Power inspection operation robot anti-misoperation system and method based on video analysis

Abstract

The invention discloses an electric power inspection operation robot anti-misoperation system and method based on video analysis, and relates to the technical field of electric power equipment, and the system comprises an inspection robot which is used for collecting first real-time state data of to-be-operated equipment, and executing an operation instruction issued by a user; the video acquisition module is used for acquiring second real-time state data of the equipment to be operated; the data acquisition and monitoring control module is used for acquiring third real-time state data of the equipment to be operated; and the main control module is used for judging whether equipment state data fed back by the first real-time state data, the second real-time state data and the third real-time state data are consistent or not, and controlling the inspection robot to execute a corresponding operation instruction when the equipment state data are consistent. The situation of misoperation of the inspection robot is avoided, and therefore stable operation of a power system is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment, and particularly to an anti-misoperation operating system and method for a power inspection operation robot based on video analysis. Background Art

[0002] During the operation and maintenance of a substation, the traditional operation method is to perform opening and closing operations manually. However, manual operation has poor timeliness for emergency opening operations, and there is an explosion risk during emergency opening operations, endangering personal safety. In recent years, power inspection operation robots have been quite common, but there is still a possibility of misoperation when using a power inspection operation robot to operate a switch cabinet. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide an anti-misoperation operating system and method for a power inspection operation robot based on video analysis.

[0004] To solve the above technical problems, the technical solution of the present invention is as follows: An anti-misoperation operating system for a power inspection operation robot based on video analysis, comprising: An inspection robot, configured to collect first real-time status data of a device to be operated and execute an operation instruction issued by a user; A video acquisition module, configured to collect second real-time status data of the device to be operated at a construction site; A data acquisition and supervisory control module, configured to obtain third real-time status data of the device to be operated; A main control module, receiving the first real-time status data, the second real-time status data, and the third real-time status data, and determining whether the device status data fed back by the first real-time status data, the second real-time status data, and the third real-time status data is consistent, and controlling the inspection robot to execute the corresponding operation instruction when they are consistent.

[0005] As a preferred solution of the anti-misoperation operating system for a power inspection operation robot based on video analysis of the present invention, wherein: the main control module includes: A human-computer interaction module, configured to display an operation interface of the inspection robot to a user and perform data interaction with the inspection robot; A streaming media module, configured to analyze the received first real-time status data, second real-time status data, and third real-time status data; And a video analysis module, configured to analyze the device status corresponding to the first real-time status data, the second real-time status data, and the third real-time status data.

[0006] As a preferred solution of the anti-misoperation system for the power inspection operation robot based on video analysis according to the present invention, wherein: the video analysis module is used to analyze the device states corresponding to the first real-time state data, the second real-time state data, and the third real-time state data by using a deep residual network (ResNet) model.

[0007] As a preferred solution of the anti-misoperation system for the power inspection operation robot based on video analysis according to the present invention, wherein: the communication protocol between the main control module and the inspection robot is http, and both the data requests and responses between the main control module and the inspection robot are encapsulated as strings in JSON format, with the encoding method being UTF-8 and the request submission method being GET or POST.

[0008] The present invention also provides an anti-misoperation method for a power inspection operation robot based on video analysis, including: Controlling the inspection robot to move to a specified position for inspection operations; Controlling the inspection robot to obtain the first real-time video data of the corresponding device, and calling the on-site camera device to collect the second real-time video data of the corresponding device; Based on the first real-time video data and the second real-time video data, analyzing to obtain the first real-time state data and the second real-time state data of the corresponding device, and obtaining the third real-time state data of the corresponding device through a data acquisition and monitoring control system; Judging whether the device state data fed back by the first real-time state data, the second real-time state data, and the third real-time state data are consistent. If they are consistent, controlling the inspection robot to execute the corresponding operation instructions.

[0009] As a preferred solution of the anti-misoperation method for the power inspection operation robot based on video analysis according to the present invention, wherein: the controlling the inspection robot to obtain the first real-time video data of the corresponding device includes: Controlling the camera component carried by the inspection robot to collect the first real-time video data of the corresponding device.

[0010] As a preferred solution of the anti-misoperation method for the power inspection operation robot based on video analysis according to the present invention, wherein: after judging whether the device state data fed back by the first real-time state data, the second real-time state data, and the third real-time state data are consistent. If they are consistent, controlling the inspection robot to execute the corresponding operation instructions, it further includes: If they are inconsistent, the user is to judge whether to control the inspection robot to execute the corresponding operation instructions.

[0011] The beneficial effects of the present invention are: The present invention collects the first real-time video data of on-site equipment through a camera component carried by an inspection robot, collects the second real-time video data of corresponding equipment through on-site monitoring equipment, analyzes the first real-time video data and the second real-time video data, parses out the status data corresponding to the equipment, and then combines the equipment status data uploaded by the data acquisition and monitoring control module to determine whether the three are consistent. When they are consistent, it controls the inspection robot to execute corresponding operation instructions, avoiding misoperation of the inspection robot, thereby ensuring the stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0013] Figure 1 It is a schematic diagram of an anti-misoperation system for a power inspection operation robot based on video analysis provided by the present invention; Figure 2 It is a schematic flow diagram of an anti-misoperation method for a power inspection operation robot based on video analysis provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] To make the content of the present invention easier to be clearly understood, the present invention will be further described in detail below according to the specific embodiments and in combination with the drawings.

[0015] Figure 1 It is a schematic diagram of an anti-misoperation system for a power inspection operation robot based on video analysis provided by an embodiment of the present application. The system includes an inspection robot, a video acquisition module, a data acquisition and monitoring control module, and a main control module.

[0016] Specifically, the inspection robot can be used in the high-voltage switchgear room of a substation, can be accurately positioned according to the scheduling tasks of the robot background system, execute the control instructions issued by the background system, and complete operations such as switching on and off power for switch cabinets, emergency tripping and closing, conventional switching operations, and conventional inspection operations of on-site equipment.

[0017] It should be noted that a high-definition camera component is carried on the inspection robot. When the inspection robot executes the operation instructions of the background system or performs conventional inspection operations, it can obtain the real-time video data of on-site equipment through the high-definition camera component. In this embodiment, the real-time video data obtained by the inspection robot is used as the first real-time status data.

[0018] The video acquisition module includes an infrared camera assembly set on-site, which can collect video data of on-site devices in real time. In this embodiment, the video data of on-site devices collected by the video acquisition module is used as the second real-time status data.

[0019] The data acquisition and supervisory control module (SCADA system module) is used to upload the status remote signaling data of on-site devices to the main control module. In this embodiment, the status remote signaling data of on-site devices collected by the data acquisition and supervisory control module is used as the third real-time status data.

[0020] The main control module is used to provide an operable graphical interface for users and interact with the background system of the inspection robot. Specifically, see Figure 1 , the main control module includes a human-computer interaction module, a streaming media module, and a video analysis module. Among them, the human-computer interaction module is used to display the operation interface of the inspection robot to users and interact with the background system of the inspection robot.

[0021] The streaming media module is used to parse the received first real-time status data, second real-time status data, and third real-time status data. The video analysis module is used to analyze the device status corresponding to the first real-time status data, second real-time status data, and third real-time status data.

[0022] In this embodiment, the communication protocol between the human-computer interaction module and the background system of the inspection robot is http. Both data requests and response returns are encapsulated as strings in JSON format, and the encoding method is uniformly UTF-8. The requests are submitted using the GET or POST method. The human-computer interaction module sends GET or POST commands to the robot background system to control the inspection robot to perform relevant operations and receive the JSON format data actively uploaded by the robot background system to parse the device status. The streaming media module supports multiple real-time streaming media protocols such as RTMP / WebRTC and can parse the video streams collected by the infrared camera assembly in the video acquisition module and the high-definition camera assembly carried by the inspection robot in real time. The video analysis module uses a deep residual network (ResNet) model to analyze the real-time status of the in-site devices.

[0023] After the main control module receives the first real-time status data of the corresponding device uploaded by the background system of the inspection robot, the second real-time status data of the corresponding device uploaded by the video acquisition module, and the third real-time status data of the corresponding device uploaded by the SCADA system, it judges whether the device status data fed back after parsing the first real-time status data, second real-time status data, and third real-time status data is consistent. If it is consistent, it controls the inspection robot to execute the corresponding operation instruction; if it is inconsistent, it is up to the user to judge whether to control the inspection robot to execute the corresponding operation instruction.

[0024] Figure 2Schematic flowchart of the anti-misoperation method for a power inspection operation robot based on video analysis provided by an embodiment of this application. The method specifically includes the following steps: Step S101: Control the inspection robot to move to a specified position for inspection operations.

[0025] Specifically, the user issues an operation instruction for the inspection robot through the main control module. The main control module sends a POST request to the inspection robot background system through the API interface. The inspection robot background system issues a command to the inspection operation robot, causing the inspection operation robot to go to the corresponding position for inspection operations.

[0026] Step S102: Control the inspection robot to obtain the first real-time video data of the corresponding device, and call the on-site camera device to collect the second real-time video data of the corresponding device.

[0027] Specifically, the inspection robot background system collects the real-time images and video data of the corresponding device through the high-definition camera carried by the inspection robot itself, and uses it as the first real-time video data. At the same time, the main control module calls the video acquisition module, controls the infrared camera component to move to the corresponding preset position, and collects the video data of the corresponding device, which is used as the second real-time video data.

[0028] Step S103: Analyze the first real-time state data and the second real-time state data of the corresponding device based on the first real-time video data and the second real-time video data, and obtain the third real-time state data of the corresponding device through the data acquisition and monitoring control system.

[0029] Specifically, the main control module analyzes the first real-time video data and the second real-time video data through the video analysis module, parses the corresponding device state data, and receives the corresponding device state data fed back by the third real-time state data uploaded by the data acquisition and monitoring control system.

[0030] Step S104: Determine whether the device state data fed back by the first real-time state data, the second real-time state data, and the third real-time state data is consistent. If it is consistent, control the inspection robot to execute the corresponding operation instruction.

[0031] Specifically, when the device state information uploaded by the inspection robot, the video acquisition module, and the data acquisition and monitoring control module is consistent, the control instruction issued by the user is executed; if the states of the three are inconsistent, it is left to the user to comprehensively judge whether to execute the operation command.

[0032] Therefore, the technical solution of this application collects the first real-time video data of on-site equipment through the camera component carried by the inspection robot, collects the second real-time video data of the corresponding equipment through the on-site monitoring equipment, analyzes the first real-time video data and the second real-time video data, parses out the status data corresponding to the equipment, and then combines the equipment status data uploaded by the data acquisition and monitoring control module to determine whether the three are consistent. When they are consistent, the inspection robot is controlled to execute the corresponding operation instructions, avoiding the situation of misoperation of the inspection robot, thereby ensuring the stable operation of the power system.

[0033] In addition to the above embodiments, the present invention may have other embodiments; all technical solutions formed by equivalent replacement or equivalent transformation fall within the protection scope required by the present invention.

Claims

1. An anti-misoperation operating system for a power inspection operation robot based on video analysis, characterized in that: Including: An inspection robot, which is used to collect the first real-time status data of the equipment to be operated and execute the operation instructions issued by the user; A video acquisition module, which is used to collect the second real-time status data of the equipment to be operated at the construction site; A data acquisition and supervisory control module, which is used to obtain the third real-time status data of the equipment to be operated; A main control module, which is used to receive the first real-time status data, the second real-time status data, and the third real-time status data, and judge whether the equipment status data fed back by the first real-time status data, the second real-time status data, and the third real-time status data is consistent, and when they are consistent, control the inspection robot to execute the corresponding operation instructions.

2. The anti-misoperation operating system for the power inspection operation robot based on video analysis according to claim 1, wherein: The main control module includes: A human-computer interaction module, which is used to display the operation interface of the inspection robot to the user and perform data interaction with the inspection robot; A streaming media module, which is used to analyze the received first real-time status data, second real-time status data, and third real-time status data; And a video analysis module, which is used to analyze the equipment status corresponding to the first real-time status data, the second real-time status data, and the third real-time status data.

3. The anti-misoperation operating system of the power inspection operation robot based on video analysis according to claim 2, characterized in that: The video analysis module is used to analyze the equipment status corresponding to the first real-time status data, the second real-time status data, and the third real-time status data by using a deep residual network (ResNet) model.

4. The anti-misoperation operating system for the power inspection operation robot based on video analysis according to claim 1, wherein: The communication protocol between the main control module and the inspection robot is http. The data requests and responses between the main control module and the inspection robot are both encapsulated as strings in JSON format, the encoding method is UTF-8, and the request submission method is GET or POST.

5. A method for preventing misoperation of a power inspection operation robot based on video analysis, characterized in that: Including: Controlling the inspection robot to move to a specified position for inspection operations; Controlling the inspection robot to obtain the first real-time video data of the corresponding equipment and calling the on-site camera device to collect the second real-time video data of the corresponding equipment; Analyzing the first real-time status data and the second real-time status data of the corresponding equipment based on the first real-time video data and the second real-time video data, and obtaining the third real-time status data of the corresponding equipment through the data acquisition and supervisory control system; Judging whether the equipment status data fed back by the first real-time status data, the second real-time status data, and the third real-time status data is consistent. If it is consistent, control the inspection robot to execute the corresponding operation instructions.

6. The anti-misoperation method for a power inspection operation robot based on video analysis according to claim 5, characterized in that: The controlling the inspection robot to obtain the first real-time video data of the corresponding equipment includes: Controlling the camera component carried by the inspection robot to collect the first real-time video data of the corresponding equipment.

7. The method for preventing misoperation of a power inspection operation robot based on video analysis according to claim 5, characterized in that: After judging whether the equipment status data fed back by the first real-time status data, the second real-time status data, and the third real-time status data is consistent, and if it is consistent, controlling the inspection robot to execute the corresponding operation instructions, it further includes: If it is inconsistent, it is up to the user to judge whether to control the inspection robot to execute the corresponding operation instructions.

Images