A knowledge graph-based intelligent positioning method for defects of a relay protection device

Abstract

The application discloses a kind of based on knowledge graph's relay protection device defect intelligent positioning method, it is related to intelligent electric power equipment fault diagnosis technical field including the following steps: data collection, the various data related to relay protection device is collected;Knowledge graph construction, on the basis of data in collected data, constructs a dynamic knowledge graph, and the graph will device information, defect type, maintenance record etc. With the mode of node and edge is expressed, when new data enters, knowledge graph will automatically adjust and update;Intelligent reasoning mechanism is constructed, by analyzing the information in knowledge graph, possible defect reason is automatically identified, and the suggestion of defect positioning is generated.The application can effectively integrate sensor real-time monitoring data, historical maintenance records and environmental information by constructing a dynamic knowledge graph.This fusion of multi-source data enables the system to comprehensively understand the operating status and potential problems of the equipment, thereby achieving higher precision fault identification.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent power equipment fault diagnosis, and particularly relates to a relay protection device defect intelligent positioning method based on a knowledge graph. BACKGROUND

[0002] In recent years, in modern power systems, relay protection devices are key components to ensure the safe and stable operation of power equipment. These devices prevent equipment damage and power accidents by monitoring and responding to abnormal conditions in real time.

[0003] However, as the complexity of equipment increases, traditional fault diagnosis methods often face problems such as insufficient data processing capacity, inaccurate fault location, and low maintenance efficiency. Existing technologies rely heavily on experience and manual judgment, lacking systematic analysis and intelligent decision support.

[0004] To solve the above problems, we propose a relay protection device defect intelligent positioning method based on a knowledge graph. SUMMARY

[0005] The purpose of this section is to summarize some aspects of the embodiments of the present application and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of the specification to avoid obscuring the purpose of this section, abstract and title, and such simplifications or omissions cannot be used to limit the scope of the present application.

[0006] In view of the problems existing in the prior art, the present application is proposed.

[0007] To solve the above technical problems, the present application provides the following technical solutions:

[0008] A relay protection device defect intelligent positioning method based on a knowledge graph, the method comprising the following steps:

[0009] Step 1: Data collection, collect various data related to relay protection devices, including real-time monitoring data of sensors, historical maintenance records, and equipment usage environment information, and integrate them into a basic database;

[0010] Step 2: Knowledge graph construction, based on the collected data, a dynamic knowledge graph is constructed, and the graph represents device information, defect types, maintenance records, etc. in the form of nodes and edges, and the knowledge graph is automatically adjusted and updated whenever new data enters;

[0011] Step 3: Build an intelligent reasoning mechanism, analyze the information in the knowledge graph to automatically identify possible defect causes, and finally generate defect positioning suggestions based on the results obtained by the intelligent reasoning mechanism.

[0012] As a preferred scheme of the method for intelligently positioning defects of a relay protection device based on a knowledge graph, the method for constructing the knowledge graph comprises the following steps:

[0013] S201: defining nodes and edges, wherein the nodes represent device information, defect types, and maintenance records, and the edges represent relationships between the nodes, and edge weights A ij are used to describe the nodes, and the total number of nodes in the knowledge graph is set as G;

[0014] S202: designing a composite function f(D t , M, E) for describing data interaction relationships;

[0015] S203: when new real-time monitoring data D t enters, the edge weights A t between the nodes are calculated by using the function f(D ij , M, E), that is, the edge weights between all the nodes are recalculated, and the structure of the knowledge graph is adjusted.

[0016] As a preferred scheme of the method for intelligently positioning defects of a relay protection device based on a knowledge graph, the expression of the composite function f(D t , M, E) is as follows:

[0017]

[0018] wherein D t represents real-time monitoring data of a sensor at a time t, M represents a set of historical maintenance records, and contains various types of maintenance information, E represents device usage environment information such as temperature and humidity, u M represents a mean value of the maintenance records, and σ M represents a standard deviation of the maintenance records.

[0019] As a preferred scheme of the method for intelligently positioning defects of a relay protection device based on a knowledge graph, in the process of S203, the calculation formula of the edge weight A ij is as follows:

[0020]

[0021] wherein R represents a normalization factor, g(N) represents an influence of a defect type, and Φ(k) represents a reliability score related to a node k.

[0022] As a preferred scheme of the method for intelligently positioning defects of a relay protection device based on a knowledge graph, the method for constructing the intelligent reasoning mechanism comprises the following steps:

[0023] S301: Sum all edge weights A ij as the knowledge graph dynamic value K(t);

[0024] S302: Define the impact of the defect factor, calculate the impact of the defect factor I c (t);

[0025]

[0026] S303: Generate defect positioning suggestion P(t) according to knowledge graph dynamic value K(t) and impact of defect factor I c (t).

[0027] As a preferred scheme of the intelligent positioning method of the relay protection device defect based on the knowledge graph, the expression of the knowledge graph dynamic value K(t) is:

[0028]

[0029] Wherein, N and M represent the number and type of nodes respectively.

[0030] As a preferred scheme of the intelligent positioning method of the relay protection device defect based on the knowledge graph, the expression of the defect positioning suggestion P(t) is:

[0031]

[0032] Wherein, H represents the normalization factor of the control output range, Nc represents the number of defect types, and C represents the set of defect factors.

[0033] A positioning system of an intelligent positioning method of a relay protection device defect based on a knowledge graph, wherein the system further comprises the following functional modules:

[0034] Data acquisition module: Real-time collection of sensor data, historical maintenance records and environmental information to form a basic data set; Knowledge graph construction module: Based on the processed data, construct a dynamic knowledge graph containing device information, defect types, maintenance records, and use nodes and edges to represent; Knowledge graph update module: Real-time monitoring of data changes, automatically updating the knowledge graph to maintain the timeliness and accuracy of the information;

[0035] and reasoning engine module: Use intelligent reasoning mechanism to analyze the information in the knowledge graph, identify possible defect causes, and generate corresponding defect positioning suggestions; Visual display module: Display the knowledge graph and reasoning results in an intuitive graphical way to help users better understand and analyze fault information; Report generation module: Automatically generate fault diagnosis and maintenance suggestion report to provide decision support for maintenance personnel.

[0036] A computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above-mentioned method for intelligently positioning defects of a relay protection device based on a knowledge graph when executing the computer program.

[0037] A computer readable storage medium stores a computer program, and the computer program implements the steps of the above-mentioned method for intelligently positioning defects of a relay protection device based on a knowledge graph when executed by a processor.

[0038] The beneficial effects of the present application are:

[0039] 1. The present application can effectively integrate real-time sensor monitoring data, historical maintenance records and environmental information by constructing a dynamic knowledge graph. The fusion of this multi-source data enables the system to comprehensively understand the running state and potential problems of the equipment, thereby achieving higher precision fault identification; and by using the reasoning mechanism, the potential patterns and relationships of fault causes can be identified according to the correlation analysis in the knowledge graph, reducing the false alarm rate and improving the reliability of fault positioning;

[0040] 2. With the changes of the running environment and state of the equipment, the traditional method often cannot adapt in time. The present application updates the knowledge graph in real time to ensure that the system can automatically adjust and optimize the reasoning rules when facing new situations, improving the adaptability of the overall system;

[0041] 3. The present application uses an intelligent reasoning mechanism, which is not limited to fault detection, but also provides a basis for subsequent decision-making. For example, according to the running history of the equipment, the system can predict potential fault risks and make preventive maintenance recommendations in advance, thereby reducing the probability of accidents. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor. Among them:

[0043] Figure 1 A flow structure diagram of a method for intelligently positioning defects of a relay protection device based on a knowledge graph is provided. DETAILED DESCRIPTION

[0044] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification.

[0045] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced without the specific details set forth in this description. In other instances, well-known methods have not been described in detail in order not to unnecessarily obscure aspects of the present application.

[0046] Secondly, the "one embodiment" or "an embodiment" referred to herein means a specific feature, structure, or characteristic under discussion. Thus, "one embodiment" does not mean a single embodiment nor is it to be taken individually or selectively from other embodiments.

[0047] Reference is made to Figure 1 For one embodiment of the present application, a knowledge graph-based intelligent positioning method for defects of a relay protection device is provided, which comprises the following steps:

[0048] Step one: data collection, various data related to the relay protection device are collected, including real-time monitoring data of sensors, historical maintenance records, and device use environment information, and are integrated together to form a basic database;

[0049] Step two: knowledge graph construction, a dynamic knowledge graph is constructed based on the collected data, and the graph represents device information, defect types, and maintenance records in the form of nodes and edges, and the knowledge graph is automatically adjusted and updated whenever new data enters;

[0050] Specifically, the knowledge graph construction method is as follows:

[0051] S201: define nodes and edges, nodes represent device information, defect types, and maintenance records, and edges represent the relationship between nodes, described by edge weight A ij , and set the total number of nodes in the knowledge graph as G;

[0052] S202: design a composite function f(D t , M, E) describing the data interaction relationship;

[0053] S203: when new real-time monitoring data D t enters, calculate the edge weight A t between nodes by f(D ij , M, E), that is, recalculate the edge weight between all nodes, and adjust the knowledge graph structure.

[0054] The expression of the composite function f(D t , M, E) is as follows:

[0055]

[0056] where D t represents the real-time monitoring data of the sensor at time t; M represents a set of historical maintenance records containing various types of maintenance information; E represents device usage environment information such as temperature and humidity; u M represents the mean of the maintenance records; σ M represents the standard deviation of the maintenance records.

[0057] In addition, the edge weight A ij is calculated as follows:

[0058]

[0059] where R represents a normalization factor, and g(N) represents the influence of defect types to avoid simple linear weighting.

[0060] g(N) = log(N + 1), where N is the number of defect types.

[0061] Φ(k) represents the reliability score associated with node k.

[0062] In summary, through the definition of the composite function f(D t , M, E) and g(N), the former quantifies the interaction of data by combining Gaussian distribution and Sigmoid function, and the latter reflects the importance of defect types by taking the logarithm of the number of defect types. These functions not only provide a basis for calculating the edge weight A ij in the knowledge graph, but also ensure the dynamic updating and accuracy of the knowledge graph.

[0063] Step three: build an intelligent reasoning mechanism to automatically identify possible defect causes by analyzing the information in the knowledge graph, and finally generate suggestions for defect positioning based on the results obtained by the intelligent reasoning mechanism.

[0064] Specifically, the construction method of the intelligent reasoning mechanism is as follows:

[0065] S301: Sum all edge weights A ij as the dynamic value K(t) of the knowledge graph;

[0066] The expression of the dynamic value K(t) of the knowledge graph is as follows:

[0067]

[0068] where N and M represent the number and type of nodes, respectively.

[0069] S302: Define the influence degree of defect factors and calculate the influence degree I c (t) of defect factors;

[0070]

[0071] S303: Based on the dynamic value K(t) of the knowledge graph and the degree of influence of the defect factor I c (t) Generate defect location suggestions P(t).

[0072] The expression for the defect location suggestion P(t) is:

[0073]

[0074] Where H represents the normalization factor controlling the output range, Nc represents the number of defect types, and C represents the set of defect factors.

[0075] The result of P(t) represents the defect location suggestion value inferred at the current time t based on the dynamic information and influence degree of each defect factor in the knowledge graph. This value is used to measure the comprehensive degree of equipment failure that each defect factor may cause, and to generate specific location suggestions accordingly.

[0076] The value of P(t) is generally within a certain range (e.g., 0 to 1). The closer the value is to 1, the greater the impact of the fault factors identified by the system on the equipment failure, and the more likely the fault needs to be investigated.

[0077] When P(t) is between 0.5 and 1, it indicates that the influence of the defect factors is relatively high, and the system will locate these factors as the most likely causes of failure.

[0078] When P(t) is below 0.5, it indicates that the equipment is currently in a relatively stable state, the possible defect factors have little impact, and no emergency intervention is required.

[0079] In summary, it can be seen that the core of constructing an intelligent reasoning mechanism lies in calculating the dynamic value K(t) of the knowledge graph, which is achieved by defining the edge weights A. ij This reflects the relationships between nodes, and their sum is used as K(t). Next, the Sigmoid function is used to calculate the degree of influence of the defect factor. I c(t) is used to quantify the relative importance of each defect. Finally, by combining this information, a defect location suggestion P(t) is generated, providing an accurate and reliable basis for fault diagnosis. This ensures a close correlation and mutual support between the above steps.

[0080] A defect intelligent location system for a knowledge graph-based intelligent defect location method in relay protection devices, comprising the following modules:

[0081] The data acquisition module: real-time collection of sensor data, historical maintenance records and environmental information, forming a basic data set; the knowledge graph construction module: based on the processed data, constructing a dynamic knowledge graph, containing device information, defect types, maintenance records, using the form of nodes and edges to represent; the knowledge graph updating module: real-time monitoring of data changes, automatically updating the knowledge graph to maintain the timeliness and accuracy of the information;

[0082] and the reasoning engine module: using intelligent reasoning mechanism to analyze the information in the knowledge graph, identifying possible defect causes and generating corresponding defect positioning suggestions; the visual display module: displaying the knowledge graph and reasoning results in an intuitive graphical way, helping users better understand and analyze fault information; the report generation module: automatically generating fault diagnosis and maintenance suggestion reports to provide decision support for maintenance personnel.

[0083] In summary, the present application can effectively integrate real-time sensor monitoring data, historical maintenance records and environmental information by constructing a dynamic knowledge graph. This fusion of multi-source data enables the system to comprehensively understand the running state and potential problems of the equipment, thereby achieving higher precision fault identification; and using reasoning mechanism, according to the correlation analysis in the knowledge graph, the potential patterns and relationships of fault causes can be identified, reducing the false alarm rate and improving the reliability of fault positioning. As the equipment operating environment and state change, traditional methods often cannot adapt in time. The present application updates the knowledge graph in real time, ensuring that the system can automatically adjust and optimize the reasoning rules when facing new situations, improving the adaptability of the overall system. Through intelligent reasoning mechanism, not only limited to fault detection, but also can provide basis for subsequent decision-making. For example, according to the running history of the equipment, the system can predict potential fault risks and propose preventive maintenance suggestions in advance, thereby reducing the probability of accidents.

[0084] The embodiment also provides a computer device suitable for the case of the intelligent defect positioning method of the relay protection device based on the knowledge graph, comprising: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to realize the intelligent defect positioning method of the relay protection device based on the knowledge graph as proposed in the above embodiment.

[0085] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved by WIFI, an operator network, NFC (Near Field Communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0086] The embodiment also provides a storage medium having a computer program stored thereon, the program being executed by a processor to implement the method for intelligently positioning defects of a relay protection device based on a knowledge graph according to the above embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk.

[0087] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A knowledge graph-based intelligent positioning method for defects of a relay protection device, characterized in that, The method comprises the following steps: Step one: data collection, collect various data related to the relay protection device, including: real-time monitoring data of sensors, historical maintenance records, equipment use environment information, and integrate them into a basic database; Step two: knowledge graph construction, based on the collected data, a dynamic knowledge graph is constructed, and the graph represents the device information, defect type, and maintenance record in the form of nodes and edges, and whenever new data enters, the knowledge graph will automatically adjust and update; Step three: build an intelligent reasoning mechanism, analyze the information in the knowledge graph, automatically identify possible defect causes, and finally generate defect positioning suggestions based on the results of the intelligent reasoning mechanism; The knowledge graph construction method is: S201: define nodes and edges, nodes represent device information, defect type, maintenance record, edges represent the relationship between nodes, and edge weight The total number of nodes in the knowledge graph is set as G. S202: design composite functions describing data interaction relationship ; The composite function The expression for the composite function is ； wherein, represents real-time monitoring data of the sensor at time t; M represents a set of historical maintenance records containing various maintenance information; E represents equipment use environment information including temperature, humidity; represents the mean value of the maintenance records; represents the standard deviation of the maintenance records; S203: when new real-time monitoring data entering, using computing edge weights between nodes i.e. re-compute edge weights between all nodes, adjust knowledge graph structure; In the S203 process, the edge weight The calculation formula is as follows: ； wherein R represents a normalization factor, represents the influence of the defect type, represents the reliability score associated with node k.

2. The method of claim 1, wherein the method is characterized by: The construction method of the intelligent reasoning mechanism is: S301: summing all edge weights as a dynamic value of the knowledge graph ; S302: define the influence degree of the defect factor, calculate the influence degree of the defect factor ; ； S303: According to the knowledge graph dynamic value And the influence degree of the defect factor Generate defect positioning suggestions .

3. The method of claim 2, wherein the method is characterized by: The knowledge graph dynamic value The expression of the knowledge graph dynamic value is: ； Wherein, N and M represent the number and type of nodes respectively.

4. The method according to claim 3, characterized in that: The defect localization suggestion The expression is: ； wherein, wherein H denotes a normalization factor that controls the output range, denotes the number of defect types, C denotes a set of defect factors.

5. The defect intelligent positioning system of the knowledge graph-based intelligent positioning method for defects of a relay protection device according to claim 4, characterized in that: The system comprises the following modules: Data acquisition module: real-time collection of sensor data, historical maintenance records and environmental information to form a basic data set; knowledge graph construction module: based on the processed data, a dynamic knowledge graph is constructed, containing device information, defect type, and maintenance record, represented in the form of nodes and edges; knowledge graph update module: real-time monitoring of data changes, automatically updating the knowledge graph to maintain the timeliness and accuracy of the information; And reasoning engine module: use intelligent reasoning mechanism to analyze the information in the knowledge graph, identify possible defect causes, and generate corresponding defect positioning suggestions; Visual display module: display the knowledge graph and reasoning results in an intuitive graphical way to help users better understand and analyze fault information; report generation module: automatically generate fault diagnosis and maintenance suggestion report to provide decision support for maintenance personnel. 6.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: The processor executes the computer program to realize the steps of the relay protection device defect intelligent positioning method based on the knowledge graph according to any one of claims 1-4.

7. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the relay protection device defect intelligent positioning method based on the knowledge graph according to any one of claims 1-4.

Images