Transformer substation operation behavior intelligent management and control system and method, storage medium and electronic equipment

Abstract

The invention discloses an intelligent substation operation behavior management and control system and method, a storage medium and electronic equipment, and the system comprises an information collection unit, an intelligent analysis unit, a centralized control management unit and a 3D electronic perimeter which is digitally set for an operation site. The intelligent analysis unit is composed of an intelligent analysis device with a preset fixed algorithm, a system safety device and a wireless or wired transmitter. According to the invention, through 3D electronic perimeter intelligent identification of substation field personnel working in a specified range, omnibearing video acquisition and analysis are carried out based on real-time scene content in a perimeter range; collected data are continuously compared and judged with unstable operation and illegal operation behavior models in a preset algorithm database in real time through an intelligent AI video algorithm, real-time online intelligent analysis, judgment, alarm and snapshot archiving of operation behaviors are achieved, and intelligentization and automation of an operation behavior monitoring system are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field, and in particular to a system, method, storage medium and electronic equipment for intelligent management and control of substation operation behavior. Background Art

[0002] At present, the current control methods for operating behaviors in substations are mainly on-site control and remote control. Among them, the on-site control method is subject to the influence of the number of supervisors and the supervision period, and cannot realize full-time personnel supervision of multiple operating surfaces in the entire station area. At this stage, the remote control method mostly uses fixed or semi-fixed cameras and other recording equipment to transmit the working site conditions to the remote observation background, and the supervisors in the observation background monitor, inspect and guide the on-site operating behaviors. The entire control system can only realize the functions of remote observation, remote analysis and video capture. Discovering and standardizing operating behaviors still requires real-time observation by background supervisors. There are also inherent problems such as large workload of background personnel, inability to cover all operating periods in real time, and inability to correct unstable operating behaviors in real time. For real-time correction of safety control, the immediate prohibition requirement has a large deviation in execution.

[0003] Looking at the power infrastructure, technical transformation and maintenance operations involved in substations, the requirements for safety control of operating behaviors are constantly increasing, and the requirements for process control are developing in the direction of "real-time and comprehensiveness". At this stage, the video control system has a lot of room for improvement in terms of advancement and intelligence, so it is imperative to give the video surveillance system intelligent functions. Summary of the invention

[0004] The purpose of the present invention is to provide a substation operation behavior intelligent management and control system, method, storage medium and electronic equipment, which can realize the intelligence and automation of the operation behavior monitoring system.

[0005] The technical solution adopted by the present invention is:

[0006] An intelligent control system for substation operation behavior, including an information collection unit, an intelligent analysis unit, a centralized control management unit and a 3D electronic perimeter, wherein the 3D electronic perimeter is a digital setting for the operation site;

[0007] The information collection unit is used to collect real-time operation information at the operation site and receive feedback information from the intelligent analysis unit; it is specifically composed of a control ball, a camera, a drone, an audible and visual alarm, a wireless or wired transmitter, and a low-voltage power supply;

[0008] The intelligent analysis unit is used to perform real-time visual AI algorithm analysis on the collected video images, conduct real-time and uninterrupted tracking and analysis on the operation area and operation behavior information flow, automatically determine whether the relevant information conforms to the action logic in the preset model library through AI intelligence, and trigger sound and light alarms to warn the operation site of the judgment results of unstable operation and illegal operation in real time, and simultaneously capture and record and upload to the centralized control management terminal; it is specifically composed of an intelligent analysis device with a preset fixed algorithm, a system safety device, and a wireless or wired transmitter;

[0009] The centralized control management unit is used to receive information from multiple different intelligent analysis devices, and centrally feed it back to the centralized control platform for rear management personnel to grasp the real-time situation of different work sites.

[0010] A control method based on the intelligent control system for substation operation behavior comprises the following steps: Step 1: creating a 3D electronic perimeter;

[0011] Step 2: Monitor the image within the 3D electronic perimeter through the information acquisition unit,

[0012] Step 3: The centralized control management unit analyzes the image within the 3D electronic perimeter and determines the position and action logic; if it meets the set requirements, continue, otherwise send a signal to the centralized control management unit; Step 4: After receiving the signal, the centralized control management unit performs actions such as alarm, snapshot, and archiving to complete automatic monitoring.

[0013] The step 1 specifically includes the following steps:

[0014] Step 1.1, detection of skeleton points of the monitoring device and estimation of the camera pose;

[0015] Step 1.2, detecting the observed target: using the target detection algorithm to obtain the two-dimensional area where the observed target of the current screen is located;

[0016] Step 1.3, target feature point matching and 3D position determination: Use the ORB algorithm to extract all camera image feature points, then use PROSAC to match the feature points and eliminate mismatched points.

[0017] The step 1.1 comprises the following steps:

[0018] Step 1.1.1, first use a target detection algorithm such as the YOLOv7 algorithm to detect the mobile device, then use a skeleton point detection model such as HRNET to detect the skeleton points of the mobile device, and obtain the two-dimensional coordinates of the skeleton points of the mobile device in the pixel coordinate system.

[0019] Step 1.1.2, establish a world coordinate system based on the mobile device, and determine the three-dimensional coordinates of the skeleton points of the mobile device in the world coordinate system,

[0020] Step 1.1.3, use the PnP or Perspective-n-Point method to solve the 3D to 2D point motion: when n 3D space points, i.e. the world coordinate system and their projection positions are known, the rotation and translation matrix is ​​used to estimate the camera's posture.

[0021] The camera projection relationship in step 1.1.3 is as follows:

[0022]

[0023] Among them, z c is the distance depth coefficient, u d 、v d is the pixel coordinate point, f cx 、f cy is the focal length of the camera, d x d y is the physical length of a pixel, u 0 、v 0 is the intersection of the camera optical axis and the image plane, x w ,y w 、z w is the world coordinate point, R and T are the image rotation and translation matrices.

[0024] In the step 1.3, feature matching point pairs are extracted in the two-dimensional area where the target is located, and the three-dimensional position of the target is calculated using the triangulation principle based on the feature matching point pairs of the target; a pair of corresponding pixel homogeneous coordinates of the three-dimensional space point formed by the left and right cameras, and two back-projected rays formed by the image point intersect at one point in space, and the intersection point is the three-dimensional coordinate corresponding to the two pixel points.

[0025] A computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the device where the computer-readable storage medium is located executes the intelligent control method for substation operation behavior as described in any one of claims 1.

[0026] An electronic device comprises: a memory and a processor, wherein the memory stores a program that can be run on the processor, and when the processor executes the program, the intelligent control method for substation operation behavior as described in any one of claims 1 to 7 is implemented.

[0027] The present invention implements research on "3D electronic perimeter intelligent identification" for substation on-site personnel working within a specified range. It will conduct all-round video acquisition and analysis based on the real-time scene content within the perimeter, and use intelligent AI video algorithms to continuously compare and judge the collected data in real time with the unstable operation and illegal operation behavior models in the predetermined algorithm database, thereby realizing real-time online intelligent analysis, judgment, alarm and snapshot archiving of the operation behavior, transforming the background "passive monitoring" into the on-site "active warning", and realizing the intelligence and automation of the operation behavior monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 A schematic diagram of establishing a 3D electronic perimeter of the present invention;

[0030] Figure 2 is a system structure diagram of the present invention;

[0031] Figure 3 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] like Figure 1 , 2 As shown in 3, the present invention includes an information collection unit, an intelligent analysis unit, a centralized control management unit and a 3D electronic perimeter, and the 3D electronic perimeter is a digital setting for the operation site;

[0034] The information collection unit is used to collect real-time operation information at the operation site and receive feedback information from the intelligent analysis unit; it is specifically composed of a control ball, a camera, a drone, an audible and visual alarm, a wireless or wired transmitter, and a low-voltage power supply;

[0035] The intelligent analysis unit is used to perform real-time visual AI algorithm analysis on the collected video images, conduct real-time and uninterrupted tracking and analysis on the operation area and operation behavior information flow, automatically determine whether the relevant information conforms to the action logic in the preset model library through AI intelligence, and trigger sound and light alarms to warn the operation site of the judgment results of unstable operation and illegal operation in real time, and simultaneously capture and record and upload to the centralized control management terminal; it is specifically composed of an intelligent analysis device with a preset fixed algorithm, a system safety device, and a wireless or wired transmitter;

[0036] The centralized control management unit is used to receive information from multiple different intelligent analysis devices, and centrally feed back to the centralized control platform for rear management personnel to grasp the real-time situation of different work sites; this part can be a project management and control platform for a construction site, or it can be a management and control platform for a company to control the information of multiple project departments.

[0037] When the present invention is actually used, the operation area is first defined according to the safety distance requirements of the power grid operation and equipment protection, and the coordinate system of the system is established according to the collection of the actual coordinate position on site. According to the established coordinate system, two-dimensional planes in different directions of the operation surface are delineated ( Figure 1 The six planes form a three-dimensional operation area (see the schematic diagram of 3D electronic perimeter intelligent establishment). Figure 1 ).

[0038] The present invention collects real-time video information, continuously compares and analyzes the information flow inside and outside the electronic perimeter in real time, and determines the violation of the information flow that exceeds the electronic perimeter, thereby achieving the fixed scope of the operation area and the standardization of operation behavior. The visual algorithm mainly studies the composition of video information, and uses the spatial recording and comparison of the data before and after the information flow to complete the intelligent analysis. The main theoretical calculations involved include information decoding, information solidification and information comparison.

[0039] A control method based on the intelligent control system for substation operation behavior according to claim 1,

[0040] Step 1: Create a 3D electronic perimeter;

[0041] Step 2: Monitor the image within the 3D electronic perimeter through the information acquisition unit,

[0042] Step 3: The centralized control management unit analyzes the image within the 3D electronic perimeter and determines the position and action logic; if it meets the set requirements, continue, otherwise send a signal to the centralized control management unit; Step 4: After receiving the signal, the centralized control management unit performs actions such as alarm, snapshot, and archiving to complete automatic monitoring.

[0043] The step 1 specifically includes the following steps:

[0044] Step 1.1, detection of skeleton points of the monitoring device and estimation of the camera posture; the step 1.1 comprises the following steps:

[0045] Step 1.1.1, first use a target detection algorithm such as the YOLOv7 algorithm to detect the mobile device, then use a skeleton point detection model such as HRNET to detect the skeleton points of the mobile device, and obtain the two-dimensional coordinates of the skeleton points of the mobile device in the pixel coordinate system.

[0046] Step 1.1.2, establish a world coordinate system based on the mobile device, and determine the three-dimensional coordinates of the skeleton points of the mobile device in the world coordinate system,

[0047] Step 1.1.3, use the PnP or Perspective-n-Point method to solve the 3D to 2D point motion: when n 3D space points, i.e. the world coordinate system and their projection positions are known, the rotation and translation matrix is ​​used to estimate the camera's posture.

[0048] The camera projection relationship in step 1.1.3 is as follows:

[0049]

[0050] Among them, z c is the distance depth coefficient, u d 、v d is the pixel coordinate point, f cx 、f cy is the focal length of the camera, d x ,d y is the physical length of a pixel, u 0 、v 0 is the intersection of the camera optical axis and the image plane, x w ,y w 、z w is the world coordinate point, R and T are the image rotation and translation matrices.

[0051] Step 1.2, detecting the observed target: using the target detection algorithm to obtain the two-dimensional area where the observed target of the current screen is located;

[0052] Step 1.3, target feature point matching and 3D position determination: Use the ORB algorithm to extract all camera screen feature points, then use PROSAC to match feature points and remove mismatched points. In step 1.3, feature matching point pairs are extracted in the 2D area where the target is located, and the 3D position of the target is calculated using the triangulation principle based on the feature matching point pairs of the target; the 3D space point forms a pair of corresponding pixel homogeneous coordinates formed by the left and right cameras, and the two back-projected rays formed by the image point intersect at one point in space, and the intersection point is the 3D coordinate corresponding to the two pixel points.

[0053] In actual use of the present invention, preferably, firstly, the skeleton points of the monitoring device are obtained, and the mobile device is detected by using a target detection algorithm such as the YOLOv7 algorithm, and then the skeleton points of the mobile device are detected by using a skeleton point detection model such as HRNET to obtain the two-dimensional coordinates of the skeleton points of the mobile device in the pixel coordinate system. Secondly, a world coordinate system is established based on the mobile device, and the three-dimensional coordinates of the skeleton points of the mobile device in the world coordinate system are determined, and finally the posture estimation of the camera is performed by the PNP principle.

[0054] When the present invention is actually used, a target detection algorithm such as the yolov7 algorithm is used to obtain the two-dimensional area where the observation target of the current screen is located. The YOLOv7 network mainly includes four parts: Input, Backbone, Neck, and Head. First, the image is pre-processed by a series of operations such as data enhancement in the input part, and then sent to the backbone network. The backbone network extracts features from the processed image; then, the extracted features are processed by the Neck module feature fusion to obtain features of three sizes: large, medium, and small; finally, the fused features are sent to the detection head, and the results are output after detection.

[0055] This project uses AI computing’s intelligent video recognition technology and information structure optimization on the basis of the existing video surveillance system to automatically collect, analyze, judge and provide feedback on the behaviors of operators, thereby realizing the automation and intelligence of operation behavior supervision. The real-time analysis and judgment function of the operation behavior of the system of the present invention adopts intelligent AI video image analysis algorithm technology, which belongs to the branch of computer science and technology. This technology enables computers to perform complex tasks that can only be completed by human intelligence through technological innovation. Furthermore, the intelligent AI visual analysis video algorithm technology used for dynamic process management has broken through the application level of video surveillance that only stays at the on-site recording and remote monitoring. Finally, the present invention uses actual coordinate positions to establish a 3D coordinate system with high accuracy, which can be adjusted in time according to changes in on-site operation conditions and has high flexibility.

[0056] A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the device where the computer-readable storage medium is located executes the intelligent control method for substation operation behavior as described above. The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory and other memory.

[0057] An electronic device comprises: a memory and a processor, wherein the memory stores a program that can be run on the processor, and when the processor executes the program, the intelligent control method for substation operation behavior as described above is implemented.

[0058] If the module / unit integrated in the electronic device described in this application is implemented in the form of 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 present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware devices through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented.

[0059] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0060] Computer-readable instructions are stored in the computer-readable storage medium, and the computer-readable instructions are executed by a processor in the electronic device to implement the intelligent control method for substation operation behavior described in any of the above embodiments.

[0061] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0062] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0063] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

[0064] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0065] Note that the above are only preferred embodiments of the present invention and the principles of the application technology. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention is described in more detail through the above embodiments, the present invention is not limited to the specific embodiments described herein, and may include more other effective embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An intelligent control system for substation operation behavior, characterized in that: It includes information collection unit, intelligent analysis unit, centralized control management unit and 3D electronic perimeter. The 3D electronic perimeter is a digital setting for the operation site. The information collection unit is used to collect real-time operation information at the operation site and receive feedback information from the intelligent analysis unit; It is specifically composed of a surveillance ball, a camera, a drone, an audible and visual alarm, a wireless or wired transmitter, and a low-voltage power supply; The intelligent analysis unit is used to perform real-time visual AI algorithm analysis on the collected video images, conduct real-time and uninterrupted tracking and analysis on the operation area and operation behavior information flow, automatically determine whether the relevant information conforms to the action logic in the preset model library through AI intelligence, and trigger sound and light alarms to warn the operation site of the judgment results of unstable operation and illegal operation in real time, and simultaneously capture and record and upload to the centralized control management terminal; it is specifically composed of an intelligent analysis device with a preset fixed algorithm, a system safety device, and a wireless or wired transmitter; The centralized control management unit is used to receive information from multiple different intelligent analysis devices, and centrally feed it back to the centralized control platform for rear management personnel to grasp the real-time situation of different work sites.

2. A control method based on the intelligent control system for substation operation behavior according to claim 1, characterized in that: The method comprises the following steps: Step 1: Create a 3D electronic perimeter; Step 2: Monitor the image within the 3D electronic perimeter through the information acquisition unit, Step 3: The centralized control management unit analyzes the image within the 3D electronic perimeter and determines the position and action logic; if it meets the set requirements, continue; otherwise, send a signal to the centralized control management unit; Step 4: After receiving the signal, the centralized control management unit performs actions such as alarm, snapshot, and archiving to complete automatic monitoring.

3. The intelligent control method for substation operation behavior according to claim 3 is characterized by: The step 1 specifically includes the following steps: Step 1.1, detection of skeleton points of the monitoring device and estimation of the camera pose; Step 1.2, detecting the observed target: using the target detection algorithm to obtain the two-dimensional area where the observed target of the current screen is located; Step 1.3, target feature point matching and 3D position determination: Use the ORB algorithm to extract all camera image feature points, then use PROSAC to match the feature points and eliminate mismatched points.

4. The intelligent control method for substation operation behavior according to claim 3 is characterized by: The step 1.1 comprises the following steps: Step 1.1.1, first use a target detection algorithm such as the YOLOv7 algorithm to detect the mobile device, then use a skeleton point detection model such as HRNET to detect the skeleton points of the mobile device, and obtain the two-dimensional coordinates of the skeleton points of the mobile device in the pixel coordinate system. Step 1.1.2, establish a world coordinate system based on the mobile device, and determine the three-dimensional coordinates of the skeleton points of the mobile device in the world coordinate system, Step 1.1.3, use the PnP or Perspective-n-Point method to solve the 3D to 2D point motion: when n 3D space points, i.e. the world coordinate system and their projection positions are known, the rotation and translation matrix is ​​used to estimate the camera's posture.

5. The intelligent control method for substation operation behavior according to claim 3 is characterized by: The camera projection relationship in step 1.1.3 is as follows: Among them, z c is the distance depth coefficient, u d 、v d is the pixel coordinate point, f cx 、f cy is the focal length of the camera, d x d y is the physical length of a pixel, u0 and v0 are the intersection points of the camera optical axis and the image plane, and x w ,y w 、z w is the world coordinate point, R and T are the image rotation and translation matrices.

6. The intelligent control method for substation operation behavior according to claim 3 is characterized by: In the step 1.3, feature matching point pairs are extracted in the two-dimensional area where the target is located, and the three-dimensional position of the target is calculated using the triangulation principle based on the feature matching point pairs of the target; a pair of corresponding pixel homogeneous coordinates of the three-dimensional space point formed by the left and right cameras, and two back-projected rays formed by the image point intersect at one point in space, and the intersection point is the three-dimensional coordinate corresponding to the two pixel points.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the device where the computer-readable storage medium is located executes the intelligent control method for substation operation behavior as described in any one of claims 1.

8. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a program that can be run on the processor, and when the processor executes the program, the intelligent control method for substation operation behavior as described in any one of claims 1-7 is implemented.

Images