Intelligent maintenance system of high-voltage switch cabinet

Through the cloud management platform and maintenance robot of the intelligent maintenance system, the time series model and high-dimensional random matrix model are used to predict and generate faults and strategy, which solves the problems of high-voltage switch cabinet detection workload and insufficient sensitivity, and realizes the high-voltage switch cabinet Real-time monitoring and automatic maintenance improve the stability of the power system.

CN118920691APending Publication Date: 2024-11-08STATE GRID HEBEI ELECTRIC POWER CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410877481.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-02
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing technology lacks intelligent means for the fault detection of high-voltage switch cabinets, the detection workload is large, the data processing is cumbersome, and the insulation defects are not sensitive enough, which affects the long-term and stable operation of the power system.

Method used

Provide an intelligent maintenance system for high-voltage switch cabinets, including maintenance robots and cloud management platforms, using data analysis modules, policy generation modules and task scheduling modules to predict and repair strategy generation, combining time series models and high-dimensional random matrix models for Condition monitoring and discrimination analysis realize real-time status monitoring and intelligent analysis of high-voltage switch cabinets, and automatically complete inspection and maintenance tasks through maintenance robots.

Benefits of technology

Real-time status monitoring and intelligent analysis of high-voltage switch cabinets are realized, defects and safety hazards are discovered and dealt with in a timely manner, greatly improving the operating reliability of switch cabinets and ensuring the long-term and stable operation of the power system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118920691A_ABST
    Figure CN118920691A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of intelligent control, in particular to an intelligent maintenance system of a high-voltage switch cabinet. The system comprises a maintenance robot and a cloud management platform. The cloud management platform comprises a data analysis module, a strategy generation module and a task scheduling module; the data analysis module is used for acquiring historical state parameters of the high-voltage switch cabinet and generating fault prediction information based on a time sequence model and a high-dimensional random matrix model, and the historical state parameters comprise equipment commissioning time, historical live detection data, historical power failure detection data and historical defect elimination detection data; the strategy generation module is used for generating a maintenance strategy according to the fault prediction information; and the task scheduling module is used for calling the maintenance robot to execute an inspection task according to the maintenance strategy, and the inspection task comprises handcart circuit breaker station judgment and maintenance based on gravity sensing. State monitoring, intelligent research and judgment and emergency response are carried out on the high-voltage switch cabinet through the cloud management technology, and long-term stable operation of a power system is guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of intelligent control technology, and more specifically, to an intelligent maintenance system for a high-voltage switch cabinet. Background Art

[0002] 10kV and 35kV switchgear are important equipment for substations to supply power to users. The safe and stable operation of switchgear plays a very important role in the safety and reliability of power supply. Long-term operation of switchgear will affect the components in the cabinet by strong electric fields, thermal effects, moisture condensation, dust, etc., which will cause the insulation performance to decline or even deteriorate, affecting the safe operation of the switchgear.

[0003] To solve the above problems, the invention patent with publication number CN112305382A discloses a method for quickly identifying the working status of the internal equipment of the high-voltage switch cabinet. The three detection methods of infrared temperature measurement, ground wave partial discharge detection and ultrasonic partial discharge detection are used together to detect the internal working status of the switch cabinet. After obtaining the surface temperature measurement of the internal equipment of the switch cabinet and the transient ground voltage wave partial discharge data, the measurement data is recorded to identify equipment defects. The invention patent with publication number CN109444693A discloses a 35kV switch cabinet partial discharge detection method based on non-stop detection. The TEV detection method is combined with the ultrasonic detection method for detection. It can be seen that the current domestic switch cabinet fault detection mainly adopts the ultrasonic method and the transient ground potential method. The two detection methods are not sensitive enough to some insulation defects; the switch cabinet live detection lacks intelligent detection means. Generally, the detection personnel hold the detection instrument to regularly detect the switch cabinet. The detection workload is large, the data processing work is cumbersome, and the detection results mainly rely on human judgment, which has high requirements for personnel.

[0004] Therefore, how to provide an intelligent detection system for high-voltage switchgear to realize real-time status monitoring, intelligent analysis and emergency response of high-voltage switchgear to ensure the long-term stable operation of the power system has become a technical problem that needs to be solved. Summary of the invention

[0005] In view of this, the present application provides an intelligent maintenance system for a high-voltage switchgear to solve the above-mentioned problems.

[0006] The technical solutions provided by this application are as follows:

[0007] A smart maintenance system for a high-voltage switch cabinet comprises a maintenance robot and a cloud management platform; the cloud management platform comprises a data analysis module, a strategy generation module and a task scheduling module; the data analysis module is used to obtain historical state parameters of the high-voltage switch cabinet, and to perform discriminant analysis on the historical state parameters based on a time series model and a high-dimensional random matrix model to generate fault prediction information, the historical state parameters comprising equipment commissioning time, historical energized detection data, historical power outage detection data, and historical fault elimination detection data, the fault prediction information comprising faulty equipment, fault causes and fault trends; the strategy generation module is used to generate a maintenance strategy based on the fault prediction information; the task scheduling module is used to call a maintenance robot to perform inspection tasks based on the maintenance strategy, the inspection tasks comprising determination and maintenance of a trolley circuit breaker station based on gravity sensing.

[0008] In one possible implementation, the data analysis module is also used to monitor the equipment status of the high-voltage switchgear according to a preset cycle, and the equipment status includes a powered state, a power-off state, and a fault-eliminating state; the task scheduling module is used to call a maintenance robot to inspect the powered operation state of the high-voltage switchgear when the high-voltage switchgear is in a powered state; to call a maintenance robot to move the high-voltage switchgear to a target area for maintenance when the high-voltage switchgear is in a power-off state; and to call a maintenance robot to replace the high-voltage switchgear when the high-voltage switchgear is in a fault-eliminating state.

[0009] In one possible implementation, the discriminant analysis of the state parameters based on the time series model and the high-dimensional random matrix model to generate fault prediction information includes:

[0010] A high-dimensional random matrix is ​​constructed according to the historical state parameters, and the high-dimensional random matrix is ​​normalized, wherein the high-dimensional random matrix is ​​used to perform abnormal data detection on the historical state parameters and eliminate abnormal data;

[0011] Based on the eliminated historical state parameters, a time series model for edge computing is constructed. The time series model is used to characterize the changing relationship between the state parameters of the high-voltage switchgear and time, so as to predict the faults of the high-voltage switchgear and generate the fault prediction information.

[0012] In one possible implementation, the maintenance robot includes a control module, a laser navigation module, a visual navigation module and a laser ranging module;

[0013] The control module is used to receive and respond to the inspection instructions issued by the task scheduling module, and start the maintenance robot to perform the inspection task; wherein the inspection instruction includes the inspection strategy, inspection task and maintenance execution area;

[0014] The laser navigation module is used to obtain the position coordinate information of the maintenance robot during operation; the visual navigation module is used to obtain the environmental information of the maintenance robot during operation; the laser ranging module is used to locate the maintenance execution area;

[0015] The control module is also used to determine the moving path of the maintenance robot according to the position coordinate information and the environmental information, and to plan and adjust the moving path of the maintenance robot in real time based on the algebraic reconstruction method ART and the positioning maintenance execution area.

[0016] In one possible implementation, the maintenance robot further includes at least one visual sensor, and the visual sensor is used to obtain the actual posture of the maintenance robot during movement; the control module is also used to perform posture correction control on the moving posture of the maintenance robot based on the actual posture and based on a novel variable domain fuzzy control algorithm.

[0017] In one possible implementation, the control module performs posture correction control on the mobile posture of the maintenance robot based on the actual posture and the novel variable universe fuzzy control algorithm, including:

[0018] Obtaining a deviation between the actual posture and the ideal posture, wherein the deviation includes a normal position deviation and an attitude angle deviation;

[0019] According to the deviation, the discourse domain is adjusted in real time based on a novel variable discourse domain fuzzy control algorithm, and the running center steering angle of the maintenance robot is determined;

[0020] According to the motion center steering angle and the preset motion center speed, the actual adjustment amount based on the maintenance robot is determined to achieve posture correction control of the maintenance robot.

[0021] In one possible implementation, the system also includes a safety management and control unit, which pre-stores a floor plan of a maintenance room of a high-voltage switchgear. The floor plan of the maintenance room is divided into at least two areas, and each area is equipped with a monitoring device for monitoring the equipment status and live parts of the high-voltage switchgear.

[0022] In one possible implementation, the security management and control unit further includes a positioning module, an alarm control module and at least one monitoring terminal;

[0023] The positioning module is used to obtain the position information of the maintenance robot in real time and determine the actual distance between the maintenance robot and the live part of the high-voltage switch cabinet;

[0024] The alarm control module is used to determine whether the actual distance is less than the preset distance; if so, generate an alarm message;

[0025] The monitoring terminal is used to visualize the equipment status, live parts and alarm information of the high-voltage switch cabinet.

[0026] In one possible implementation, the system also includes a maintenance operation unit, which is used to perform tests and / or maintenance work on the high-voltage switchgear. The tests include mechanical property tests, loop resistance tests, insulation resistance tests, and AC withstand voltage tests; and the maintenance work includes cleaning, dust removal, and conductive paste application.

[0027] In one possible implementation, the inspection task also includes local discharge signal detection, insulation resistance detection and AC withstand voltage detection of high-voltage switch cabinet.

[0028] The present application provides an intelligent maintenance system for high-voltage switchgear, which performs status monitoring, intelligent analysis and emergency response on high-voltage switchgear through cloud management technology. It will perform status monitoring, data analysis and comprehensive intelligent analysis on a large number of high-voltage switchgear in the power system, and regularly and automatically complete various types of tests and maintenance work, so as to promptly discover and deal with defects and safety hazards in the switchgear, greatly improve the reliability of the switchgear operation, and thus ensure the long-term stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present application 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 embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0030] Figure 1 A schematic structural diagram of an intelligent maintenance system for a high-voltage switchgear provided in Example 1 of the present application.

[0031] Figure 2 A schematic diagram of the structure of a maintenance robot provided in Example 1 of the present application.

[0032] Figure 3 A schematic diagram of the structure of an intelligent maintenance system for a high-voltage switchgear provided in Example 2 of the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] Embodiment 1:

[0035] See also Figure 1 , is a schematic diagram of the structure of an intelligent maintenance system for a high-voltage switchgear provided in Embodiment 1 of the present application. Figure 1 As shown in , the above-mentioned intelligent maintenance system includes a cloud management platform 1 and a maintenance robot 2.

[0036] In the embodiment of the present application, the cloud management platform 1 comprehensively collects parameters such as equipment commissioning time, manufacturer, historical detection data, live, online, power outage, and fault elimination detection data. The multi-dimensional state data is integrated, and effective big data technologies such as time series models and high-dimensional random matrix models are used to mine and analyze a large amount of relevant data and extract information, analyze the trend of equipment test data, actively judge the time, cause, and development of equipment failures of the same type, and actively push test plans.

[0037] Specifically, the cloud management platform includes a data analysis module 10 , a strategy generation module 11 and a task scheduling module 12 .

[0038] The data analysis module 10 is specifically used to obtain the historical state parameters of the high-voltage switchgear, and to perform discriminant analysis on the historical state parameters based on the time series model and the high-dimensional random matrix model to generate fault prediction information. The above historical state parameters include equipment commissioning time, historical live detection data, historical power outage detection data, and historical fault elimination detection data, and the above fault prediction information includes faulty equipment, fault causes, and fault trends.

[0039] In a specific application scenario, during daily live maintenance, the maintenance robot inspects the status of the switch cabinet and transmits the data to the integrated cloud management technology for analysis and judgment to make the next maintenance decision. During power outages or defect handling, no manual work is required, and the equipment is automatically shut down, the trolley circuit breaker is pulled out, moved, and pushed to the intelligent maintenance test technology. The intelligent maintenance test technology performs a series of maintenance and test operations on the trolley circuit breaker, and transmits the equipment response data to the integrated cloud management technology for analysis and judgment, and makes further maintenance decisions.

[0040] The above-mentioned discriminant analysis of the historical state parameters based on the time series model and the high-dimensional random matrix model to generate fault prediction information may further include:

[0041] A high-dimensional random matrix is ​​constructed based on the above historical state parameters, and the high-dimensional random matrix is ​​normalized. The processed high-dimensional random matrix is ​​used to detect abnormal data on the above historical state data and eliminate abnormal data.

[0042] Based on the historical status data after removing abnormal data, a time series model for edge computing is constructed to characterize the relationship between the state parameters of the high-voltage switchgear and time, so as to predict the faults of the high-voltage switchgear and generate the above-mentioned fault prediction information. By comparing with historical data and analyzing trends, the historical test records of the equipment can be automatically pushed according to the current working equipment and the nature of the work. Through graphical display, historical data can be compared in real time. Based on the intelligent diagnosis algorithm of convolutional neural network, intelligent cloud diagnosis of equipment field detection data is realized to provide support for equipment status analysis.

[0043] The strategy generation module 11 is specifically used to generate a maintenance strategy according to the fault prediction information.

[0044] The task scheduling module 12 is specifically used to call the maintenance robot to perform inspection tasks according to the maintenance strategy. The inspection tasks include handcart circuit breaker position determination and maintenance based on gravity sensing, switch cabinet partial discharge signal detection based on image recognition, insulation resistance detection and AC withstand voltage detection.

[0045] See also Figure 2 , which is a structural diagram of a maintenance robot provided in Example 1 of the present application. Maintenance robot 2 is used to realize the functions of daily inspection, operation, replacement, transportation, comprehensive testing, maintenance operation and other functions of high-voltage switchgear. A dual current loop torque servo control strategy is adopted, combined with an elastic rigid-flexible connection mechanism, to realize its rigid-flexible coupling operation. According to the working space and safety requirements, a spatial reachable model under the constraints of the operating robot arm bounding box is obtained by training.

[0046] As a possible implementation manner, the above-mentioned maintenance robot may specifically include a control module 20, a laser navigation module 21, a visual navigation module 22 and a laser ranging module 23.

[0047] The control module 20 is specifically used to receive the inspection instruction issued by the task scheduling module of the cloud management platform 1 and start the maintenance robot to perform the inspection task. The inspection instruction includes the inspection strategy, inspection task and maintenance execution area.

[0048] The laser navigation module 21 is specifically used to obtain the position coordinate information of the maintenance robot 2 during operation. The visual navigation module 22 is specifically used to obtain the environmental information during operation of the maintenance robot. The laser ranging module is used to locate the maintenance execution area. The high-precision positioning of the maintenance robot is achieved based on the multi-sensor information fusion technology.

[0049] In addition, considering that each inspection task and maintenance execution area may be different, how to plan the most reasonable path for the maintenance robot is the premise for improving the operation safety of the maintenance robot, avoiding interference with obstacles and improving operation efficiency.

[0050] To solve the above problems, the ART method is used in the first embodiment of the present application to perform dynamic path planning of the maintenance robot. As an achievable method, the control module 20 is further used to determine the moving path of the maintenance robot according to the position coordinate information and the environmental information, and to plan and adjust the moving path of the maintenance robot in real time based on the positioning maintenance execution area.

[0051] The maintenance robot in the first embodiment of the present application uses Mecanum wheels as a walking device, and can realize actions such as walking forward, backward, left, right, and turning on the spot. However, due to the narrow space between the high-voltage switch cabinets, the maintenance robot needs to frequently change its posture when completing the inspection task. Therefore, it is crucial to realize the position adjustment and posture change of the maintenance robot in a small space. During the operation of the maintenance robot 2, the posture of the maintenance robot can also be corrected. Specifically, the above-mentioned maintenance robot 2 can also include at least one visual sensor 24, which is specifically used to obtain the actual posture of the maintenance robot during movement.

[0052] The above-mentioned control module 20 is also specifically used to perform posture correction control on the mobile posture of the maintenance robot based on the new variable universe fuzzy control algorithm according to the above-mentioned actual posture. Specifically, it may include: obtaining the deviation between the actual posture and the ideal posture of the maintenance robot, including the normal position deviation and the posture angle deviation. According to the above-mentioned deviation, the domain is adjusted in real time based on the new variable universe fuzzy control algorithm, and the steering angle of the operation center of the maintenance robot is determined. According to the above-mentioned steering angle of the operation center and the preset operation center speed, the adjustment amount based on the actual posture of the maintenance robot is determined to realize the posture correction control of the maintenance robot. Optionally, the above-mentioned ideal posture and preset operation center speed can be set according to the actual situation, and the embodiments of the present application do not make specific restrictions.

[0053] The intelligent maintenance system for high-voltage switchgear provided in the embodiment of the present application performs status monitoring, intelligent analysis and emergency response on the high-voltage switchgear through cloud management technology. It will perform status monitoring, data analysis and comprehensive intelligent analysis on a large number of high-voltage switchgear in the power system, and regularly and automatically complete various types of tests and maintenance work, so as to promptly discover and deal with defects and safety hazards in the switchgear, greatly improve the reliability of the switchgear operation, and thus ensure the long-term stable operation of the power system.

[0054] Embodiment 2

[0055] See also Figure 3 , is a schematic diagram of the structure of an intelligent maintenance system for a high-voltage switchgear provided in Embodiment 2 of the present application. Figure 3 As shown in , different from the first embodiment, the above intelligent maintenance system also includes a maintenance operation unit 4 and a safety control unit 3.

[0056] The above-mentioned maintenance operation unit 4 is specifically used to test and / or perform maintenance work on the high-voltage switchgear. The above-mentioned test work includes mechanical property test, loop resistance test, insulation resistance test and AC withstand voltage test. The above-mentioned maintenance work includes cleaning and dust removal and conductive paste application. Specifically, the maintenance operation unit 4 mainly includes a comprehensive experimental station, a maintenance operation station, a power supply equipment charging station, etc.

[0057] Among them, the power supply equipment is the power supply point for the intelligent maintenance test. It is mainly responsible for the power supply of multiple systems such as intelligent maintenance test technology and integrated cloud management technology to ensure that the intelligent maintenance test technology, integrated cloud management technology and other systems can work normally and reliably. It mainly includes two parts: normal power supply of station transformer AC and emergency power supply of battery.

[0058] The main function of the comprehensive test station is to conduct comprehensive power-off tests on the trolley circuit breaker. The main test items include mechanical property test, loop resistance test, insulation resistance test and AC withstand voltage test, etc. In the traditional working mode, the trolley circuit breaker is tested outside the switch cabinet. Each test has a designated test instrument and wiring method. The mechanical property test, loop resistance test and insulation resistance test are non-destructive tests with low test voltage and no special requirements for the surrounding environment. It is ensured that no one works on the tested equipment during the test operation. At the same time, the test instruments of the three tests are small in size and light in weight, and there are no special requirements for the layout in the comprehensive test technology. The AC withstand voltage test is a destructive test with a high test voltage. It requires the insulation materials in the cabinet to meet the standard specifications, otherwise it will cause the test high voltage to discharge to the equipment casing or other grounding bodies during the test. At the same time, the AC withstand voltage test has a large test equipment and heavy weight. The layout in the comprehensive test technology needs to consider factors such as volume, quality, discharge, and safety.

[0059] The main function of the maintenance operation station is to clean and dust the trolley circuit breaker and apply conductive paste. Cleaning and dust removal is mainly to remove dirt from the surface of the trolley circuit breaker and maintain its good operating conditions to avoid adverse working conditions such as flashover or overheating. The conductive paste application work is to apply conductive paste such as molybdenum disulfide to the contacts of the trolley circuit breaker to enhance the contact ability between the moving and static contacts of the trolley circuit breaker, and ensure that the contact heating and ablation caused by excessive contact resistance will not occur during operation. In the traditional working mode, manual cleaning and dust removal are completed on the outside of the switch cabinet with a cleaning cloth and a blower, and the conductive paste application of the trolley circuit breaker is completed with a brush. When designing the maintenance operation station, many factors such as tool application and processing flow should be considered.

[0060] Safety control unit 3 is specifically used to control the safety of the entire work process, from the determination of test conditions before starting work, the detection of safe distances during the test, to the recovery of safe working conditions after the test, etc., to all-round safety intelligent control.

[0061] The cloud management platform 1, the maintenance robot 2 and the safety control unit are all interconnected. The main function of the cloud management platform 1 is to issue and manage periodic task inspection instructions and temporary task fault elimination instructions. For example, when the switch cabinet is energized, a live inspection instruction is sent to the robot to inspect the energized operation status of the switch cabinet. In the case of a routine power outage of the switch cabinet, a power outage operation instruction is sent to the robot, and the robot is ordered to move the trolley circuit breaker to the intelligent maintenance test technology, and then the intelligent maintenance test technology is ordered to perform comprehensive maintenance tests on the trolley circuit breaker. In the event of a switch cabinet failure, a fault elimination instruction is sent to pull out the faulty trolley circuit breaker and replace the spare trolley circuit breaker with the faulty switch cabinet. All types of data information of the trolley circuit breaker in various situations are comprehensively judged by the data analysis module 10, and transmitted to the strategy generation module 11 and the task scheduling module 12 based on wireless communication technology, and then the maintenance decision and the next maintenance plan are generated. All activities of the maintenance robot and various active operations are completed under the supervision of the safety control unit.

[0062] Specifically, the above-mentioned safety control unit 3 pre-stores a maintenance room plan of the high-voltage switchgear, and the maintenance room plan is divided into at least two areas. A monitoring device is configured in each area to monitor the equipment status and live parts of the high-voltage switchgear.

[0063] Furthermore, the security management and control unit 3 may specifically include an RFID-based positioning module 30 , an alarm control module 31 and at least one monitoring terminal 32 .

[0064] The positioning module 30 is specifically used to obtain the position information of the maintenance robot in real time and determine the actual distance between the maintenance robot and the live parts of the high-voltage switch cabinet.

[0065] The alarm control module 31 is specifically used to determine whether the actual distance is less than the preset distance. If so, an alarm message is generated.

[0066] Specifically, the circuit resistance test and characteristic test of the trolley circuit breaker are non-insulation tests with low test voltage, less destructive to the equipment, and will not cause safety accidents such as high-voltage test discharge and electric shock. The wiring method of the insulation resistance test and the AC withstand voltage test is the same, that is, one end of the trolley circuit breaker is short-circuited to the test line, and the other end is short-circuited to the ground. The insulation resistance test is a DC test, so the AC withstand voltage test instrument must not be connected during the insulation test; the AC withstand voltage test is a high voltage test, so during the AC withstand voltage test, all instruments and the trolley circuit breaker must be disconnected, and keep a sufficient safe distance from the housing of the intelligent maintenance cabinet.

[0067] In addition, during the test, the loop resistance test requires the program-controlled switching program to turn the trolley circuit breaker to the closed position, and the DC voltage drop method is used to perform the loop resistance test on both sides of each phase contact. The mechanical characteristic test needs to cooperate with the program-controlled switching program. While the trolley circuit breaker is opening and closing, the characteristic meter is used to measure its opening and closing time characteristics and low-voltage action characteristics. The mechanical characteristic test requires short-circuiting one side of the circuit breaker to the ground and the other side to the measuring line, so the program-controlled switching is also required to cooperate with the mechanical part to realize this function. The loop resistance tester and the switch characteristic tester are both light in weight, so it is considered to place the two instruments on the top of the switch cabinet.

[0068] The monitoring terminal 32 is specifically used to visualize the equipment status, live parts and the above-mentioned alarm information of the high-voltage switch cabinet.

[0069] The embodiments of the present application take into account that during the maintenance of high-voltage switchgear, a large number of devices to be inspected have different equipment states, but there is no obvious difference in appearance. Through the on-site safety monitoring terminal and RFID-based positioning technology, it can be effectively determined whether a sufficient safety distance is maintained from the live parts. This technology includes RFID-based intelligent positioning, intelligent sensing monitoring based on sound and light alarms, and back-end monitoring, which can effectively ensure the safety of equipment personnel and prevent violations.

[0070] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0071] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0072] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent maintenance system for high-voltage switchgear, characterized in that: The system includes a maintenance robot and a cloud management platform; the cloud management platform includes a data analysis module, a strategy generation module and a task scheduling module; A data analysis module is used to obtain historical state parameters of the high-voltage switchgear, and to perform discriminant analysis on the historical state parameters based on a time series model and a high-dimensional random matrix model to generate fault prediction information, wherein the historical state parameters include equipment commissioning time, historical energized detection data, historical power outage detection data, and historical fault elimination detection data, and the fault prediction information includes faulty equipment, fault causes, and fault trends; the strategy generation module is used to generate a maintenance strategy based on the fault prediction information; The task scheduling module is used to call the maintenance robot to perform inspection tasks according to the maintenance strategy, and the inspection tasks include the position determination and maintenance of the trolley circuit breaker based on gravity sensing.

2. The intelligent maintenance system for high-voltage switchgear according to claim 1 is characterized in that: The data analysis module is also used to monitor the equipment status of the high-voltage switchgear according to a preset cycle, and the equipment status includes the energized state, the power-off state, and the fault-eliminating state; the task scheduling module is used to call the maintenance robot to inspect the energized operation state of the high-voltage switchgear when the high-voltage switchgear is in the energized state; to call the maintenance robot to move the high-voltage switchgear to the target area for maintenance when the high-voltage switchgear is in the power-off state; and to call the maintenance robot to replace the high-voltage switchgear when the high-voltage switchgear is in the fault-eliminating state.

3. The intelligent maintenance system for high-voltage switchgear according to claim 1 is characterized in that: The discriminant analysis of the state parameters based on the time series model and the high-dimensional random matrix model to generate fault prediction information includes: A high-dimensional random matrix is ​​constructed according to the historical state parameters, and the high-dimensional random matrix is ​​normalized, wherein the high-dimensional random matrix is ​​used to perform abnormal data detection on the historical state parameters and eliminate abnormal data; Based on the historical state parameters after eliminating abnormal data, a time series model for edge computing is constructed. The time series model is used to characterize the changing relationship between the state parameters of the high-voltage switchgear and time, so as to predict the faults of the high-voltage switchgear and generate the fault prediction information.

4. The intelligent maintenance system for high-voltage switchgear according to claim 1 is characterized in that: The maintenance robot includes a control module, a laser navigation module, a visual navigation module and a laser ranging module; The control module is used to receive and respond to the inspection instructions issued by the task scheduling module, and start the maintenance robot to perform the inspection task; wherein the inspection instruction includes the inspection strategy, inspection task and maintenance execution area; The laser navigation module is used to obtain the position coordinate information of the maintenance robot during operation; the visual navigation module is used to obtain the environmental information of the maintenance robot during operation; the laser ranging module is used to locate the maintenance execution area; The control module is further used to determine the moving path of the maintenance robot according to the position coordinate information and the environmental information, and to plan and adjust the moving path of the maintenance robot in real time based on the positioning maintenance execution area.

5. The intelligent maintenance system for high-voltage switchgear according to claim 4 is characterized in that: The maintenance robot also includes at least one visual sensor, which is used to obtain the actual posture of the maintenance robot during movement; the control module is also used to perform posture correction control on the moving posture of the maintenance robot based on the actual posture and based on a new variable domain fuzzy control algorithm.

6. The intelligent maintenance system for high-voltage switchgear according to claim 5, characterized in that: The control module performs posture correction control on the mobile posture of the maintenance robot based on the actual posture and the novel variable universe fuzzy control algorithm, including: Obtaining a deviation between the actual posture and the ideal posture, wherein the deviation includes a normal position deviation and an attitude angle deviation; According to the deviation, the discourse domain is adjusted in real time based on a novel variable discourse domain fuzzy control algorithm, and the running center steering angle of the maintenance robot is determined; According to the running center steering angle and the preset motion center speed, the actual posture adjustment amount based on the maintenance robot is determined to achieve posture correction control of the maintenance robot.

7. The intelligent maintenance system for high-voltage switchgear according to claim 1, characterized in that: The system also includes a safety management and control unit, which pre-stores a floor plan of a maintenance room of a high-voltage switch cabinet. The floor plan of the maintenance room is divided into at least two areas, and a monitoring device is configured in each area for monitoring the equipment status and live parts of the high-voltage switch cabinet.

8. The intelligent maintenance system for high-voltage switchgear according to claim 7, characterized in that: The security management and control unit also includes a positioning module, an alarm control module and at least one monitoring terminal; The positioning module is used to obtain the position information of the maintenance robot in real time and determine the actual distance between the maintenance robot and the live part of the high-voltage switch cabinet; The alarm control module is used to determine whether the actual distance is less than the preset distance; if so, generate an alarm message; The monitoring terminal is used to visualize the equipment status, live parts and alarm information of the high-voltage switch cabinet.

9. The intelligent maintenance system for high-voltage switchgear according to claim 1, characterized in that: The system also includes a maintenance operation unit, which is used to perform tests and / or maintenance work on the high-voltage switchgear. The test work includes mechanical property tests, loop resistance tests, insulation resistance tests and AC withstand voltage tests; the maintenance work includes cleaning, dust removal and conductive paste application.

10. The intelligent maintenance system for high-voltage switchgear according to claim 1, characterized in that: The inspection tasks also include local discharge signal detection, insulation resistance detection and AC withstand voltage detection of high-voltage switch cabinets.