Zinc oxide arrester operation state simulation method and system based on knowledge graph

Abstract

The application discloses a zinc oxide arrester operation state simulation method and system based on a knowledge graph and belongs to the field of intelligent operation and maintenance of electrical equipment. The defect feature data parameters of the arrester obtained by the prior art scheme are relatively single, and the accuracy of the arrester operation state evaluation model prediction is affected. The zinc oxide arrester operation state simulation method based on the knowledge graph constructs a key quantity extraction model, an arrester knowledge graph model, an arrester state function integration model and an arrester operation state simulation model, obtains the operation state data of a certain zinc oxide arrester, visualizes the data related to the key state quantity of the arrester in the form of a "knowledge graph", and thus the key state quantity of the arrester and the arrester state feature parameters can be objectively, comprehensively and accurately obtained, and therefore the accuracy of the arrester operation state simulation can be effectively improved, and effective reference can be provided for the daily operation maintenance and overhaul of the zinc oxide arrester.

Description

Technical Field

[0001] This invention relates to a method and system for simulating the operating status of zinc oxide surge arresters based on knowledge graphs, belonging to the field of intelligent operation and maintenance of electrical equipment. Background Technology

[0002] As the scale of surge arrester assets continues to increase, the workload of surge arrester operation and maintenance has increased significantly, leading to increased risks from "over-maintenance" and "under-maintenance" of surge arresters, which threatens the reliability of power grid operation.

[0003] Chinese Patent (Publication No.: CN112255484B) discloses a method and system for online monitoring and evaluation of surge arrester operating status. The method includes acquiring online and historical operating status data of the surge arrester; filtering out surge arrester defect characteristic data parameters and their variation patterns; determining surge arrester operating status evaluation indicators; establishing a surge arrester operating status evaluation model; inputting historical operating status data into the surge arrester operating status evaluation model for model training; and inputting online operating status data as real-time input to the surge arrester operating status evaluation model for prediction, thereby achieving evaluation of the surge arrester equipment operating status and prediction of its development trend. The method analyzes the magnitude and amplification factor response of historical operating status data and its higher harmonic components under different insulation degradation states, statistically analyzes the parameters that show significant changes in the operating status data and its higher harmonic components under different insulation degradation states as surge arrester defect characteristic data parameters, and obtains their variation patterns.

[0004] However, the above scheme only uses the operating status data under different insulation degradation states as the parameter of the arrester defect feature data. The relatively simple parameter of the arrester defect feature data will affect the accuracy of the arrester operating status assessment model prediction.

[0005] If the selection of further surge arrester defect characteristic data parameters is not objective or comprehensive enough, it will lead to inaccurate assessment of the surge arrester's operating status, which in turn will not provide an effective reference for the daily operation, maintenance and repair of zinc oxide surge arresters, and will not be able to monitor potential hazards of surge arresters in a timely manner, and will not be able to reduce the risk of surge arrester failure in a timely manner.

[0006] The information disclosed in this background section is only for understanding the background of the inventive concept, and therefore may include information that does not constitute prior art. Summary of the Invention

[0007] To address the aforementioned problems, or one of them, the present invention aims to provide a knowledge graph-based method for simulating the operating status of zinc oxide surge arresters. This method involves constructing a key quantity extraction model, a surge arrester knowledge graph model, a surge arrester state function integration model, and a surge arrester operating status simulation model. The method processes state maintenance data to extract key state quantities that characterize the state of a specific zinc oxide surge arrester. Then, it searches for these key state quantities to obtain surge arrester state characteristic parameters and determines several weighting factors and evaluation functions for these parameters. These weighting factors and evaluation functions are then integrated to obtain a unified evaluation function for a specific zinc oxide surge arrester. Finally, the unified evaluation function is calculated to obtain the operating status data of the specific zinc oxide surge arrester. Therefore, this method effectively reduces discrepancies caused by individual experience in maintenance and repair work, and significantly improves the efficiency and accuracy of maintenance and repair work.

[0008] To address the aforementioned problems, or one of them, the second objective of this invention is to provide a knowledge graph-based zinc oxide surge arrester operation status simulation system. This system processes state-based maintenance data by setting up a key quantity extraction module, a surge arrester knowledge graph module, a surge arrester state function integration module, and a surge arrester operation status simulation module. It extracts key state quantities that characterize the state of a specific zinc oxide surge arrester; then searches for these key state quantities to obtain surge arrester state characteristic parameters and determines several weighting factors and evaluation functions for these parameters; finally, it integrates these weighting factors and evaluation functions to obtain a unified evaluation function for a specific zinc oxide surge arrester; and finally, it calculates the unified evaluation function to obtain the operation status data of the specific zinc oxide surge arrester. Therefore, this system effectively reduces discrepancies caused by individual experience in maintenance and repair work, and effectively improves the efficiency and accuracy of maintenance and repair work.

[0009] To address the aforementioned problems, or one of the aforementioned problems, the third objective of this invention is to provide a method and system for simulating the operating status of zinc oxide surge arresters by visualizing data related to key state quantities of surge arresters in the form of a "knowledge graph." This allows for the objective, comprehensive, and accurate acquisition of key state quantities and state characteristic parameters of surge arresters, thereby effectively improving the accuracy of surge arrester operating status simulation. It provides a valid reference for the daily operation, maintenance, and repair of zinc oxide surge arresters, enabling timely monitoring of potential hazards in surge arresters and timely reduction of surge arrester failure risks.

[0010] To achieve one of the above objectives, the first technical solution of the present invention is as follows:

[0011] A knowledge graph-based simulation method for the operating status of zinc oxide surge arresters.

[0012] Includes the following steps:

[0013] The first step is to obtain the status and maintenance data of a specific zinc oxide surge arrester;

[0014] The second step is to use a pre-built key quantity extraction model to process the condition operation and maintenance data and extract the key state quantities of the arrester that can characterize the state of a certain zinc oxide arrester.

[0015] The third step involves searching for key state variables of the surge arrester using a pre-built knowledge graph model, obtaining the state characteristic parameters of the surge arrester, and determining several weighting factors and evaluation functions for the state characteristic parameters of the surge arrester.

[0016] The fourth step is to integrate several weighting factors and evaluation functions based on the pre-constructed arrester state function integration model to obtain a unified evaluation function for a zinc oxide arrester.

[0017] The fifth step involves using a pre-built simulation model of the arrester's operating status to calculate a unified evaluation function, thereby obtaining the operating status data of a specific zinc oxide arrester and realizing knowledge graph-based simulation of the zinc oxide arrester's operating status.

[0018] This invention, through continuous exploration and experimentation, constructs a key quantity extraction model, a surge arrester knowledge graph model, a surge arrester state function integration model, and a surge arrester operation state simulation model. It processes state-based operation and maintenance data to extract key state quantities that characterize the state of a specific zinc oxide surge arrester. Then, it searches for these key state quantities to obtain surge arrester state characteristic parameters and determines several weighting factors and evaluation functions for these parameters. These weighting factors and evaluation functions are then integrated to obtain a unified evaluation function for a specific zinc oxide surge arrester. Finally, the unified evaluation function is calculated to obtain the operation state data of a specific zinc oxide surge arrester. Therefore, this invention effectively reduces discrepancies caused by individual experience in operation and maintenance work, significantly improving the efficiency and accuracy of operation and maintenance, and providing a reference for achieving more intelligent daily operation, maintenance, and repair of power equipment.

[0019] Furthermore, this invention first processes the condition-based operation and maintenance data through a key quantity extraction model to extract key state quantities of the surge arrester that can characterize the state of a certain zinc oxide surge arrester. Then, using a surge arrester knowledge graph model, the surge arrester state characteristic parameters involving key state quantities are visualized in the form of a "knowledge graph". This allows for the objective, comprehensive, and accurate acquisition of key state quantities and state characteristic parameters of the surge arrester, thus effectively improving the accuracy of surge arrester operation state simulation. This provides a valid reference for the daily operation, maintenance, and repair of zinc oxide surge arresters, enabling timely monitoring of potential hazards and timely reduction of surge arrester failure risks. In this way, the condition-based maintenance of surge arresters is combined with surge arrester reliability assessment, achieving the goal of improving the inherent reliability and safety of surge arresters with minimal maintenance resource consumption.

[0020] Furthermore, this invention provides a knowledge graph-based simulation method for the operating status of zinc oxide surge arresters. By constructing a simulation model of the operating status of zinc oxide surge arresters using state variables, the method simulates and evaluates the operating status of surge arresters, thereby solving the problem of "over-maintenance" or "under-maintenance" of electrical equipment in actual operation and maintenance, and thus achieving precise operation and maintenance and condition-based maintenance centered on reliability.

[0021] As a preferred technical measure:

[0022] The method for obtaining status maintenance data in the first step is as follows:

[0023] Maintenance data was obtained by monitoring the equalizing ring, resistors, and external insulation components.

[0024] Maintenance data two was obtained by monitoring the sealing ring, the air extraction leak detection hole, and the flange;

[0025] By reading data from the discharge counter and leakage current meter, we obtain maintenance data three;

[0026] The three operation and maintenance data are merged to form the status operation and maintenance data.

[0027] As a preferred technical measure:

[0028] In the second step, the method for extracting the key state variables of a surge arrester that can characterize the state of a certain zinc oxide surge arrester is as follows:

[0029] Step 21: Obtain data from several on-site cases;

[0030] Step 22: Classify and process the on-site case data to obtain a formatted fault template;

[0031] Step 23: Based on the fault modules, establish a fault case library for zinc oxide surge arresters;

[0032] Step 23: Based on the zinc oxide surge arrester fault case library, filter the condition-based operation and maintenance data to obtain the key state quantities of the surge arrester that can characterize the state of a certain zinc oxide surge arrester.

[0033] Critical condition quantities include at least electrical performance and / or sealing performance and / or accessory performance and / or family defects.

[0034] As a preferred technical measure:

[0035] In the third step, the method for constructing the surge arrester knowledge graph model is as follows:

[0036] Step 31: Obtain key information from the zinc oxide surge arrester fault case database;

[0037] The key information includes at least the voltage level and / or the substation to which it belongs and / or the surge arrester model and / or the manufacturer and / or the commissioning date and / or the fault date and / or the service life and / or the function of the faulty component and / or the specific faulty component and / or the main fault cause and / or the detection method.

[0038] Step 32: Based on the key information, construct a graph database with nodes, edges, and attributes;

[0039] The graphical database represents a system or a specific fault mode of zinc oxide surge arrester through nodes; or / and, the graphical database represents the condition simulation and maintenance knowledge of zinc oxide surge arrester through nodes.

[0040] Graph databases are used to represent the logical connections or dependencies between nodes;

[0041] Graph databases use attributes to represent the definition information of nodes or edges;

[0042] Step 33: Based on the graph database, construct a knowledge network graph structure of fault characteristics for zinc oxide surge arresters;

[0043] Or / and, based on the graph database, construct a knowledge network graph structure for the condition simulation and maintenance of zinc oxide surge arresters;

[0044] Step 34: Based on the knowledge network structure of zinc oxide surge arrester fault characteristics and / or the knowledge network structure of zinc oxide surge arrester state simulation and maintenance, establish a complete node knowledge graph model of the surge arrester to realize the searchability of key state quantities of the surge arrester.

[0045] As a preferred technical measure:

[0046] The method for determining several weighting factors and evaluation functions for the state characteristic parameters of surge arresters is as follows:

[0047] S31, Obtain the critical state parameters of the surge arrester. The critical state parameters of the surge arrester include at least electrical performance, sealing performance, accessory performance, and family defects.

[0048] S32. Based on the key state variables of the surge arrester, search the surge arrester knowledge graph model to obtain the state characteristic parameters of the surge arrester.

[0049] S33 classifies the state characteristic parameters of the surge arrester into important state parameters, general state parameters, and minor state parameters, and assigns weights to them respectively.

[0050] As a preferred technical measure:

[0051] The surge arrester's conditional parameters include at least the body temperature rise, total current, resistive current, DC 1mA voltage, and 0.75U. 1mA Leakage current, equalizing ring condition, external insulation condition, sealing ring condition, drainage design, base insulation resistance, discharge counter condition, leakage current meter condition, and family defects;

[0052] The weights of important state variables are k1 = 0.5, those of general state variables are k2 = 0.3, and those of minor state variables are k3 = 0.2.

[0053] As a preferred technical measure:

[0054] In the fourth step, the unified evaluation function is composed of several single-state evaluation functions;

[0055] Several single-state evaluation functions include the body temperature rise evaluation function, the total current evaluation function, the resistive current evaluation function, the DC 1mA voltage evaluation function, and the 0.75U... 1mA Leakage current evaluation function, equalizing ring status evaluation function, external insulation status evaluation function, sealing ring status evaluation function, drainage design evaluation function, base insulation resistance evaluation function, discharge counter status evaluation function, leakage current meter status evaluation function, and family defect evaluation function;

[0056] The formula for calculating the body temperature rise evaluation function is as follows:

[0057]

[0058] Where x is the measured temperature difference / maximum allowable temperature difference.

[0059] As a preferred technical measure:

[0060] The method for obtaining the operating status data of a zinc oxide surge arrester in the fifth step is as follows:

[0061] Step 51: Set the full score for evaluating the operating status of zinc oxide surge arresters. The full score is A.

[0062] Step 52: Set the deduction value based on the full score and weight settings;

[0063] The maximum deduction for important state variables shall not exceed three-fifths of A, the maximum deduction for general state variables shall not exceed one-third of A, and the maximum deduction for minor state variables shall not exceed one-tenth of A.

[0064] Step 53: Based on the deduction values ​​and the evaluation functions of various state variables, obtain the total evaluation score:

[0065]

[0066] Where k1 is the weight of important state variables, k2 is the weight of general state variables, k3 is the weight of minor state variables, and f i (x) is the evaluation function for important state variables, g i (x) is the evaluation function for general state variables, h i (x) is the evaluation function for minor state variables;

[0067] Step 54: Based on the total evaluation score and the maximum deduction, determine the operating status level of a certain zinc oxide surge arrester, obtain the operating status data of a certain zinc oxide surge arrester, and realize the simulation of the operating status of zinc oxide surge arresters based on knowledge graph.

[0068] As a preferred technical measure:

[0069] The method for determining the operating status level of a zinc oxide surge arrester is as follows:

[0070] The operational status levels are divided into normal status, alert status, abnormal status, and critical status;

[0071] If the score for a certain important state quantity of the surge arrester reaches the maximum value, the final operational evaluation level will be reduced by three levels based on the level determined by the total evaluation score.

[0072] If it is a general state variable, the final operational evaluation level will be reduced by two levels based on the level determined by the total evaluation score;

[0073] If it is a minor state variable, the final operational evaluation level will be reduced by one level based on the level determined by the total evaluation score;

[0074] If the deductions for two or more state variables reach the maximum value, the final operational evaluation level will be reduced by the cumulative level.

[0075] To achieve one of the above objectives, the second technical solution of the present invention is as follows:

[0076] A knowledge graph-based simulation system for the operating status of zinc oxide surge arresters includes a key quantity extraction module, a surge arrester knowledge graph module, a surge arrester state function integration module, and a surge arrester operating status simulation module.

[0077] The key quantity extraction module is used to process the status operation and maintenance data and extract the key status quantities of the arrester that can characterize the status of a certain zinc oxide arrester.

[0078] The surge arrester knowledge graph module is used to search for key state variables of surge arresters, obtain surge arrester state characteristic parameters, and determine several weighting factors and evaluation functions for surge arrester state characteristic parameters.

[0079] The surge arrester state function integration module is used to integrate several weighting factors and evaluation functions to obtain a unified evaluation function for a zinc oxide surge arrester.

[0080] The surge arrester operation status simulation module is used to calculate a unified evaluation function to obtain the operation status data of a certain zinc oxide surge arrester, and realize the operation status simulation of zinc oxide surge arresters based on knowledge graph.

[0081] This invention, through continuous exploration and experimentation, processes state-based maintenance data by setting up a key quantity extraction module, a surge arrester knowledge graph module, a surge arrester state function integration module, and a surge arrester operation state simulation module. It extracts key state quantities that characterize the state of a specific zinc oxide surge arrester. Then, it searches for these key state quantities to obtain surge arrester state characteristic parameters and determines several weighting factors and evaluation functions for these parameters. These weighting factors and evaluation functions are then integrated to obtain a unified evaluation function for a specific zinc oxide surge arrester. Finally, the unified evaluation function is calculated to obtain the operation state data of the specific zinc oxide surge arrester. Therefore, this invention effectively reduces discrepancies caused by individual experience in maintenance and repair work, significantly improving the efficiency and accuracy of maintenance and repair, and providing a reference for achieving more intelligent daily operation, maintenance, and repair of power equipment.

[0082] Furthermore, this invention utilizes a key quantity extraction module and a surge arrester knowledge graph module to visualize the data related to the key state quantities of the surge arrester in the form of a "knowledge graph." This allows for the objective, comprehensive, and accurate acquisition of the key state quantities and state characteristic parameters of the surge arrester, thereby effectively improving the accuracy of surge arrester operation state simulation. It provides a valuable reference for the daily operation, maintenance, and repair of zinc oxide surge arresters, enabling timely monitoring of potential hazards and timely reduction of surge arrester failure risks. This combines surge arrester condition-based maintenance with surge arrester reliability assessment, achieving the goal of improving the inherent reliability and safety of surge arresters with minimal maintenance resource consumption.

[0083] Compared with existing technical solutions, the present invention has the following beneficial effects:

[0084] This invention, through continuous exploration and experimentation, constructs a key quantity extraction model, a surge arrester knowledge graph model, a surge arrester state function integration model, and a surge arrester operation state simulation model. It processes state-based operation and maintenance data to extract key state quantities that characterize the state of a specific zinc oxide surge arrester. Then, it searches for these key state quantities to obtain surge arrester state characteristic parameters and determines several weighting factors and evaluation functions for these parameters. These weighting factors and evaluation functions are then integrated to obtain a unified evaluation function for a specific zinc oxide surge arrester. Finally, the unified evaluation function is calculated to obtain the operation state data of a specific zinc oxide surge arrester. Therefore, this invention effectively reduces discrepancies caused by individual experience in operation and maintenance work, significantly improving the efficiency and accuracy of operation and maintenance, and providing a reference for achieving more intelligent daily operation, maintenance, and repair of power equipment.

[0085] This invention, through continuous exploration and experimentation, processes state-based maintenance data by setting up a key quantity extraction module, a surge arrester knowledge graph module, a surge arrester state function integration module, and a surge arrester operation state simulation module. It extracts key state quantities that characterize the state of a specific zinc oxide surge arrester. Then, it searches for these key state quantities to obtain surge arrester state characteristic parameters and determines several weighting factors and evaluation functions for these parameters. These weighting factors and evaluation functions are then integrated to obtain a unified evaluation function for a specific zinc oxide surge arrester. Finally, the unified evaluation function is calculated to obtain the operation state data of the specific zinc oxide surge arrester. Therefore, this invention effectively reduces discrepancies caused by individual experience in maintenance and repair work, significantly improving the efficiency and accuracy of maintenance and repair, and providing a reference for achieving more intelligent daily operation, maintenance, and repair of power equipment.

[0086] Furthermore, this invention first processes the condition-based operation and maintenance data through a key quantity extraction model to extract key state quantities of the surge arrester that can characterize the state of a certain zinc oxide surge arrester. Then, using a surge arrester knowledge graph model, the surge arrester state characteristic parameters involving key state quantities are visualized in the form of a "knowledge graph." This allows for the objective, comprehensive, and accurate acquisition of key state quantities and state characteristic parameters of the surge arrester, thus effectively improving the accuracy of surge arrester operation state simulation. This provides a valid reference for the daily operation, maintenance, and repair of zinc oxide surge arresters, enabling timely monitoring of potential hazards and timely reduction of surge arrester failure risks. In this way, the condition-based maintenance of surge arresters is combined with surge arrester reliability assessment, achieving the goal of improving the inherent reliability and safety of surge arresters with minimal maintenance resource consumption. Attached Figure Description

[0087] Figure 1 This is a flowchart of a knowledge graph-based simulation method for the operating status of zinc oxide surge arresters according to the present invention.

[0088] Figure 2 This is another flowchart of the knowledge graph-based simulation method for the operating status of zinc oxide surge arresters according to the present invention;

[0089] Figure 3 This is a schematic diagram of the knowledge graph of fault characteristics and condition-based maintenance of zinc oxide surge arresters according to the present invention;

[0090] Figure 4 This is a flowchart for evaluating the operating status of the zinc oxide surge arrester of the present invention. Detailed Implementation

[0091] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0092] Conversely, this invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of the invention as defined in the claims. Furthermore, to provide a better understanding of the invention, certain specific details are described in detail below. However, those skilled in the art will fully understand the invention even without these detailed descriptions.

[0093] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. The term "or / and" as used herein includes any and all combinations of one or more of the associated listed items.

[0094] like Figure 1 As shown, this is the first specific embodiment of the knowledge graph-based simulation method for the operating state of zinc oxide surge arresters according to the present invention:

[0095] A knowledge graph-based simulation method for the operating status of zinc oxide surge arresters.

[0096] Includes the following steps:

[0097] The first step is to obtain the status and maintenance data of a specific zinc oxide surge arrester;

[0098] The second step is to use a pre-built key quantity extraction model to process the condition operation and maintenance data and extract the key state quantities of the arrester that can characterize the state of a certain zinc oxide arrester.

[0099] The third step involves searching for key state variables of the surge arrester using a pre-built knowledge graph model, obtaining the state characteristic parameters of the surge arrester, and determining several weighting factors and evaluation functions for the state characteristic parameters of the surge arrester.

[0100] The fourth step is to integrate several weighting factors and evaluation functions based on the pre-constructed arrester state function integration model to obtain a unified evaluation function for a zinc oxide arrester.

[0101] The fifth step involves using a pre-built simulation model of the arrester's operating status to calculate a unified evaluation function, thereby obtaining the operating status data of a specific zinc oxide arrester and realizing knowledge graph-based simulation of the zinc oxide arrester's operating status.

[0102] A second specific embodiment of the knowledge graph-based simulation method for the operating status of zinc oxide surge arresters according to this invention:

[0103] A knowledge graph-based simulation method for the operating status of zinc oxide surge arresters includes the following steps:

[0104] S1. Establish a fault case library for zinc oxide surge arresters through methods such as on-site case collection, and classify and organize fault cases according to the case library template.

[0105] S2, based on the formatted fault case library that has been classified in S1, proposes key state quantities that can accurately reflect the state of the surge arrester.

[0106] S3, based on the key state quantities of electrical equipment determined in S2, uses the graph database Neo4j to build a knowledge graph of fault characteristics and condition-based maintenance for zinc oxide surge arresters;

[0107] S4, based on the fault characteristics and condition-based maintenance knowledge graph built in S3, introduces the following parameters: body temperature rise, total current, resistive current, DC 1mA voltage, and 0.75U. 1mA Leakage current, equalizing ring condition, external insulation condition, sealing ring condition, drainage design, base insulation resistance, discharge counter condition, leakage current meter condition, and family defects are used as state characteristic parameters of the surge arrester, and the weighting factors and evaluation functions of each state quantity are determined.

[0108] S5 integrates the evaluation functions of each state quantity determined in S4 into a unified evaluation function for electrical equipment, and builds a health status assessment model for zinc oxide surge arresters.

[0109] S6 verifies the zinc oxide surge arrester health status assessment model built in S5 using existing engineering operation and maintenance data, enabling it to output the surge arrester health status based on input status information, realizing knowledge graph-based simulation of zinc oxide surge arrester operation status, and providing a basis for differentiated maintenance of zinc oxide surge arresters.

[0110] This invention provides a knowledge graph-based simulation method for the operating status of zinc oxide surge arresters to solve the problem of "over-maintenance" or "under-maintenance" of electrical equipment in actual operation and maintenance, thereby achieving precise operation and maintenance.

[0111] A specific embodiment of the present invention for building a fault case library of zinc oxide surge arresters:

[0112] In step S1, the establishment of the zinc oxide surge arrester fault case library is based on the investigation of 110kV, 220kV, and 500kV zinc oxide surge arrester fault cases that occurred in various substations.

[0113] The formatted fault case library mainly collects statistical information from eleven aspects: voltage level, substation, surge arrester model, manufacturer, commissioning date, fault date, years of operation, function of faulty components (sealing, electrical, etc.), specific faulty components, main causes of fault, and detection method.

[0114] One specific embodiment of the present invention selects key state quantities:

[0115] In step S2, based on the zinc oxide surge arrester fault case library built in S1, the key state parameters of the health status of the zinc oxide surge arrester are determined through data statistical analysis, and should be selected from four aspects: electrical performance, sealing performance, accessory performance, and family defects.

[0116] A specific embodiment of the present invention for constructing a knowledge graph of zinc oxide surge arresters:

[0117] In step S3, based on the fault characteristics of zinc oxide surge arresters obtained in S2, the Neo4j platform will be used to construct a knowledge graph of zinc oxide surge arrester fault characteristics and a condition-based maintenance knowledge graph from six dimensions: knowledge acquisition, knowledge fusion, knowledge storage, query-based semantic understanding, knowledge retrieval, and visualization. The specific steps are as follows:

[0118] S3.1 integrates and processes relevant knowledge from the fault case library, retaining eleven key information aspects: voltage level, substation, surge arrester model, manufacturer, commissioning date, fault date, years of operation, function of faulty component (sealing, electrical, etc.), specific faulty component group, main fault cause, and detection method.

[0119] S3.2 utilizes Neo4j to store the key information integrated in S3.1. Since the model built by Neo4j includes three units: nodes, edges, and attributes, nodes, edges, and attributes can be used to represent a certain system or a specific fault mode of the zinc oxide surge arrester, the logical association or subordinate relationship between each node, and the definition of nodes or relationships.

[0120] Furthermore, a graph database is created based on the above model relationships, a network graph structure is constructed, and the ontology can be viewed or modified by accessing the ontology port;

[0121] S3.3, the knowledge graph of fault characteristics of zinc oxide surge arresters and the knowledge graph of condition assessment and maintenance of zinc oxide surge arresters are transplanted into HTML files to establish a complete node knowledge graph and realize the searchability of relevant state quantities.

[0122] A specific embodiment of the present invention for determining specific state variables and evaluation functions:

[0123] In step S4, based on the complete knowledge graph built in S3, specific state quantities and evaluation functions are determined from four aspects: sealing performance, electrical performance, accessory performance, and family defects of zinc oxide surge arresters. This specifically includes the following steps:

[0124] S4.1 According to the statistics of the zinc oxide surge arrester failure case database, the main components of the electrical system that fail include the equalizing ring, the resistor element, and the external insulation. Then, evaluation criteria are set according to the characteristics of these three components.

[0125] S4.2 Select the sealing ring, the air extraction leak detection hole, and the flange as the three key state variables in the sealing system;

[0126] S4.3 Select the attachments (discharge counter and leakage current meter) and family defects as critical state quantities;

[0127] S4.4 categorizes the key state quantities of the aforementioned electrical performance, sealing performance, accessory performance, and family defects into three categories: important state quantities, general state quantities, and minor state quantities. Weights are assigned to different state quantities, and maximum deduction values ​​are specified.

[0128] A specific embodiment of the present invention for scoring zinc oxide surge arresters:

[0129] The health status of zinc oxide surge arresters is divided into four categories: "Normal," "Caution," "Abnormal," and "Severe." The arresters are scored according to the weights and maximum deduction values ​​specified in S4. The scoring process requires attention to the following: If the deduction for a critical status parameter of the arrester reaches its maximum value, the final health evaluation status should be three levels lower than the original status. If it is a general status parameter, the final evaluation will decrease by two levels; if it is a minor status parameter, the final evaluation will decrease by one level. If the deduction for two or more status parameters reaches its maximum value, the decrease in status evaluation levels will be cumulative.

[0130] Based on the zinc oxide surge arrester fault case library, typical fault information is selected and scored. The scoring results are compared with the actual operation and maintenance results to verify the accuracy of the scoring and realize the health status evaluation result by inputting the status information of the surge arrester.

[0131] This invention's method is based on knowledge graphs. It constructs a knowledge graph of zinc oxide arrester fault characteristics and a knowledge graph of condition-based maintenance based on an existing database of zinc oxide arrester fault cases. This enables functions such as keyword search and node classification for opening and closing. It identifies state variables with varying weights and sets an evaluation function for each state variable, ultimately deriving a total evaluation function. This function can be used to input the state variable information of the zinc oxide arrester to obtain the arrester's health status, providing a reasonable reference for the arrester's operation, maintenance, and differentiated repair work.

[0132] like Figure 2 As shown, this is the third specific embodiment of the knowledge graph-based simulation method for the operating state of zinc oxide surge arresters according to the present invention:

[0133] A knowledge graph-based simulation method for the operating status of zinc oxide surge arresters, comprising the following steps:

[0134] Step 1: Build a fault case library.

[0135] A database of zinc oxide surge arrester failure cases was established through methods such as on-site case collection, and failure cases were categorized and organized according to the database template.

[0136] Step 2: Determine the critical state variables.

[0137] Based on a formatted fault case library that has been categorized, key state variables that can accurately reflect the state of surge arresters are proposed.

[0138] Step 3: Build a knowledge graph.

[0139] Based on the determined key state variables of electrical equipment, the Neo4j platform is used to construct a knowledge graph of fault characteristics and a condition-based maintenance knowledge graph for zinc oxide surge arresters, encompassing six dimensions: knowledge acquisition, knowledge fusion, knowledge storage, query-based semantic understanding, knowledge retrieval, and visualization. This step further includes:

[0140] 3.1 The relevant knowledge in the fault case library is integrated and processed, retaining eleven key information aspects: voltage level, substation, surge arrester model, manufacturer, commissioning date, fault date, years of operation, function of faulty component (sealing, electrical, etc.), specific faulty component group, main fault cause, and detection method.

[0141] 3.2 Utilize Neo4j to store the key information integrated in S3.1. Since the model constructed by Neo4j includes three units: nodes, edges, and attributes, nodes, edges, and attributes can be used to represent a certain system or a specific fault mode of the zinc oxide surge arrester, the logical association or subordinate relationship between each node, and the definition of nodes or relationships;

[0142] 3.3 Based on the above model relationships, create a graph database, construct a network graph structure, and view or modify it by accessing the ontology port;

[0143] 3.4 The knowledge graph of fault characteristics of zinc oxide surge arresters and the knowledge graph of condition assessment and maintenance of zinc oxide surge arresters are transplanted into HTML files to establish a complete node knowledge graph and realize the searchability of relevant state variables.

[0144] This invention, based on knowledge graphs, focuses on six modules: knowledge acquisition, knowledge fusion, knowledge storage, knowledge query, knowledge retrieval, and visualization. It utilizes the Neo4j platform to construct a knowledge graph of fault characteristics and a condition-based maintenance knowledge graph for zinc oxide surge arresters, enabling functions such as keyword search, node annotation, and node classification / opening / closing. (See also...) Figure 3 The purpose of constructing a knowledge graph is primarily to provide users with a semi-intelligent and rapid means of detecting the status of surge arresters, reducing discrepancies caused by individual experience in operation and maintenance work, improving the efficiency and accuracy of operation and maintenance work, and providing a reference for achieving more intelligent daily operation, maintenance, and repair of power equipment.

[0145] Step 4: Determine the weights and evaluation functions for each state variable.

[0146] Based on the established fault characteristics and condition-based maintenance knowledge graph, the following parameters are introduced: body temperature rise, total current, resistive current, DC 1mA voltage, and 0.75U. 1mA Leakage current, equalizing ring condition, external insulation condition, sealing ring condition, drainage design, base insulation resistance, discharge counter condition, leakage current meter condition, and family defects are used as state characteristic parameters of the surge arrester, and the weighting factors and evaluation functions of each state quantity are determined.

[0147] Step 5: Build a health status assessment model for zinc oxide surge arresters.

[0148] The established evaluation functions for each state variable are integrated into a unified evaluation function for electrical equipment, and a health status assessment model for zinc oxide surge arresters is built.

[0149] Step 6, Model Validation.

[0150] The health status assessment model for zinc oxide surge arresters is validated by using actual operation and maintenance data from existing projects, enabling it to output the health status of the surge arrester based on the input status information, thus providing a basis for differentiated maintenance of zinc oxide surge arresters.

[0151] like Figure 4 As shown, a specific embodiment of the present invention is used to assess the health status of a zinc oxide surge arrester:

[0152] A method for assessing the health status of a zinc oxide surge arrester includes the following steps:

[0153] Step 1, Selecting state variables.

[0154] Based on the analysis results of the zinc oxide surge arrester fault case database and the functional system classification of surge arresters, a health status assessment of zinc oxide surge arresters is conducted in four aspects: sealing performance, electrical performance, accessory performance, and family-related defects.

[0155] Step 2: Establishment of state quantity evaluation function and introduction of weighting factors.

[0156] The assessment of the health status of zinc oxide surge arresters includes: electrical performance, sealing performance, accessory performance, and family-related defects; key state quantities include the condition of the equalizing ring, body temperature rise, total current, resistive current, DC 1mA voltage, and 0.75U. 1mA The following should be considered: leakage current, external insulation condition, sealing ring condition, presence or absence of drainage design, base insulation condition, discharge counter and leakage current meter condition, and presence of family-related defects.

[0157] The above state variables are classified into important state variables, general state variables, and minor state variables, and weights are assigned to them respectively. The weight of important state variables is k1 = 0.5, the weight of general state variables is k2 = 0.3, and the weight of minor state variables is k3 = 0.2.

[0158] Step 3: Construct a single-state evaluation function.

[0159] Taking the body temperature rise as an example, the independent variable x is taken as the measured temperature difference / maximum allowable temperature difference. Its evaluation function is:

[0160]

[0161] The evaluation functions for the other key state variables are the same.

[0162] Step 4: Build a health status assessment model for zinc oxide surge arresters.

[0163] The health status evaluation of zinc oxide surge arresters has a maximum score of 100 points. The maximum deduction for each status quantity varies depending on its category. Based on weighting, the maximum deduction for important status quantities is no more than 60 points, for general status quantities no more than 30 points, and for minor status quantities no more than 10 points. Status quantities that cannot be determined are left undeducted. Finally, the total evaluation score is obtained based on the evaluation formulas for each status quantity.

[0164]

[0165] A system embodiment applying the method of the present invention:

[0166] A knowledge graph-based simulation system for the operating status of zinc oxide surge arresters includes a key quantity extraction module, a surge arrester knowledge graph module, a surge arrester state function integration module, and a surge arrester health status simulation module.

[0167] The key quantity extraction module is used to process the status operation and maintenance data and extract the key status quantities of the arrester that can characterize the status of a certain zinc oxide arrester.

[0168] The surge arrester knowledge graph module is used to search for key state variables of surge arresters, obtain surge arrester state characteristic parameters, and determine several weighting factors and evaluation functions for surge arrester state characteristic parameters.

[0169] The surge arrester state function integration module is used to integrate several weighting factors and evaluation functions to obtain a unified evaluation function for a zinc oxide surge arrester.

[0170] The surge arrester health status simulation module is used to calculate a unified evaluation function to obtain the health status data of a certain zinc oxide surge arrester, and realize the simulation of the operating status of zinc oxide surge arresters based on knowledge graph.

[0171] An embodiment of a device applying the method of the present invention:

[0172] A computer device comprising:

[0173] One or more processors;

[0174] Storage device for storing one or more programs;

[0175] When the one or more programs are executed by the one or more processors, the one or more processors implement the above-described knowledge graph-based simulation method for the operating state of zinc oxide surge arresters.

[0176] An embodiment of a computer medium applying the method of the present invention:

[0177] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned knowledge graph-based simulation method for the operating state of a zinc oxide surge arrester.

[0178] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied 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.

[0179] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0180] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0181] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0182] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A knowledge graph-based simulation method for the operating status of zinc oxide surge arresters. Its features are, Includes the following steps: The first step is to obtain the status and maintenance data of a specific zinc oxide surge arrester; The second step is to use a pre-built key quantity extraction model to process the condition operation and maintenance data and extract the key state quantities of the arrester that can characterize the state of a certain zinc oxide arrester. The third step involves searching for key state variables of the surge arrester using a pre-built knowledge graph model, obtaining the state characteristic parameters of the surge arrester, and determining several weighting factors and evaluation functions for the state characteristic parameters of the surge arrester. The fourth step is to integrate several weighting factors and evaluation functions based on the pre-constructed arrester state function integration model to obtain a unified evaluation function for a zinc oxide arrester. The fifth step involves using a pre-built simulation model of the arrester's operating status to calculate a unified evaluation function, thereby obtaining the operating status data of a zinc oxide arrester and realizing knowledge graph-based simulation of the operating status of zinc oxide arresters. In the second step, the method for extracting the key state variables of a surge arrester that can characterize the state of a certain zinc oxide surge arrester is as follows: Step 21: Obtain data from several on-site cases; Step 22: Classify and process the on-site case data to obtain a formatted fault template; Step 23: Based on the fault modules, establish a fault case library for zinc oxide surge arresters; Step 24: Based on the zinc oxide surge arrester fault case library, filter the condition-based operation and maintenance data to obtain the key state quantities of the surge arrester that can characterize the state of a certain zinc oxide surge arrester. Critical condition quantities include at least electrical performance and / or sealing performance and / or accessory performance and / or family defects; The method for determining several weighting factors and evaluation functions for the state characteristic parameters of surge arresters is as follows: S31, Obtain the critical state parameters of the surge arrester. The critical state parameters of the surge arrester include at least electrical performance, sealing performance, accessory performance, and family defects. S32. Based on the key state variables of the surge arrester, search the surge arrester knowledge graph model to obtain the state characteristic parameters of the surge arrester. S33 classifies the state characteristic parameters of the surge arrester into important state parameters, general state parameters, and minor state parameters, and assigns weights to them respectively.

2. The method for simulating the operating status of zinc oxide surge arresters based on knowledge graphs as described in claim 1, characterized in that, The method for obtaining status maintenance data in the first step is as follows: Maintenance data was obtained by monitoring the equalizing ring, resistors, and external insulation components. Maintenance data two was obtained by monitoring the sealing ring, the air extraction leak detection hole, and the flange; By reading data from the discharge counter and leakage current meter, we obtain maintenance data three; The three operation and maintenance data are merged to form the status operation and maintenance data.

3. The method for simulating the operating status of zinc oxide surge arresters based on knowledge graphs as described in claim 1, characterized in that, In the third step, the method for constructing the surge arrester knowledge graph model is as follows: Step 31: Obtain key information from the zinc oxide surge arrester fault case database; The key information includes at least the voltage level and / or the substation to which it belongs and / or the surge arrester model and / or the manufacturer and / or the commissioning date and / or the fault date and / or the service life and / or the function of the faulty component and / or the specific faulty component and / or the main fault cause and / or the detection method. Step 32: Based on the key information, construct a graph database with nodes, edges, and attributes; The graphical database represents a system or a specific fault mode of zinc oxide surge arrester through nodes; or / and, the graphical database represents the condition simulation and maintenance knowledge of zinc oxide surge arrester through nodes. Graph databases are used to represent the logical connections or dependencies between nodes; Graph databases use attributes to represent the definition information of nodes or edges; Step 33: Based on the graph database, construct a knowledge network graph structure of fault characteristics for zinc oxide surge arresters; Or / and, based on the graph database, construct a knowledge network graph structure for the condition simulation and maintenance of zinc oxide surge arresters; Step 34: Based on the knowledge network structure of zinc oxide surge arrester fault characteristics and / or the knowledge network structure of zinc oxide surge arrester state simulation and maintenance, establish a complete node knowledge graph model of the surge arrester to realize the searchability of key state quantities of the surge arrester.

4. The knowledge graph-based simulation method for the operating status of zinc oxide surge arresters as described in claim 3, characterized in that, The surge arrester's condition characteristic parameters include at least the body temperature rise, total current, resistive current, DC 1mA voltage, and 0.75... U 1mA Leakage current, equalizing ring condition, external insulation condition, sealing ring condition, drainage design, base insulation resistance, discharge counter condition, leakage current meter condition, and family defects; Weights of important state variables k 1 = 0.5, the weight of general state variables k 2 = 0.3, the weight of the secondary state variable k 3 = 0.

2.

5. The method for simulating the operating status of zinc oxide surge arresters based on knowledge graphs as described in claim 1, characterized in that, In the fourth step, the unified evaluation function is composed of several single-state evaluation functions; Several single-state evaluation functions include the body temperature rise evaluation function, the total current evaluation function, the resistive current evaluation function, the DC 1mA voltage evaluation function, and 0.75 U 1mA Leakage current evaluation function, equalizing ring status evaluation function, external insulation status evaluation function, sealing ring status evaluation function, drainage design evaluation function, base insulation resistance evaluation function, discharge counter status evaluation function, leakage current meter status evaluation function, and family defect evaluation function; The formula for calculating the body temperature rise evaluation function is as follows: in ，x This represents the measured temperature difference / the maximum permissible temperature difference.

6. The method for simulating the operating status of zinc oxide surge arresters based on knowledge graphs as described in claim 1, characterized in that, The method for obtaining the operating status data of a zinc oxide surge arrester in the fifth step is as follows: Step 51: Set the full score for evaluating the operating status of zinc oxide surge arresters. The full score is A. Step 52: Set the deduction value based on the full score and weight settings; The maximum deduction for important state variables shall not exceed three-fifths of A, the maximum deduction for general state variables shall not exceed one-third of A, and the maximum deduction for minor state variables shall not exceed one-tenth of A. Step 53: Based on the deduction values ​​and the evaluation functions of various state variables, obtain the total evaluation score: ； in, k 1 represents the weight of important state variables. k 2 represents the weight of the general state variables. k 3 represents the weight of the secondary state variable. f i (x) The evaluation function for important state variables, g i (x) The evaluation function for general state variables, h i (x) The evaluation function for secondary state variables; Step 54: Based on the total evaluation score and the maximum deduction, determine the operating status level of a certain zinc oxide surge arrester, obtain the operating status data of a certain zinc oxide surge arrester, and realize the simulation of the operating status of zinc oxide surge arresters based on knowledge graph.

7. The knowledge graph-based simulation method for the operating status of zinc oxide surge arresters as described in claim 6, characterized in that, The method for determining the operating status level of a zinc oxide surge arrester is as follows: The operational status levels are divided into normal status, alert status, abnormal status, and critical status; If the score for a certain important state quantity of the surge arrester reaches the maximum value, the final operational evaluation level will be reduced by three levels based on the level determined by the total evaluation score. If it is a general state variable, the final operational evaluation level will be reduced by two levels based on the level determined by the total evaluation score; If it is a minor state variable, the final operational evaluation level will be reduced by one level based on the level determined by the total evaluation score; If the deductions for two or more state variables reach the maximum value, the final operational evaluation level will be reduced by the cumulative level.

8. A knowledge graph-based simulation system for the operating status of zinc oxide surge arresters, employing the knowledge graph-based simulation method for the operating status of zinc oxide surge arresters as described in claim 1, characterized in that... It includes a key quantity extraction module, a surge arrester knowledge graph module, a surge arrester state function integration module, and a surge arrester operation state simulation module; The key quantity extraction module is used to process the status operation and maintenance data and extract the key status quantities of the arrester that can characterize the status of a certain zinc oxide arrester. The surge arrester knowledge graph module is used to search for key state variables of surge arresters, obtain surge arrester state characteristic parameters, and determine several weighting factors and evaluation functions for surge arrester state characteristic parameters. The surge arrester state function integration module is used to integrate several weighting factors and evaluation functions to obtain a unified evaluation function for a zinc oxide surge arrester. The surge arrester operation status simulation module is used to calculate a unified evaluation function to obtain the operation status data of a certain zinc oxide surge arrester, and realize the operation status simulation of zinc oxide surge arresters based on knowledge graph.

Images