Operation area electronic fence automatic generation and intrusion alarm method and medium

Abstract

The invention discloses an operation area electronic fence automatic generation and intrusion alarm method and a medium in the technical field of electronic fences. The method comprises the steps of obtaining a full-scene standard three-dimensional model based on three-dimensional data of a transformer substation building and primary equipment and shooting data of secondary equipment; a digital model is constructed based on key information of typical work tickets and secondary safety measure tickets, correlation mapping of the digital model and a full-scene standard three-dimensional model is established through a global unique identifier to generate digital expression, and intervals and screen cabinets of operation and inspection work are divided into a plurality of work areas. Automatically generating a virtual electronic fence based on PRM sampling path planning and collision early warning; different monitoring precision virtual electronic fences are set for indoor and outdoor environments according to the type of a working area, the position of an irregular obstacle is obtained in real time, and an alarm is triggered immediately when an intrusion behavior is found. According to the invention, automatic generation of the electronic fence and intrusion alarm are realized, the operation safety risk is reduced, and the human resource configuration and process management and control efficiency are optimized.

Description

Technical Field

[0001] The invention relates to an automatic generation method and intrusion alarm method for an operation area electronic fence and a medium, belonging to the technical field of electronic fences. Background Art

[0002] In the current substation operation environment, it is crucial to ensure the safety of the boundaries of the operating area. Traditionally, this safety protection is mainly achieved by setting up physical safety fences. As an intuitive isolation method, safety fences are designed to clearly define the operating area and the non-operating area to prevent unauthorized personnel or equipment from mistakenly entering the working area that may be energized or have other safety risks. These fences are usually made of hard materials such as metal or plastic, with a certain strength and durability to ensure that they can provide stable protection during the operation. However, with the expansion of substation scale and the increase in operation complexity, the deployment and maintenance of traditional safety fences face many challenges.

[0003] Although traditional safety fences play a fundamental role in substation security protection, their inherent limitations are becoming increasingly prominent. First, the fences are often insufficient, especially in large substations or during peak hours of operation. The limited number of fences can hardly meet the safety isolation requirements of all operating areas. Second, the fences themselves are relatively heavy, which not only increases the difficulty of handling and deployment, but also occupies a large storage space, which is not conducive to the effective use of resources. In addition, omissions are prone to occur during the deployment of fences, especially in complex terrain or emergency situations, and it is difficult to ensure that each operating area can be isolated in a timely and accurate manner. More importantly, the traditional safety monitoring method is highly dependent on the manual monitoring of the guardian, which not only increases the workload of the guardian, but also easily leads to monitoring loopholes due to human factors, such as distraction and misjudgment, which seriously threatens the safety of on-site workers. Therefore, there is an urgent need for a more intelligent and efficient safety protection technology to make up for the shortcomings of the existing fence system.

[0004] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgement or any form of suggestion that the information constitutes the prior art already known to ordinary technicians in this field. Summary of the invention

[0005] The technical problem to be solved by the present invention is: how to automatically generate electronic fences and intrusion alarms in the work area to reduce work safety risks, optimize human resource allocation and improve process control efficiency.

[0006] In order to solve the above technical problems, the present invention is implemented by adopting the following technical solutions.

[0007] In a first aspect, the present invention provides a method for automatically generating an electronic fence in a work area and providing an intrusion alarm, comprising: Based on the 3D data of the substation building and primary equipment and the on-site shooting data of the secondary equipment, a full-scene standard 3D model is obtained; Use natural language processing technology to analyze and extract key information from typical work tickets and secondary safety measures tickets, build digital models of primary and secondary safety work areas, and use the globally unique identifier GUID to establish an association mapping between the digital model and the full-scene standard 3D model to generate a digital expression of the safety work area; Based on the digital expression of the safe work area, the intervals of real-time operation and inspection work and the cabinet objects are divided into several independent work areas according to the boundaries of the cabinet objects. According to the characteristics of several independent work areas, the virtual electronic fence demarcation work area type is automatically generated in the full-scene standard 3D model based on the PRM sampling path planning algorithm and collision warning algorithm; A virtual electronic fence whitelist is set according to the workspace type and the parsed information of the digital model, and different monitoring accuracies are set for the virtual electronic fence according to indoor and outdoor environments; According to the virtual electronic fence whitelist, the location of irregular obstacles is obtained in real time based on wireless positioning technology, and an alarm is triggered immediately when an intrusion is detected.

[0008] Furthermore, based on the 3D data of the substation building and primary equipment and the on-site shooting data of the secondary equipment, a full-scene standard 3D model is obtained, including: Based on point cloud scanning technology, three-dimensional modeling of substation buildings and primary equipment is carried out to obtain three-dimensional models of substation buildings and primary equipment; Based on the on-site shooting data of the secondary equipment, the three-dimensional model of the secondary equipment is restored using image processing technology and three-dimensional modeling algorithms; According to the basic data of substation building, primary equipment and secondary equipment, the 3D models of substation building and primary equipment and the 3D models of secondary equipment are associated to obtain a full-scene standard 3D model; Among them, the basic data includes operation data, video surveillance data and intelligent inspection data.

[0009] Furthermore, natural language processing technology is used to analyze and extract key information from typical work tickets and secondary safety measures tickets, to build digital models of primary and secondary safety work areas, and to establish an association mapping between the digital model and the full-scene standard 3D model through a globally unique identifier GUID, to generate a digital expression of the safety work area, including: Use natural language processing technology to analyze and extract key information from typical work tickets and secondary safety measures tickets, and build digital models of primary and secondary safety work areas in a structured manner; Establishing an association mapping between the digital model and the full-scene standard three-dimensional model through a globally unique identifier GUID; generating a digital representation of a safe working area based on the association map and key information extracted from the digital model; The key information includes the name of the guardian, the name of the operator, work tasks, work content, and safety measures; The work area types include work areas, danger areas, passages and temporary control areas.

[0010] Furthermore, natural language processing technology is used to analyze and extract key information from typical work tickets and secondary safety measures tickets, and a digital model of the primary and secondary safety work areas is constructed in a structured manner, including: Use natural language processing technology to obtain typical work tickets and secondary security measures tickets and perform data preprocessing to obtain preprocessed data; The Transform-based neural network model is used to extract the pre-processed data to obtain the key information of typical work tickets and secondary security measures tickets; The key information is classified and a digital model of the primary and secondary safe working areas is automatically constructed in a structured manner.

[0011] Furthermore, according to the characteristics of several independent workspaces, the virtual electronic fence workspace type is automatically generated based on the PRM sampling path planning algorithm and the collision warning algorithm in the full-scene standard three-dimensional model, including: When the inspection work is in progress: For indoor environments: set up maintenance signs in the work area and set up red curtains to block non-work areas; For outdoor environments: When there are no irregular obstacles in the outdoor environment: set up maintenance signs in the working area and set up red curtains to block the non-working area; When there are irregular obstacles in the outdoor environment: Generate a virtual electronic fence based on the PRM sampling path planning algorithm and collision warning algorithm; When the operation and maintenance work is completed: the working areas in the indoor and outdoor environments will be free of maintenance signs, and the non-working areas will be free of red curtains.

[0012] Furthermore, the generation of a virtual electronic fence based on the PRM sampling path planning algorithm and the collision warning algorithm includes: The PRM sampling path planning algorithm is used to densely sample the sampling points evenly distributed in the standard 3D model of the entire scene; Connect each sampling point with other sampling points within a preset connection distance, remove the edges that collide with irregular obstacles based on the collision warning algorithm, and obtain a collision-free path graph from the starting point to the end point; Optimizing the collision-free path graph by changing a preset connection distance or a path optimization algorithm to obtain optimized path points; In the full-scene standard three-dimensional model, a virtual electronic fence is automatically generated according to the trajectory coordinates of the optimized path points to limit the movement range of irregular obstacles.

[0013] Furthermore, the virtual electronic fence whitelist is set according to the workspace type and the parsed information of the digital model, and different monitoring accuracies are set for the virtual electronic fence according to the indoor and outdoor environments, including: By analyzing the key information of the digital model, the information of the guardian and the operator can be obtained; By setting up a virtual electronic fence whitelist based on the work area type and guardian and operator information; For indoor switch room scenarios, monitoring is performed based on LiDAR, providing a virtual electronic fence with centimeter-level monitoring accuracy of no more than 2 cm; For outdoor scenarios, monitoring is carried out based on ultra-wideband UWB technology, providing a virtual electronic fence with a decimeter-level monitoring accuracy of no more than 1.5 decimeters.

[0014] Furthermore, the real-time acquisition of the position of the irregular obstacle based on the wireless positioning technology according to the virtual electronic fence whitelist includes: Set up a positioning base station at the substation and bind the positioning tag to the list of operators in the virtual electronic fence whitelist; The operators wear positioning tags, and their real-time location is obtained by tracking the dynamic position of the positioning tags within the virtual electronic fence.

[0015] Furthermore, when an intrusion is detected, an alarm is immediately triggered, including: When it is monitored that a worker enters a dangerous area in violation of regulations, or a work supervisor leaves his post or location without authorization, an automatic vibration alarm or voice alarm will be immediately sent to relevant personnel through the positioning terminal to warn of the abnormal situation.

[0016] In a second aspect, the present invention provides a computer-readable storage medium having a computer program / instruction stored thereon, which implements the steps of the method described in the first aspect when the computer program / instruction is executed by a processor.

[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention uses natural language processing technology to deeply analyze work tickets and secondary safety tickets, not only constructing digital models of primary and secondary safe working areas, but also associating the digital models with the full-scene three-dimensional model through the globally unique identifier GUID, ensuring the accurate expression of the safe working area. By integrating the multi-dimensional data of substation buildings, primary equipment and secondary equipment, a standard three-dimensional model of the full scene is constructed, realizing the accurate digital reproduction of the working environment.

[0018] 2. The present invention also innovatively uses the PRM sampling path planning algorithm and collision warning algorithm to automatically generate a virtual electronic fence that matches the characteristics of the work area, effectively demarcates various work areas, and flexibly sets the monitoring accuracy according to the type of work area and environmental characteristics, which not only ensures safety but also improves efficiency.

[0019] 3. The present invention also uses wireless positioning technology to monitor the position of irregular obstacles in real time. Once an intrusion is detected, the system can quickly trigger an alarm to effectively prevent operational risks and ensure the safety of operators and equipment. It significantly improves the safety management level of substation operation and maintenance operations, reduces human errors and safety hazards, and provides a strong guarantee for the stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 The figure is a flow chart of a method for automatically generating an electronic fence and intrusion alarm in a work area provided by an embodiment of the present invention; Figure 2 The figure is a schematic diagram of a process of constructing a digital model of a primary and secondary safe working area provided by an embodiment of the present invention; Figure 3 The figure is a schematic diagram of a process of generating a virtual electronic fence based on a PRM sampling path planning algorithm and a collision warning algorithm provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0022] The term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the related objects are in an "or" relationship.

[0023] Example 1

[0024] like Figure 1 As shown, this embodiment introduces a method for automatically generating an electronic fence in a work area and an intrusion alarm, including: Step 1: Based on the 3D data of the substation building and primary equipment and the on-site shooting data of the secondary equipment, a full-scene standard 3D model is obtained.

[0025] The present invention obtains various information about the building structure, primary equipment and secondary equipment of the substation by integrating 3D modeling technology with on-site shooting data, and constructs an accurate full-scene standard 3D model. In the spatial reference framework of the full-scene standard 3D model, a virtual electronic fence can be generated to realize the intrusion alarm of irregular obstacles. The operating environment of the substation is fully digitally reproduced, laying a solid foundation for subsequent safety management work.

[0026] Step 2: Use natural language processing technology to analyze and extract key information from typical work tickets and secondary safety measures tickets, build digital models of primary and secondary safety work areas, and use the globally unique identifier GUID to establish an association mapping between the digital model and the full-scene standard 3D model to generate a digital expression of the safe work area.

[0027] The present invention utilizes natural language processing technology to process work tickets and secondary safety tickets to construct digital models of primary and secondary safe working areas, and establishes precise association between the digital model and the full-scene standard three-dimensional model by introducing a globally unique identifier GUID, which not only improves work efficiency but also ensures the accuracy and consistency of the safe working area.

[0028] Step 3: Based on the digital expression of the safe working area, the intervals of real-time operation and maintenance work and the cabinet objects are divided into several independent working areas according to the boundaries of the cabinet objects. According to the characteristics of several independent working areas, the virtual electronic fence work area type is automatically generated in the full-scene standard 3D model based on the PRM sampling path planning algorithm and collision warning algorithm.

[0029] The present invention divides the substation into multiple independent working areas, and uses the PRM sampling path planning algorithm and collision warning algorithm to automatically generate a virtual electronic fence that matches the characteristics of the working area, thereby realizing accurate division and effective isolation of the substation working area, effectively avoiding collisions and misoperations during the operation process, and improving operation safety and efficiency.

[0030] Step 4: A virtual electronic fence whitelist is set according to the workspace type and the parsed information of the digital model, and different monitoring accuracies are set for the virtual electronic fence according to indoor and outdoor environments.

[0031] The present invention adjusts the monitoring accuracy according to the white list of the virtual electronic fence and the different characteristics of the indoor and outdoor environments, which not only avoids false alarms and missed alarms, but also ensures that the system can maintain the best working state in different environments, thereby improving the flexibility and adaptability of the system.

[0032] Step 5: According to the virtual electronic fence whitelist, the location of irregular obstacles is obtained in real time based on wireless positioning technology, and an alarm is triggered immediately when an intrusion is detected.

[0033] The present invention uses wireless positioning technology to monitor the position of irregular obstacles in real time and immediately trigger an alarm when an intrusion is found, thus achieving real-time monitoring and intrusion detection of the substation operation area, effectively preventing operation risks and ensuring the safety of operators and equipment. At the same time, the real-time alarm function also improves the response speed and accuracy of the system, providing a strong guarantee for the stable operation of the system.

[0034] Example 2

[0035] Based on the same inventive concept as Example 1, this example introduces a method for automatically generating an electronic fence in a work area and an intrusion alarm, which specifically includes the following steps: Step 1: Based on the 3D data of the substation building and primary equipment and the on-site shooting data of the secondary equipment, a full-scene standard 3D model is obtained, including: Based on point cloud scanning technology, three-dimensional modeling of substation buildings and primary equipment is carried out to obtain three-dimensional models of substation buildings and primary equipment; Based on the on-site shooting data of secondary equipment including on-site screen cabinets, equipment and components, the three-dimensional model of the secondary equipment is restored using image processing technology and three-dimensional modeling algorithms; According to the basic data of substation buildings, primary equipment and secondary equipment, the three-dimensional models of substation buildings and primary equipment and the three-dimensional model of secondary equipment are associated to obtain a full-scene standard three-dimensional model, realizing dynamic visualization of the model.

[0036] Among them, the basic data includes operation data, video surveillance data and intelligent inspection data.

[0037] Step 2: Use natural language processing technology to analyze and extract key information of typical work tickets and secondary safety measures tickets, build digital models of primary and secondary safety work areas, and establish an association mapping between the digital model and the full-scene standard 3D model through the global unique identifier GUID to generate a digital expression of the safe work area, such as Figure 2 As shown, including: Using natural language processing technology, we analyze and extract key information from typical work tickets and secondary safety measures tickets, and build digital models of primary and secondary safety work areas in a structured manner, including: Use natural language processing technology to obtain typical work tickets and secondary security measures tickets and perform data preprocessing to obtain preprocessed data; The Transform-based neural network model is used to extract the pre-processed data to obtain the key information of typical work tickets and secondary security measures tickets; Classify the key information and automatically construct a digital model of the primary and secondary safe working areas in a structured manner; Establishing an association mapping between the digital model and the full-scene standard three-dimensional model through a globally unique identifier GUID; generating a digital representation of a safe working area based on the association map and key information extracted from the digital model; The key information includes the name of the guardian, the name of the operator, work tasks, work content, and safety measures; The work area types include work areas, danger areas, passages and temporary control areas.

[0038] Step 3: Based on the digital expression of the safe working area, the intervals of real-time operation and maintenance work and the cabinet objects are divided into several independent working areas according to the boundaries of the cabinet objects. According to the characteristics of several independent working areas, the virtual electronic fence work area type is automatically generated in the full-scene standard 3D model based on the PRM sampling path planning algorithm and collision warning algorithm.

[0039] In this embodiment, according to the characteristics of several independent workspaces, a virtual electronic fence is automatically generated based on the PRM sampling path planning algorithm and the collision warning algorithm in the full-scene standard three-dimensional model to define the workspace type, including: When the inspection work is in progress: For indoor environments: set up maintenance signs in the work area and set up red curtains to block non-work areas; For outdoor environments: When there are no irregular obstacles in the outdoor environment: set up maintenance signs in the working area and set up red curtains to block the non-working area; When there are irregular obstacles in the outdoor environment: Generate a virtual electronic fence based on the PRM sampling path planning algorithm and collision warning algorithm; When the operation and maintenance work is completed: the working areas in the indoor and outdoor environments will be free of maintenance signs, and the non-working areas will be free of red curtains.

[0040] In this embodiment, a virtual electronic fence is generated based on the PRM sampling path planning algorithm and the collision warning algorithm, such as Figure 3 As shown, including: The PRM sampling path planning algorithm is used to densely sample the sampling points evenly distributed in the standard 3D model of the entire scene; Connect each sampling point with other sampling points within the preset connection distance, remove the edges that collide with irregular obstacles based on the collision warning algorithm, and obtain a collision-free path graph from the starting point to the end point to ensure that the generated path will not collide with irregular obstacles; By changing the preset connection distance, reducing unreasonable paths, improving the overall planning efficiency or optimizing the collision-free path graph with a path optimization algorithm, reducing the path length or time while maintaining safety, an optimized path point is obtained; In the full-scene standard three-dimensional model, a virtual electronic fence is automatically generated according to the trajectory coordinates of the optimized path points to limit the movement range of irregular obstacles.

[0041] The path optimization algorithm includes dynamic programming and genetic algorithm.

[0042] Step 4: A virtual electronic fence whitelist is set according to the workspace type and the parsed information of the digital model, and different monitoring accuracies are set for the virtual electronic fence according to indoor and outdoor environments.

[0043] In this embodiment, a virtual electronic fence whitelist is set according to the workspace type and the parsed information of the digital model, including: By analyzing the key information of the digital model, the information of the guardian and the operator can be obtained; By setting up a virtual electronic fence whitelist based on the work area type and guardian and operator information.

[0044] In this embodiment, different monitoring accuracies are set for the virtual electronic fence according to indoor and outdoor environments, including: For indoor switch room scenarios, monitoring is performed based on LiDAR, providing a virtual electronic fence with a centimeter-level monitoring accuracy of no more than 2 cm, which can effectively prevent cross-panel cabinet and cross-boundary operations; For outdoor scenarios, UWB technology is used for monitoring, providing a virtual electronic fence with a decimeter-level monitoring accuracy of no more than 1.5 decimeters, which can effectively prevent out-of-bounds operations and accidental entry into intervals.

[0045] Step 5: According to the virtual electronic fence whitelist, the location of irregular obstacles is obtained in real time based on wireless positioning technology, and an alarm is triggered immediately when an intrusion is detected.

[0046] In this embodiment, according to the virtual electronic fence whitelist, the position of the irregular obstacle is obtained in real time based on the wireless positioning technology, including: Set up a positioning base station at the substation and bind the positioning tag to the list of operators in the virtual electronic fence whitelist; The operators wear positioning tags, and their real-time location is obtained by tracking the dynamic position of the positioning tags within the virtual electronic fence.

[0047] When operators are performing maintenance work on site, the work area is automatically marked in the full-scene standard 3D model and a virtual electronic fence is generated, which is linked with the cameras in the work area to automatically track and record the operator's activities in the area.

[0048] In this embodiment, when an intrusion behavior is discovered, an alarm is immediately triggered, including: When it is monitored that a worker enters a dangerous area in violation of regulations, or a work supervisor leaves his post or location without authorization, an automatic vibration alarm or voice alarm will be immediately sent to relevant personnel through the positioning terminal to warn of the abnormal situation.

[0049] When team members conduct daily inspections: Automatically locate the positions of team members and record their clock-ins, while linking on-site cameras to take snapshots of team members.

[0050] In actual application, a positioning base station is set up in the substation to bind the positioning tag to the whitelist personnel one by one. In the work order, the operator wears a positioning tag, and the dynamic position of the operator is obtained in real time according to the positioning tag. The positioning data of the dynamic position of the operator is uploaded to the back-end system platform synchronously, and the dynamic position of the operator is displayed at any time. The back-end operation and maintenance personnel remotely monitor the operator according to the alarm information. When the operator mistakenly enters the non-operating interval, the operator is guided to enter the safe area through real-time voice shouting and collaborative guidance. At the same time, the full-scene standard 3D model performs 3D scene video linkage, and automatically presents the operator's on-site area video. At the same time, when the operator enters the risk area or the person in charge of the work leaves the post, an alarm is issued. When the alarm is issued, the positioning terminal automatically vibrates / voices an alarm. In addition, the inspection personnel punch in through automatic positioning, and the on-site camera is linked to capture and record the monitoring of intrusion behavior.

[0051] Example 3

[0052] Similar to the inventive concept of other embodiments, this embodiment provides a computer-readable storage medium on which computer instructions are stored. When the computer instructions are executed by a processor, the steps of the method of the above-mentioned embodiment 1 or 2 are implemented.

[0053] To summarize the above embodiments, the present invention uses work tickets and secondary safety tickets as business processes to drive the entire operation and maintenance process, integrates the full-scene standard three-dimensional model application video image monitoring, wireless positioning technology, audio and video remote collaboration and other advanced Internet of Things and computer communication technologies, with the goal of ensuring the personal safety of operators and equipment safety. Through precise analysis of the digital "two tickets", real-time analysis and active early warning of operation risks and violations, holographic full-process tracking and evaluation and other means, the safety risks of personnel operations are reduced, the contradictions of human resources in operations are alleviated, and the quality and efficiency of operation process management are improved.

[0054] The present invention uses natural language processing technology to deeply analyze the work ticket and the secondary safety ticket, not only constructing a digital model of the primary and secondary safe working areas, but also associating the digital model with the full-scene three-dimensional model through the globally unique identifier GUID, ensuring the accurate expression of the safe working area. By integrating the multi-dimensional data of the substation building, primary equipment and secondary equipment, a standard three-dimensional model of the full scene is constructed, realizing the accurate digital reproduction of the working environment.

[0055] The present invention also innovatively uses the PRM sampling path planning algorithm and collision warning algorithm to automatically generate a virtual electronic fence that matches the characteristics of the work area, effectively demarcating various work areas. At the same time, it flexibly sets the monitoring accuracy according to the type of work area and environmental characteristics, which not only ensures safety but also improves efficiency.

[0056] The present invention also monitors the position of irregular obstacles in real time through wireless positioning technology. Once an intrusion is detected, the system can quickly trigger an alarm, effectively prevent operational risks, and ensure the safety of operators and equipment. It significantly improves the safety management level of substation operation and maintenance operations, reduces human errors and safety hazards, and provides a strong guarantee for the stable operation of the power system. It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0057] 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.

[0058] 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.

[0059] 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 in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0060] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A method for automatically generating electronic fences and intrusion alarms in a work area, characterized in that: include: Based on the 3D data of the substation building and primary equipment and the on-site shooting data of the secondary equipment, a full-scene standard 3D model is obtained; Use natural language processing technology to analyze and extract key information from typical work tickets and secondary safety measures tickets, build digital models of primary and secondary safety work areas, and use the globally unique identifier GUID to establish an association mapping between the digital model and the full-scene standard 3D model to generate a digital expression of the safety work area; Based on the digital expression of the safe work area, the intervals of real-time operation and inspection work and the cabinet objects are divided into several independent work areas according to the boundaries of the cabinet objects. According to the characteristics of several independent work areas, the virtual electronic fence demarcation work area type is automatically generated in the full-scene standard 3D model based on the PRM sampling path planning algorithm and collision warning algorithm; A virtual electronic fence whitelist is set according to the workspace type and the parsed information of the digital model, and different monitoring accuracies are set for the virtual electronic fence according to indoor and outdoor environments; According to the virtual electronic fence whitelist, the location of irregular obstacles is obtained in real time based on wireless positioning technology, and an alarm is triggered immediately when an intrusion is detected.

2. The method for automatically generating electronic fences and intrusion alarms in a work area according to claim 1, characterized in that: Based on the 3D data of the substation building and primary equipment and the on-site shooting data of the secondary equipment, a full-scene standard 3D model is obtained, including: Based on point cloud scanning technology, three-dimensional modeling of substation buildings and primary equipment is carried out to obtain three-dimensional models of substation buildings and primary equipment; Based on the on-site shooting data of the secondary equipment, the three-dimensional model of the secondary equipment is restored using image processing technology and three-dimensional modeling algorithms; According to the basic data of substation building, primary equipment and secondary equipment, the 3D models of substation building and primary equipment and the 3D models of secondary equipment are associated to obtain a full-scene standard 3D model; Among them, the basic data includes operation data, video surveillance data and intelligent inspection data.

3. The method for automatically generating electronic fences and intrusion alarms in a work area according to claim 1, characterized in that: Natural language processing technology is used to analyze and extract key information from typical work tickets and secondary safety measures tickets, build digital models of primary and secondary safety work areas, and establish an association mapping between the digital model and the full-scene standard 3D model through the globally unique identifier GUID to generate a digital expression of the safe work area, including: Use natural language processing technology to analyze and extract key information from typical work tickets and secondary safety measures tickets, and build digital models of primary and secondary safety work areas in a structured manner; Establishing an association mapping between the digital model and the full-scene standard three-dimensional model through a globally unique identifier GUID; generating a digital representation of a safe working area based on the association map and key information extracted from the digital model; The key information includes the name of the guardian, the name of the operator, work tasks, work content, and safety measures; The work area types include work areas, danger areas, passages and temporary control areas.

4. The method for automatically generating electronic fences and intrusion alarms in a work area according to claim 3, characterized in that: Using natural language processing technology, we analyze and extract key information from typical work tickets and secondary safety measures tickets, and build digital models of primary and secondary safety work areas in a structured manner, including: Use natural language processing technology to obtain typical work tickets and secondary security measures tickets and perform data preprocessing to obtain preprocessed data; The Transform-based neural network model is used to extract the pre-processed data to obtain the key information of typical work tickets and secondary security measures tickets; The key information is classified and a digital model of the primary and secondary safe working areas is automatically constructed in a structured manner.

5. The method for automatically generating electronic fences and intrusion alarms in a work area according to claim 1, characterized in that: According to the characteristics of several independent workspaces, the virtual electronic fence workspace type is automatically generated based on the PRM sampling path planning algorithm and the collision warning algorithm in the full-scene standard three-dimensional model, including: When the inspection work is in progress: For indoor environments: set up maintenance signs in the work area and set up red curtains to block non-work areas; For outdoor environments: When there are no irregular obstacles in the outdoor environment: set up maintenance signs in the working area and set up red curtains to block the non-working area; When there are irregular obstacles in the outdoor environment: Generate a virtual electronic fence based on the PRM sampling path planning algorithm and collision warning algorithm; When the operation and maintenance work is completed: the working areas in the indoor and outdoor environments will be free of maintenance signs, and the non-working areas will be free of red curtains.

6. The method for automatically generating electronic fences and intrusion alarms in a work area according to claim 5, characterized in that: The method of generating a virtual electronic fence based on the PRM sampling path planning algorithm and the collision warning algorithm includes: The PRM sampling path planning algorithm is used to densely sample the sampling points evenly distributed in the standard 3D model of the entire scene; Connect each sampling point with other sampling points within a preset connection distance, remove the edges that collide with irregular obstacles based on the collision warning algorithm, and obtain a collision-free path graph from the starting point to the end point; Optimizing the collision-free path graph by changing a preset connection distance or a path optimization algorithm to obtain optimized path points; In the full-scene standard three-dimensional model, a virtual electronic fence is automatically generated according to the trajectory coordinates of the optimized path points to limit the movement range of irregular obstacles.

7. The method for automatically generating electronic fences and intrusion alarms in a work area according to claim 1, characterized in that: The virtual electronic fence whitelist is set according to the workspace type and the parsed information of the digital model, and different monitoring accuracies are set for the virtual electronic fence according to the indoor and outdoor environments, including: By analyzing the key information of the digital model, the information of the guardian and the operator can be obtained; By setting up a virtual electronic fence whitelist based on the work area type and guardian and operator information; For indoor switch room scenarios, monitoring is performed based on LiDAR, providing a virtual electronic fence with centimeter-level monitoring accuracy of no more than 2 cm; For outdoor scenarios, monitoring is carried out based on ultra-wideband UWB technology, providing a virtual electronic fence with a decimeter-level monitoring accuracy of no more than 1.5 decimeters.

8. The method for automatically generating electronic fences and intrusion alarms in a work area according to claim 1, characterized in that: The method of obtaining the position of irregular obstacles in real time based on the virtual electronic fence whitelist and wireless positioning technology includes: Set up a positioning base station at the substation and bind the positioning tag to the list of operators in the virtual electronic fence whitelist; The operators wear positioning tags, and their real-time location is obtained by tracking the dynamic position of the positioning tags within the virtual electronic fence.

9. The method for automatically generating electronic fences and intrusion alarms in a work area according to claim 1, characterized in that: When an intrusion is detected, an alarm is triggered immediately, including: When it is monitored that an operator enters a dangerous area in violation of regulations, or a work supervisor leaves his post or location without authorization, an automatic vibration alarm or voice alarm will be immediately sent to relevant personnel through the positioning terminal to warn of the abnormal situation.

10. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images