection route, conduct intelligent video analysis according to different inspection contents on the inspection route, perform image detection to determine whether there are abnormal images, and alarm when abnormal status occurs and send work orders to the electronic work ticket system; The multi-source data linkage alarm module matches the platform fire and gas system, central control system and equipment abnormal alarm signals with the nearby on-site video monitoring equipment 6 by soft docking, reads the alarm signal equipment location information and links the corresponding video monitoring equipment 6, performs video pop-up and alarm, and sends work orders to the electronic work ticket system 16; The real-scene mapping module embeds the IP address of the on-site video monitoring equipment at each point of the platform 3D model, so as to view the operating status of the equipment at the specified location in real time through the platform 3D model 15, and alarm when abnormal status occurs and send a work order to the electronic work ticket system; The inspection report module conducts on-site inspection of abnormalities based on the abnormal status information received by the electronic work ticket system 16, and forms an inspection analysis report based on the inspection or maintenance results, which is used to record the remote automatic video inspection analysis process and results, record the linkage alarm related information, and record the third-party monitoring data.

[0029] In the above embodiment, the video monitoring equipment 6 mainly includes a video network video recorder (NVR), a server, various cameras on site, etc. The cameras mainly include explosion-proof high-definition network cameras, thermal imaging cameras, infrared cameras, ultraviolet fluorescent oil spill monitoring cameras, etc.

[0030] In the above embodiment, in the intelligent video inspection module, the entire video stream is automatically inspected, and the inspection management server can issue inspection instructions at regular intervals, perform intelligent video analysis according to different inspection contents on the inspection route, and determine whether there is an abnormal state. In the event of an abnormal state, an alarm will be issued and a work order will be sent to the electronic job ticket system.

[0031] Specifically, the intelligent video inspection module includes: a production network 2, various video monitoring devices 6, a video monitoring system 5, a video analysis server 4, an inspection management server 3, an electronic work ticket system 16 and an inspection module display terminal 17; Various video surveillance devices 6 store the real-time acquired on-site video data of the inspection route in a storage unit (such as an NVR) of the video surveillance system 5; The inspection management server 3 sends inspection instructions to the video analysis server 4 according to the set time; The video analysis server 4 retrieves real-time video from the storage unit of the video surveillance system 5, divides the functions according to the inspection contents of various video surveillance devices 6 on the inspection route, and the video stream enters the corresponding intelligent analysis operator of the video analysis server 4 for image recognition.

[0032] After all video streams are analyzed, if there is no abnormality, the inspection is completed and an analysis report is formed; if there is an alarm abnormality, the video stream of the corresponding video monitoring device 6 is retrieved, and image frame recognition is continued for at least five consecutive time points to confirm the abnormal information again; If the abnormality is confirmed again, an alarm signal is outputted on the inspection management server 3, and a corresponding video window pops up on the inspection module display terminal 17 for manual confirmation; After manual confirmation, the work order is sent to the electronic work ticket system 16 via the production network 2, and the inspection or maintenance results are uploaded to the inspection management server 3.

[0033] In this embodiment, the intelligent analysis operator performs image recognition specifically by extracting, comparing, analyzing and identifying image features. The main identification and analysis contents of the intelligent analysis operator include: remote meter reading, leakage monitoring, high temperature identification, oil spill monitoring, flame identification, gas leakage identification and valve opening identification. For example, taking the valve leakage in the production process of an offshore platform as an example: the camera captures the real-time video image of the valve and transmits it to the video analysis server. After preprocessing, feature extraction is performed, such as the color, texture and shape features of the oil spill area, and further processing and analysis are performed through edge detection operators or convolutional neural networks to determine the leakage.

[0034] In the above embodiment, the multi-source data linkage alarm module includes: an industrial control network 1, field instrument valves and other equipment 12, field fire and gas detection equipment 14, a central control system 11, a fire and gas system 13, an OPC server 7 and a switch 8; The on-site instrument valves and other equipment 12 and the on-site fire and gas detection equipment 14 transmit the collected or monitored data to the central control system 11 and the fire and gas system 13 for analysis and processing, and then transmit the central control and fire and gas alarm signals to the OPC server 7 via the switch 8; The OPC server 7 transmits the alarm signal to the inspection management server 3 of the production network 2 through the industrial control network 1; On the inspection management server 3, through the soft docking method, the IP addresses of the on-site instrument valves and other equipment 12, the on-site fire and gas detection equipment 14 and the nearby video monitoring equipment 6 are mapped to realize the alarm signal and video linkage of the central control system 11, the equipment status monitoring system, and the fire and gas system 13; A video window corresponding to the alarm signal area pops up on the inspection module display terminal 17, and manual confirmation is performed. After manual confirmation, the work order information is sent to the electronic work ticket system 16, and the inspection or maintenance results are uploaded to the inspection management server 3 to form an inspection analysis report.

[0035] In this embodiment, a one-way isolation gateway 9 and a protocol converter 10 are deployed between the industrial control network 1 and the production network 2; the OPC server 7 transmits the alarm signal to the production network 2 through the industrial control network 1 and the one-way isolation gateway 9, and performs security control on the data interaction between the networks through the one-way isolation gateway 9; the alarm signal is then converted into the IP / TCP protocol through the protocol converter 10 and transmitted to the inspection management server 3.

[0036] In this embodiment, the multi-source data mainly includes abnormal alarm data of field instrument sensing, valve monitoring, and fire and gas detection in the industrial control network, and abnormal temperature and pressure alarm data of equipment and pipeline monitoring in the production network.

[0037] In this embodiment, the OPC server 7 transmits the abnormal alarm data after protocol conversion to the inspection management server, and uses software to map the IP addresses of monitoring equipment such as field probes, transmitters, valves and other equipment with nearby cameras to achieve accurate pop-up windows for alarm linkage.

[0038] In the above embodiment, the real scene mapping module includes a platform three-dimensional model 15; the platform three-dimensional model 15 performs virtual-real scene mapping with the video surveillance device 6, and the IP address of the on-site video surveillance device 6 is embedded in each point of the platform three-dimensional model.

[0039] In the above embodiment, the electronic work ticket system 16 receives abnormal inspection information through wireless / wired communication, performs standardized management of the abnormal inspection information, and promptly delivers personnel work orders.

[0040] In one embodiment of the present invention, a one-key intelligent video automatic inspection method for an unmanned offshore platform is provided. In this embodiment, the inspection task is decomposed into three major functions: one-key intelligent video inspection, linkage alarm, and real-scene mapping. Figure 2As shown, the method comprises the following steps: 1) Intelligent video inspection: Various video surveillance devices deployed on the inspection route obtain the on-site video data of the inspection route in real time, conduct intelligent video analysis according to the different inspection contents on the inspection route, perform image detection, determine whether there are abnormal images, and alarm and send work orders to the electronic work ticket system in case of abnormal status. If there are no abnormal images, an inspection analysis report is generated; Among them, intelligent video analysis includes remote meter reading, leakage monitoring, high temperature identification, oil spill monitoring, flame identification, gas leak identification and valve opening identification.

[0041] 2) Multi-source data linkage alarm: The platform's fire and gas system, central control system and equipment abnormal alarm signals are matched with nearby on-site video surveillance equipment through soft docking to achieve the alarm signal and video linkage of the central control system, each equipment status monitoring system, and fire and gas system, read the location information of the alarm signal equipment and link it with the corresponding video surveillance equipment, display video pop-ups and alarms, and send work orders to the electronic work ticket system.

[0042] 3) Real-scene mapping: The IP address of the on-site video surveillance equipment is embedded in each point of the platform's 3D model, so that the operating status of the equipment at the specified location can be quickly viewed in real time through the platform's 3D model. In case of abnormal status, an alarm will be issued and a work order will be sent to the electronic job ticket system.

[0043] 4) Inspection report: Conduct on-site inspection of abnormalities based on the abnormal status information received from the electronic work ticket system, and form an inspection analysis report based on the inspection or maintenance results.

[0044] In the above step 1), image detection is performed to determine whether there is an abnormal image, including the following steps: 1.1) Perform image recognition based on the results of intelligent video analysis, extract effective information from the image recognition results, and determine whether there is an abnormal state; 1.2) After all video streams are analyzed, if there is no abnormality, the inspection is completed and an inspection analysis report is generated; 1.3) If there is an alarm anomaly, the video stream of the corresponding video surveillance device is retrieved, and image frame recognition is continued for at least five consecutive time points to confirm the anomaly information again; 1.4) If the abnormality is confirmed again, an alarm signal will be output and a work order will be sent to the electronic work ticket system.

[0045] In summary, the present invention aims at the characteristics of unmanned platforms, builds an automatic video inspection module based on video surveillance hardware equipment and multi-source alarm data, and realizes remote automatic video inspection and alarm linkage.

[0046] The method provided in this embodiment is based on the above-mentioned system embodiments. Please refer to the above-mentioned embodiments for specific processes and detailed contents, which will not be repeated here.

[0047] A computing device provided in one embodiment of the present invention may be a terminal, which may include: a processor, a communications interface, a memory, a display screen, and an input device. Among them, the processor, the communications 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, wherein the non-volatile storage medium stores an operating system and a computer program, and the computer program is executed by the processor to implement the methods in the above embodiments; 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 industrial WIFI, industrial 5G 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.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] 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.

[0053] 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 comprising 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.

[0054] 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.

[0055] 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 one-key intelligent video automatic inspection method for an offshore unmanned platform, characterized in that: include: Various video surveillance devices deployed on the inspection route acquire the on-site video data of the inspection route in real time, conduct intelligent video analysis according to the different inspection contents on the inspection route, detect images to determine whether there are abnormal images, and alarm when there is an abnormal state and send a work order to the electronic work ticket system; Use software docking to match the platform's fire and gas system, central control system, and equipment abnormal alarm signals with nearby on-site video surveillance equipment, read the alarm signal equipment location information, and link the corresponding video surveillance equipment to display video pop-ups and alarms, and send work orders to the electronic work ticket system; The IP address of the on-site video surveillance equipment is embedded in each point of the platform's 3D model, so that the operating status of the equipment at the specified location can be viewed in real time through the platform's 3D model. In case of abnormal status, an alarm will be issued and a work order will be sent to the electronic work ticket system; Conduct on-site inspections of abnormalities based on abnormal status information received from the electronic work ticket system, and generate inspection and analysis reports based on the inspection or maintenance results.

2. The one-key intelligent video automatic inspection method for an unmanned offshore platform as claimed in claim 1, characterized in that: Intelligent video analysis includes: remote meter reading, leakage monitoring, high temperature identification, oil spill monitoring, flame identification, gas leak identification and valve opening identification.

3. The one-key intelligent video automatic inspection method for an unmanned offshore platform as claimed in claim 1 is characterized in that: Perform image detection to determine whether there are abnormal images, including: Perform image recognition based on the results of intelligent video analysis, extract effective information from the image recognition results, and determine whether there is an abnormal state; After all video streams are analyzed, if there is no abnormality, the inspection is completed and an inspection analysis report is generated; If there is an alarm anomaly, the video stream of the corresponding video surveillance device is retrieved, and image frame recognition is continued for at least five consecutive time points to confirm the anomaly information again; If the abnormality is confirmed again, an alarm signal will be output and a work order will be sent to the electronic job ticket system.

4. A one-key intelligent video automatic inspection system for unmanned offshore platforms, characterized in that: The system includes: The intelligent video inspection module uses various video surveillance devices deployed on the inspection route to obtain real-time on-site video data of the inspection route, conduct intelligent video analysis according to different inspection contents on the inspection route, detect images to determine whether there are abnormal images, and alarm when abnormal status occurs and send work orders to the electronic work ticket system; The multi-source data linkage alarm module matches the platform's fire and gas system, central control system and equipment abnormal alarm signals with nearby on-site video surveillance equipment through soft docking, reads the alarm signal equipment location information and links the corresponding video surveillance equipment to display video pop-ups and alarms, and sends work orders to the electronic work ticket system; The real-scene mapping module embeds the IP address of the on-site video surveillance equipment at each point of the platform's 3D model, so as to view the operating status of the equipment at the specified location in real time through the platform's 3D model, and alarm when an abnormal state occurs and send a work order to the electronic work ticket system; The inspection report module conducts on-site inspection of abnormalities based on the abnormal status information received from the electronic work ticket system, and generates an inspection analysis report based on the inspection or maintenance results.

5. The one-key intelligent video automatic inspection system for unmanned offshore platforms as claimed in claim 4 is characterized in that: The intelligent video inspection module includes: various video surveillance equipment, video surveillance system, video analysis server, inspection management server, electronic operation ticket system and inspection module display terminal; Various video surveillance devices store the real-time on-site video data on the inspection route in the storage unit of the video surveillance system; The inspection management server sends inspection instructions to the video analysis server regularly according to the set time; The video analysis server retrieves real-time video from the storage unit of the video surveillance system, divides the functions according to the inspection content of various video surveillance devices on the inspection route, and the video stream enters the corresponding intelligent analysis operator of the video analysis server for image recognition; After all video streams are analyzed, if there is no abnormality, the inspection is completed and an inspection analysis report is generated; if there is an alarm abnormality, the video stream of the corresponding video surveillance device is retrieved, and image frame recognition is continued for at least five consecutive time points to reconfirm the abnormal information; If the abnormality is confirmed again, an alarm signal will be output on the inspection management server, and a corresponding video window will pop up on the inspection module display terminal for manual confirmation; After manual confirmation, the work order is sent to the electronic work ticket system through the production network, and the inspection or maintenance results are uploaded to the inspection management server.

6. The one-key intelligent video automatic inspection system for unmanned offshore platforms as claimed in claim 4 is characterized in that: The multi-source data linkage alarm module includes: on-site instrument valves and other equipment, on-site fire and gas detection equipment, central control system, fire and gas system, OPC server and switch; On-site instrument valves and other equipment and on-site fire and gas detection equipment transmit the collected or monitored data to the central control system and fire and gas system for analysis and processing, and then transmit the central control and fire and gas alarm signals to the OPC server via the switch; The OPC server transmits the alarm signal to the inspection management server of the production network through the industrial control network; On the inspection management server, through soft docking, IP addresses of on-site instrument valves and other equipment, on-site fire and gas detection equipment and nearby video surveillance equipment are mapped to achieve alarm signal and video linkage between the central control system, each equipment status monitoring system, and fire and gas system; A video window corresponding to the alarm signal area pops up on the inspection module display terminal and is manually confirmed. After manual confirmation, the work order information is sent to the electronic work ticket system, and the troubleshooting or maintenance results are uploaded to the inspection management server to form an inspection analysis report.

7. The one-key intelligent video automatic inspection system for unmanned offshore platforms as claimed in claim 6 is characterized in that: A one-way isolation gateway and a protocol converter are deployed between the industrial control network and the production network. The OPC server transmits the alarm signal to the production network through the industrial control network and the one-way isolation gateway, and performs security control on the data interaction between networks through the one-way isolation gateway. The alarm signal is then converted to the IP / TCP protocol through the protocol converter and transmitted to the inspection management server.

8. The one-key intelligent video automatic inspection system for unmanned offshore platforms as claimed in claim 4 is characterized in that: The reality mapping module includes a three-dimensional model of the platform; The platform's three-dimensional model is mapped to the video surveillance equipment through virtual and real scenes, and the IP address of the on-site video surveillance equipment is embedded in each point of the platform's three-dimensional model.

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 3.

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 3.

Images