Power equipment intelligent diagnosis and maintenance system and method based on knowledge graph

Abstract

The invention belongs to but not limited to the technical field of fault diagnosis and maintenance of power equipment, and discloses an intelligent diagnosis and maintenance system and method for power equipment based on a knowledge graph. A data acquisition and preprocessing module acquires real-time operation data and historical data of the power equipment; the knowledge graph construction module associates various kinds of information of the power equipment to construct a knowledge graph; the intelligent diagnosis module performs association analysis on power equipment faults based on a knowledge graph and a machine learning algorithm, identifies fault modes and potential faults, and predicts possible faults of the equipment; the maintenance suggestion module automatically generates a detailed maintenance scheme according to the diagnosis result; the operation and maintenance visualization module provides visual fault diagnosis results and maintenance suggestions, supports multi-level data display, and helps operation and maintenance personnel to clearly understand the equipment state. The operation safety of the power equipment is improved, the operation and maintenance cost is remarkably reduced, and the overall efficiency of equipment management in an intelligent power grid environment is improved.

Description

Technical Field

[0001] The present invention belongs to but is not limited to the technical field of fault diagnosis and maintenance of electric power equipment, and in particular relates to an intelligent diagnosis and maintenance system and method for electric power equipment based on a knowledge graph. Background Art

[0002] Currently, traditional monitoring systems based on manual rules and simple data analysis are widely used in the field of fault diagnosis and maintenance of power equipment. These systems mainly rely on the set equipment parameter thresholds and changes in monitoring indicators (such as temperature, voltage, current, etc.) to generate simple alarm signals. However, the causes of equipment failures are often complex and hidden. Traditional monitoring methods are difficult to accurately determine the cause and location of the failure, resulting in a high rate of false alarms and missed alarms, which affects the accuracy of fault diagnosis and the timeliness of equipment maintenance.

[0003] The technical problems that need to be solved urgently in the prior art are:

[0004] 1. Multi-source data integration and intelligent analysis: The operating data of power equipment is complex and diverse, and it is necessary to integrate multi-source information such as the equipment's historical operating data, fault records, maintenance logs, etc. to obtain a more comprehensive understanding of the equipment's operating status.

[0005] 2. Knowledge association and intelligent diagnosis: Traditional methods are difficult to capture the correlation between faults. It is necessary to establish a power equipment knowledge base based on the knowledge graph, perform intelligent analysis through multi-level knowledge association, and improve the accuracy of fault diagnosis.

[0006] 3. Automatic generation of maintenance suggestions: Based on the fault type and equipment status, the system needs to automatically generate maintenance suggestions to help operation and maintenance personnel quickly handle faults and perform preventive maintenance. Summary of the invention

[0007] In response to the problems existing in the prior art, the present invention provides an intelligent diagnosis and maintenance system and method for power equipment based on knowledge graph.

[0008] The present invention is implemented as follows: an intelligent diagnosis and maintenance system for power equipment based on knowledge graph, comprising:

[0009] Data collection and preprocessing module, used to collect real-time operation data and historical data of power equipment, including temperature, humidity, current, voltage, as well as historical fault records and maintenance logs, and generate high-quality data sets through data standardization processing;

[0010] The knowledge graph construction module is used to construct the power equipment information into a knowledge graph, convert the equipment, fault, and maintenance measures information into a node and edge relationship library, determine the association distance between different nodes based on the shortest path algorithm of the weighted graph, and generate the fault propagation path to identify the key fault nodes;

[0011] The intelligent diagnosis module, based on the knowledge graph and Bayesian network algorithm, performs probabilistic reasoning on fault data, calculates the probability of occurrence of various fault modes, and predicts potential failures of equipment;

[0012] Maintenance suggestion module, which automatically generates detailed maintenance plans based on diagnosis results, including troubleshooting steps and preventive maintenance suggestions;

[0013] The operation and maintenance visualization module is used to display fault diagnosis results and maintenance suggestions. It supports multi-level data display and provides operation and maintenance personnel with a clear view of equipment status.

[0014] The embodiment of the present invention also includes:

[0015] The data acquisition and preprocessing module collects real-time operating data and historical data of power equipment, including temperature, humidity, current, voltage, as well as historical fault records and maintenance logs, and performs denoising on the data through wavelet transform to improve data accuracy;

[0016] The knowledge graph construction module builds a knowledge graph of equipment, faults, and maintenance measures based on the operation information and historical fault data of power equipment, and sorts the importance of nodes through the PageRank algorithm to identify key equipment and fault nodes;

[0017] The intelligent diagnosis module predicts the time series data of key fault nodes based on the knowledge graph and the time series-based ARIMA model to identify the potential fault trends of the equipment;

[0018] Maintenance suggestion module, based on the diagnosis module

[0019] Furthermore, the data acquisition and preprocessing module includes:

[0020] Data collection:

[0021] Through the Internet of Things (IoT) technology, sensors such as temperature, humidity, current, and voltage are used to collect power equipment operating data in real time.

[0022] Collect the historical fault records and maintenance logs of the equipment, establish a fault record library, and provide data support for subsequent knowledge graph construction and fault analysis.

[0023] Data preprocessing:

[0024] Data cleaning: fill missing values, process outliers and denoise the collected data to ensure data integrity.

[0025] Data standardization: Normalize all data and store them in a unified format in the database to facilitate subsequent analysis.

[0026] Feature extraction: Extract important feature data such as temperature, voltage, current, etc. of the equipment to provide input for node construction and fault diagnosis of the knowledge graph.

[0027] Furthermore, the knowledge graph building blocks include:

[0028] Define the types of nodes and edges:

[0029] Node: includes equipment, fault type, fault cause, maintenance measures, etc.

[0030] Edge: represents the relationship between different nodes, such as equipment-fault, fault-cause, cause-maintenance measure, etc.

[0031] Building a knowledge graph:

[0032] Data storage: Use graph databases (such as Neo4j) to store the knowledge graph structure of power equipment to facilitate complex relationship queries and fault analysis.

[0033] Semantic modeling: Use the ontology model to establish the association between nodes and edges, and form the basic architecture of the power equipment knowledge base by associating attribute information from different data sources.

[0034] Relationship Building:

[0035] Based on the equipment operation data and historical maintenance data, the relationship between equipment and faults is constructed to form a knowledge graph containing cause-effect relationships. For example, the association between equipment temperature rise and a certain type of fault is recorded.

[0036] Through machine learning algorithms (such as association rule algorithms), potential relationships in historical fault data are mined, the strength of associations in the knowledge graph is strengthened, and the accuracy of diagnosis is improved.

[0037] Furthermore, the intelligent diagnosis module includes:

[0038] Failure mode identification:

[0039] Pattern recognition: Through the knowledge graph-based pattern matching algorithm, the current equipment status is matched with the historical failure patterns in the knowledge graph to identify possible failure types.

[0040] Use Graph Neural Network (GNN) to further mine complex equipment-fault association information and identify hidden failure modes.

[0041] Fault reasoning:

[0042] Rule reasoning: Utilize the relationships between equipment and fault, fault and cause in the knowledge graph, and use the rule-based reasoning engine to automatically deduce the possible causes of the current fault.

[0043] Machine learning diagnosis: Use random forest or support vector machine (SVM) models to analyze multi-dimensional equipment data to assist in identifying abnormal conditions and potential fault types that are not clearly defined in the knowledge graph.

[0044] Failure prediction:

[0045] Use time series models (such as ARIMA and LSTM) to predict equipment operation data, detect possible failures in advance, and issue warnings to operation and maintenance personnel.

[0046] Conduct trend analysis on equipment status data, combine predicted fault information with the associations in the knowledge graph, and further analyze possible chain reactions.

[0047] Furthermore, the maintenance suggestion module includes:

[0048] Automatically generate maintenance recommendations:

[0049] Based on the "fault-maintenance measures" relationship in the knowledge graph, specific maintenance suggestions are automatically generated, including repair steps, tool lists, maintenance materials, etc.

[0050] For complex fault conditions, the system will recommend corresponding preventive maintenance measures to help the equipment avoid the recurrence of the same type of fault.

[0051] Personalized maintenance plan:

[0052] The system generates a personalized maintenance plan based on the actual use of the equipment. For key equipment, more frequent inspections and maintenance are recommended, while for minor faults, less frequent maintenance is arranged.

[0053] By analyzing the equipment health index and empirical rules in the knowledge graph, detailed operation suggestions are provided to shorten maintenance time and improve equipment health level.

[0054] Dynamically update the knowledge graph:

[0055] After the maintenance suggestions are generated, the actual operation records are fed back to the knowledge graph library, and the graph content is dynamically updated to continuously improve the accuracy and timeliness of fault diagnosis and maintenance suggestions.

[0056] Furthermore, the operation and maintenance visualization module includes:

[0057] Fault and device status display:

[0058] Use a graphical interface to display the equipment operating status and real-time fault conditions. The interface design includes equipment parameters, fault information, prediction results, etc.

[0059] Fault information is presented in a graphically visualized way, showing the cause of the fault, affected components and related equipment, helping operation and maintenance personnel to intuitively understand the cause and impact of the fault.

[0060] Multi-level data display:

[0061] Different data levels are set in the system interface to support single information display and global overview of equipment, and provide integrated information display from "equipment-fault-maintenance".

[0062] The visual interface can display the health status of the equipment in different time periods and support viewing of specific fault details and diagnostic analysis results.

[0063] Visual tracking of maintenance process:

[0064] The system dynamically displays the maintenance progress during the maintenance process, helping operation and maintenance personnel to understand the maintenance progress in real time.

[0065] Visualize historical maintenance records and diagnostic results to support operation and maintenance personnel in comparing equipment conditions at different stages, helping to summarize equipment operation rules and optimize future maintenance strategies.

[0066] Another object of the present invention is to provide a method for intelligent diagnosis and maintenance of electric equipment based on a knowledge graph, comprising the following steps:

[0067] Step 1: Data collection and preprocessing

[0068] 1. Data collection: Through sensors and monitoring systems, real-time data of power equipment, such as temperature, current, voltage and other operating data, is collected, and combined with the historical fault records and maintenance logs of the equipment.

[0069] 2. Data cleaning: Clean up outliers and fill in missing values ​​in the collected data to ensure the integrity and accuracy of the data.

[0070] 3. Data preprocessing: Standardize the data and convert the equipment status parameters into a unified numerical format for subsequent modeling and analysis.

[0071] Step 2: Knowledge graph construction

[0072] 1. Knowledge base establishment: The equipment type, fault type, fault cause, fault phenomenon, maintenance measures and other information are modeled through knowledge graph construction technology to form a knowledge base.

[0073] 2. Knowledge graph modeling: Based on the working principle and failure mode of power equipment, a knowledge graph of power equipment is constructed, which includes different categories of nodes such as equipment nodes, fault nodes, cause nodes, and maintenance measures nodes, and their relationships are described by edges.

[0074] 3. Data relationship definition: Define the relationship between different nodes (such as equipment-fault, fault-cause, cause-maintenance measures, etc.), convert the relationship into edges in the graph, and form a semantically rich association relationship network.

[0075] Step 3: Smart Diagnosis

[0076] 1. Fault pattern recognition: Through knowledge graphs and intelligent algorithms (such as rule-based reasoning, graph neural networks, etc.), the associations between different nodes are analyzed to identify common failure modes of power equipment.

[0077] 2. Fault reasoning analysis: Utilize the association relationship of the knowledge graph to perform reasoning analysis on the abnormal data of the equipment to determine the possible cause and type of the fault.

[0078] 3. Intelligent prediction: Based on the historical data and current operating status of the equipment, predict potential failure risks, reason through the associated information in the knowledge graph, and identify possible failures in advance.

[0079] Step 4: Maintenance suggestion generation

[0080] 1. Fault type identification: According to the diagnosed fault type, match the maintenance plan in the knowledge base and extract the maintenance measures and processes associated with the fault.

[0081] 2. Generate maintenance recommendations: Based on the specific equipment conditions, the system generates personalized maintenance recommendations, including detailed repair steps and preventive maintenance recommendations.

[0082] 3. Dynamic update: When the system receives new maintenance results, it updates the fault information to the knowledge base and continuously optimizes the content of the knowledge graph to make maintenance recommendations more complete.

[0083] Step 5: Visualization of operation and maintenance

[0084] 1. Fault and maintenance suggestion display: Through the operation and maintenance visualization module, fault nodes and related maintenance measures are displayed in a graphical manner, and visual analysis of the power equipment status is provided.

[0085] 2. Equipment status tracking: Displays the real-time status, fault trends and warning information of the equipment, helping operation and maintenance personnel to intuitively view the operation status of the equipment.

[0086] 3. Maintenance data backtracking: Supports operation and maintenance personnel to trace historical fault information and maintenance data through a visual interface to improve the pertinence of equipment fault handling.

[0087] Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method for intelligent diagnosis and maintenance of power equipment based on the knowledge graph.

[0088] Another object of the present invention is to provide a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the method for intelligent diagnosis and maintenance of power equipment based on knowledge graph.

[0089] Another object of the present invention is to provide an information data processing terminal, which includes the above-mentioned knowledge graph-based intelligent diagnosis and maintenance system for power equipment.

[0090] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0091] First, 1. The accuracy of fault diagnosis is significantly improved: This system builds a knowledge base of related power equipment through knowledge graphs, which enables the system to perform multi-level fault diagnosis on equipment and improve the accuracy of fault identification. At the same time, based on the intelligent reasoning model, the system can automatically infer the cause of the fault and reduce false alarms and missed alarms.

[0092] 2. Significant improvement in operation and maintenance efficiency: Traditional fault diagnosis relies on manual inspections and empirical analysis, while this system quickly locates the cause of the fault through intelligent automatic diagnosis and maintenance suggestions, providing operation and maintenance personnel with a clear fault handling solution, shortening equipment downtime and significantly improving maintenance efficiency.

[0093] 3. Personalization and optimization of maintenance plans: The system generates personalized maintenance suggestions for different equipment based on the association analysis of the knowledge graph, and can update the knowledge base in real time according to the equipment usage. In this way, the system's maintenance plan is more targeted and timely, which helps to optimize the daily maintenance process of power equipment.

[0094] 4. Enhanced equipment failure prediction capabilities: Through the fusion analysis of historical data and knowledge graphs, the system can identify potential failures of power equipment in advance, help operation and maintenance personnel implement preventive maintenance measures, reduce the probability of failures, and extend the service life of equipment.

[0095] 5. Achieve efficient management of multi-source data: The system integrates multi-source information such as real-time equipment data, historical fault records and maintenance logs, making the system data more complete. The association structure of the knowledge graph can display the operating status of the equipment throughout its life cycle, providing data support for subsequent equipment updates and optimizations.

[0096] Through the above-mentioned intelligent diagnosis and maintenance solutions, the system can not only improve the operational safety of power equipment, but also significantly reduce operation and maintenance costs and improve the overall efficiency of equipment management in the smart grid environment.

[0097] Second, ###The technical problems of the prior art solved by this invention in industrial applications and the remarkable technical progress achieved.

[0098] 1. Technical Problems Solved

[0099] At present, intelligent diagnosis and maintenance of power equipment face many challenges in industrial applications, mainly including:

[0100] 1. Low fault diagnosis accuracy: Traditional power equipment diagnosis methods rely on empirical rules or simple statistical analysis, which makes it difficult to accurately identify complex fault modes, especially potential faults under the influence of multiple factors.

[0101] 2. Low efficiency of maintenance decision-making: The existing system lacks systematic and intelligent support when generating maintenance recommendations, resulting in inaccurate maintenance plans, increasing equipment downtime and maintenance costs.

[0102] 3. Difficulty in data integration and correlation analysis: There are many types of power equipment operation data, involving real-time data and historical data. Existing technologies are difficult to effectively integrate and correlate these heterogeneous data, which limits the ability of fault prediction and preventive maintenance.

[0103] 4. Insufficient visualization: The current operation and maintenance system lacks intuitive and easy-to-understand visualization methods for displaying fault diagnosis results and maintenance suggestions, which affects the decision-making efficiency and accuracy of operation and maintenance personnel.

[0104] 5. Poor system scalability: With the diversification of power equipment types and operating environments, the existing diagnosis and maintenance systems have limitations in knowledge base construction and algorithm adaptability, making it difficult to meet the needs of different equipment and scenarios.

[0105] 2. Technical solution

[0106] The present invention provides an intelligent diagnosis and maintenance system for power equipment based on knowledge graph, which systematically solves the above technical problems by integrating modules such as data acquisition, knowledge graph construction, intelligent diagnosis, maintenance suggestion generation and operation and maintenance visualization, combined with advanced mathematical models and data processing technology. The specific method includes:

[0107] 1. Data acquisition and preprocessing module: comprehensively collect real-time operation data and historical data of power equipment, and improve data quality, remove noise and ensure the accuracy of subsequent analysis through preprocessing technologies such as data cleaning, normalization and wavelet transform.

[0108] 2. Knowledge graph construction module: associate multi-source heterogeneous data such as equipment, faults, maintenance measures, etc. to build a structured knowledge graph, use the shortest path algorithm and PageRank algorithm of the weighted graph to identify key nodes, and form a deep correlation between equipment and faults.

[0109] 3. Intelligent diagnosis module: Combined with mathematical models such as Bayesian theorem and Fourier transform, it accurately calculates the probability of failure and performs frequency domain analysis, identifies complex failure modes and potential failure trends, and improves the accuracy and reliability of fault prediction.

[0110] 4. Maintenance suggestion module: Based on the intelligent diagnosis results, it automatically generates personalized maintenance plans, covering troubleshooting steps and preventive maintenance suggestions, optimizing maintenance decisions, and reducing equipment downtime and maintenance costs.

[0111] 5. Operation and maintenance visualization module: Through visualization methods such as multi-dimensional graphics and trend curves, it intuitively displays fault diagnosis results and maintenance suggestions, supports multi-level data display, and improves the decision-making efficiency and accuracy of operation and maintenance personnel.

[0112] III. Significant Technological Progress

[0113] In industrial applications, the present invention has achieved the following significant technological advances by combining data and advanced mathematical models:

[0114] 1. Improve the accuracy and reliability of fault diagnosis: Through the combination of knowledge graph and Bayesian theorem, the system can integrate multi-source data for probabilistic reasoning, accurately identify complex fault modes and potential faults, and significantly improve the accuracy and reliability of diagnosis.

[0115] 2. Optimize maintenance decisions and improve maintenance efficiency: The personalized maintenance plan generated by the intelligent diagnosis module is based on accurate fault prediction, which reduces unnecessary maintenance operations, shortens maintenance cycles, reduces maintenance costs, and improves overall operation and maintenance efficiency.

[0116] 3. Efficient integration and analysis of heterogeneous data: The knowledge graph construction module effectively integrates real-time data and historical data, and uses graph structure and algorithms to optimize data association analysis capabilities, enabling the system to fully and systematically understand the equipment operating status and fault evolution process.

[0117] 4. Enhance system visualization and user-friendliness: The operation and maintenance visualization module helps operation and maintenance personnel quickly understand equipment status and fault conditions through intuitive graphical display and multi-level data display, thereby improving the user experience and operation convenience of the system.

[0118] 5. Improve the scalability and adaptability of the system: Through modular design and the flexible structure of the knowledge graph, the present invention can adapt to the needs of different types of power equipment and diversified operating environments, has good scalability and adaptability, and meets the requirements of future technological development.

[0119] 6. Reduce computing resources and time costs: The use of efficient data preprocessing and mathematical model optimization algorithms improves the computing efficiency of the system, reduces dependence on computing resources, shortens the time for fault diagnosis and maintenance suggestion generation, and improves business forecasting and response speed.

[0120] 7. Support preventive maintenance and intelligent decision-making: Based on time series analysis and frequency domain analysis, the system can not only predict potential failures of equipment, but also provide preventive maintenance suggestions to help enterprises implement proactive maintenance strategies and improve the overall operating stability and life of the equipment.

[0121] The present invention systematically solves the key problems in the existing intelligent diagnosis and maintenance technology of power equipment by integrating knowledge graphs, advanced mathematical models (such as Bayesian theorem and Fourier transform) and efficient data processing and visualization technology. It has made significant technological progress in fault diagnosis accuracy, maintenance decision-making efficiency, data integration and analysis capabilities, system visualization and scalability, and significantly improved the intelligence level and industrial application value of power equipment operation and maintenance. These technological advances not only optimize the operation and management of power equipment, but also provide efficient and reliable intelligent operation and maintenance solutions for related industries, promoting technological innovation and industrial upgrading in the power industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0122] Figure 1 It is a structural diagram of a knowledge graph-based intelligent diagnosis and maintenance system for electric power equipment provided by an embodiment of the present invention;

[0123] Figure 2 It is a flow chart of the knowledge graph-based intelligent diagnosis and maintenance method for power equipment provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0124] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0125] like Figure 1 As shown, an embodiment of the present invention provides an intelligent diagnosis and maintenance system for power equipment based on a knowledge graph, including:

[0126] Data acquisition and preprocessing module: collects real-time operation data and historical data of power equipment, including equipment parameters such as temperature, humidity, current, voltage, as well as historical fault records and maintenance logs;

[0127] Knowledge graph construction module: associates various types of information on power equipment into a knowledge graph, forming a relationship library of nodes and edges such as equipment, faults, and maintenance measures;

[0128] Intelligent diagnosis module: Based on knowledge graph and machine learning algorithm, it conducts correlation analysis on power equipment failures, identifies failure modes and potential failures, and predicts possible equipment failures;

[0129] Maintenance suggestion module: automatically generates detailed maintenance plans based on the diagnosis results, including troubleshooting steps and preventive maintenance suggestions;

[0130] Operation and maintenance visualization module: provides visualized fault diagnosis results and maintenance suggestions, supports multi-level data display, and helps operation and maintenance personnel clearly understand the equipment status.

[0131] The intelligent diagnosis module uses the support vector machine (SVM) algorithm to perform correlation analysis on power equipment faults to identify fault modes and potential faults, and predict faults based on the trained SVM model.

[0132] The intelligent diagnosis module uses the Autoregressive Integrated Moving Average (ARIMA) model to perform time series analysis on the operating data of power equipment to predict the possible failure trends and time nodes of the equipment.

[0133] The support vector machine (SVM) algorithm is introduced as the core algorithm of the intelligent diagnosis module. SVM is a supervised learning model that is widely used in classification and regression analysis. By training the SVM model, the failure mode of power equipment can be effectively identified and potential failures can be accurately predicted. The introduction of this algorithm improves the accuracy and reliability of the diagnosis module and can better cope with complex failure mode identification tasks.

[0134] The Autoregressive Integrated Moving Average (ARIMA) model is introduced as a time series analysis tool for the intelligent diagnosis module. The ARIMA model can conduct in-depth time series analysis on the operating data of power equipment, capture trends and periodic changes in the data, and thus predict the failure trends and specific time nodes that may occur in the future. This prediction capability helps to carry out maintenance and preventive measures in advance, further improving the maintenance efficiency of the system and the reliability of the equipment.

[0135] The system provided by the embodiment of the present invention not only has the intelligent diagnosis and maintenance capabilities based on the knowledge graph, but also combines advanced mathematical models to further improve the accuracy and efficiency of fault identification and prediction, thereby significantly enhancing the technical level and application value of the entire system.

[0136] The implementation method of this system is divided into module design and algorithm implementation. It mainly uses the combination of knowledge graph and machine learning to intelligently analyze the real-time and historical data of power equipment, and output maintenance suggestions and visual display results.

[0137] 1. Data acquisition and preprocessing module

[0138] Data collection:

[0139] Through the Internet of Things (IoT) technology, sensors such as temperature, humidity, current, and voltage are used to collect power equipment operating data in real time.

[0140] Collect the historical fault records and maintenance logs of the equipment, establish a fault record library, and provide data support for subsequent knowledge graph construction and fault analysis.

[0141] Data preprocessing:

[0142] Data cleaning: fill missing values, process outliers and denoise the collected data to ensure data integrity.

[0143] Data standardization: Normalize all data and store them in a unified format in the database to facilitate subsequent analysis.

[0144] Feature extraction: Extract important feature data such as temperature, voltage, current, etc. of the equipment to provide input for node construction and fault diagnosis of the knowledge graph.

[0145] 2. Knowledge graph building module

[0146] Define the types of nodes and edges:

[0147] Node: includes equipment, fault type, fault cause, maintenance measures, etc.

[0148] Edge: represents the relationship between different nodes, such as equipment-fault, fault-cause, cause-maintenance measure, etc.

[0149] Building a knowledge graph:

[0150] Data storage: Use graph databases (such as Neo4j) to store the knowledge graph structure of power equipment to facilitate complex relationship queries and fault analysis.

[0151] Semantic modeling: Use the ontology model to establish the association between nodes and edges, and form the basic architecture of the power equipment knowledge base by associating attribute information from different data sources.

[0152] Relationship Building:

[0153] Based on the equipment operation data and historical maintenance data, the relationship between equipment and faults is constructed to form a knowledge graph containing cause-effect relationships. For example, the association between equipment temperature rise and a certain type of fault is recorded.

[0154] Through machine learning algorithms (such as association rule algorithms), potential relationships in historical fault data are mined, the strength of associations in the knowledge graph is strengthened, and the accuracy of diagnosis is improved.

[0155] 3. Intelligent diagnosis module

[0156] Failure mode identification:

[0157] Pattern recognition: Through the knowledge graph-based pattern matching algorithm, the current equipment status is matched with the historical failure patterns in the knowledge graph to identify possible failure types.

[0158] Use Graph Neural Network (GNN) to further mine complex equipment-fault association information and identify hidden failure modes.

[0159] Fault reasoning:

[0160] Rule reasoning: Utilize the relationships between equipment and fault, fault and cause in the knowledge graph, and use the rule-based reasoning engine to automatically deduce the possible causes of the current fault.

[0161] Machine learning diagnosis: Use random forest or support vector machine (SVM) models to analyze multi-dimensional equipment data to assist in identifying abnormal conditions and potential fault types that are not clearly defined in the knowledge graph.

[0162] Failure prediction:

[0163] Use time series models (such as ARIMA and LSTM) to predict equipment operation data, detect possible failures in advance, and issue warnings to operation and maintenance personnel.

[0164] Conduct trend analysis on equipment status data, combine predicted fault information with the associations in the knowledge graph, and further analyze possible chain reactions.

[0165] 4.Maintenance suggestion module

[0166] Automatically generate maintenance recommendations:

[0167] Based on the "fault-maintenance measures" relationship in the knowledge graph, specific maintenance suggestions are automatically generated, including repair steps, tool lists, maintenance materials, etc.

[0168] For complex fault conditions, the system will recommend corresponding preventive maintenance measures to help the equipment avoid the recurrence of the same type of fault.

[0169] Personalized maintenance plan:

[0170] The system generates a personalized maintenance plan based on the actual use of the equipment. For key equipment, more frequent inspections and maintenance are recommended, while for minor faults, less frequent maintenance is arranged.

[0171] By analyzing the equipment health index and empirical rules in the knowledge graph, detailed operation suggestions are provided to shorten maintenance time and improve equipment health level.

[0172] Dynamically update the knowledge graph:

[0173] After the maintenance suggestions are generated, the actual operation records are fed back to the knowledge graph library, and the graph content is dynamically updated to continuously improve the accuracy and timeliness of fault diagnosis and maintenance suggestions.

[0174] 5. Operation and maintenance visualization module

[0175] Fault and device status display:

[0176] Use a graphical interface to display the equipment operating status and real-time fault conditions. The interface design includes equipment parameters, fault information, prediction results, etc.

[0177] Fault information is presented in a graphically visualized way, showing the cause of the fault, affected components and related equipment, helping operation and maintenance personnel to intuitively understand the cause and impact of the fault.

[0178] Multi-level data display:

[0179] Different data levels are set in the system interface to support single information display and global overview of equipment, and provide integrated information display from "equipment-fault-maintenance".

[0180] The visual interface can display the health status of the equipment in different time periods and support viewing of specific fault details and diagnostic analysis results.

[0181] Visual tracking of maintenance process:

[0182] The system dynamically displays the maintenance progress during the maintenance process, helping operation and maintenance personnel to understand the maintenance progress in real time.

[0183] Visualize historical maintenance records and diagnostic results to support operation and maintenance personnel in comparing equipment conditions at different stages, helping to summarize equipment operation rules and optimize future maintenance strategies.

[0184] like Figure 2As shown, an embodiment of the present invention provides an electric equipment intelligent diagnosis and maintenance method based on a knowledge graph of an electric equipment intelligent diagnosis and maintenance system based on a knowledge graph, comprising the following steps:

[0185] Step 1: Data collection and preprocessing

[0186] 1. Data collection: Through sensors and monitoring systems, real-time data of power equipment, such as temperature, current, voltage and other operating data, is collected, and combined with the historical fault records and maintenance logs of the equipment.

[0187] 2. Data cleaning: Clean up outliers and fill in missing values ​​in the collected data to ensure the integrity and accuracy of the data.

[0188] 3. Data preprocessing: Standardize the data and convert the equipment status parameters into a unified numerical format for subsequent modeling and analysis.

[0189] Step 2: Knowledge graph construction

[0190] 1. Knowledge base establishment: The equipment type, fault type, fault cause, fault phenomenon, maintenance measures and other information are modeled through knowledge graph construction technology to form a knowledge base.

[0191] 2. Knowledge graph modeling: Based on the working principle and failure mode of power equipment, a knowledge graph of power equipment is constructed, which includes different categories of nodes such as equipment nodes, fault nodes, cause nodes, and maintenance measures nodes, and their relationships are described by edges.

[0192] 3. Data relationship definition: Define the relationship between different nodes (such as equipment-fault, fault-cause, cause-maintenance measures, etc.), convert the relationship into edges in the graph, and form a semantically rich association relationship network.

[0193] Step 3: Smart Diagnosis

[0194] 1. Fault pattern recognition: Through knowledge graphs and intelligent algorithms (such as rule-based reasoning, graph neural networks, etc.), the associations between different nodes are analyzed to identify common failure modes of power equipment.

[0195] 2. Fault reasoning analysis: Utilize the association relationship of the knowledge graph to perform reasoning analysis on the abnormal data of the equipment to determine the possible cause and type of the fault.

[0196] 3. Intelligent prediction: Based on the historical data and current operating status of the equipment, predict potential failure risks, reason through the associated information in the knowledge graph, and identify possible failures in advance.

[0197] Step 4: Maintenance suggestion generation

[0198] 1. Fault type identification: According to the diagnosed fault type, match the maintenance plan in the knowledge base and extract the maintenance measures and processes associated with the fault.

[0199] 2. Generate maintenance recommendations: Based on the specific equipment conditions, the system generates personalized maintenance recommendations, including detailed repair steps and preventive maintenance recommendations.

[0200] 3. Dynamic update: When the system receives new maintenance results, it updates the fault information to the knowledge base and continuously optimizes the content of the knowledge graph to make maintenance recommendations more complete.

[0201] Step 5: Visualization of operation and maintenance

[0202] 1. Fault and maintenance suggestion display: Through the operation and maintenance visualization module, fault nodes and related maintenance measures are displayed in a graphical manner, and visual analysis of the power equipment status is provided.

[0203] 2. Equipment status tracking: Displays the real-time status, fault trends and warning information of the equipment, helping operation and maintenance personnel to intuitively view the operation status of the equipment.

[0204] 3. Maintenance data backtracking: Supports operation and maintenance personnel to trace historical fault information and maintenance data through a visual interface to improve the pertinence of equipment fault handling.

[0205] The following are the detailed steps to implement the intelligent diagnosis and maintenance system of power equipment based on knowledge graph:

[0206] Step 1: Data collection and preprocessing

[0207] 1. Data collection:

[0208] Real-time data collection: Through sensors and monitoring systems installed on the equipment, real-time operating data of power equipment, such as temperature, current, voltage, etc., are collected. These data are transmitted to the system's central database through Internet of Things (IoT) devices.

[0209] Historical data integration: Combine the historical fault records and maintenance logs of the equipment and import them into the database through interfaces or file uploads to provide rich background data for subsequent knowledge graph construction.

[0210] 2. Data cleaning:

[0211] Outlier processing: Detect and remove outliers in the data, such as abnormal values ​​due to sensor failure. Use statistical methods (such as box plots, 3σ method) or machine learning algorithms (such as Isolation Forest) to identify anomalies.

[0212] Missing value processing: To fill in missing values, you can use the mean, median, or algorithms such as KNN (K-NearestNeighbors) to fill in missing values ​​to ensure data integrity.

[0213] 3. Data preprocessing:

[0214] Data standardization: Convert all equipment status parameters into a unified numerical format to ensure data consistency during the modeling process. Use standardization methods (such as normalization to the 0-1 range) to eliminate differences in different feature dimensions.

[0215] Feature extraction: Based on the physical meaning of different data and the characteristics of power equipment, key features such as temperature, current fluctuation, and equipment load are extracted to provide more focused data input for diagnosis.

[0216] Step 2: Knowledge graph construction

[0217] 1. Knowledge base establishment:

[0218] Knowledge base data definition: The type of equipment, common fault types, fault causes, fault phenomena, maintenance measures and other information are organized in a standardized format and stored in the knowledge base to form structured basic knowledge data of power equipment.

[0219] 2. Knowledge graph modeling:

[0220] Graph node creation: Based on the operation logic and failure mode of power equipment, create equipment nodes, failure nodes, cause nodes and maintenance measure nodes. Each node represents a power equipment status or diagnostic information.

[0221] Node attribute definition: Assign necessary attributes to each node, such as device nodes record model and maintenance history, fault nodes record fault type and probability of occurrence, and maintenance measure nodes contain specific steps.

[0222] 3. Data relationship definition:

[0223] Edge definition: By defining the relationship between the device and the fault node, the relationship type between different nodes is defined to generate the edge in the graph. For example, the edge between the device node and the fault node represents "a possible fault of the device".

[0224] Semantic relationship expansion: According to the maintenance logic of power equipment and the prior information recorded in the knowledge base, the relationship types are further enriched, such as converting the "fault-cause" and "cause-maintenance measures" relationships into connecting edges in the graph to form a semantically rich knowledge graph network.

[0225] Step 3: Smart Diagnosis

[0226] 1. Failure mode identification:

[0227] Pattern matching: Through the rule matching algorithm, the system can find historical failure modes similar to the current device status in the knowledge graph. Find qualified failure modes based on graph matching algorithms (such as depth-first traversal).

[0228] Intelligent algorithm application: Use graph neural network (GNN) to analyze the node relationships in the knowledge graph, identify complex equipment-fault associations, and enhance the system's recognition accuracy of fault modes.

[0229] 2. Fault reasoning analysis:

[0230] Rule reasoning: Based on the node relationships in the knowledge graph, a rule-based reasoning engine is used to reason about device abnormal data. The rule engine derives the possible causes and types of faults based on the logical relationships in the knowledge graph.

[0231] Machine learning diagnosis: By introducing machine learning algorithms such as random forest and support vector machine (SVM), potential faults are predicted based on the multi-dimensional feature input of the equipment, assisting graph reasoning and improving diagnostic accuracy.

[0232] 3. Intelligent prediction:

[0233] Time series analysis: Use ARIMA or LSTM models to predict equipment operation data and detect possible failure risks in advance.

[0234] Association reasoning: The predicted abnormal conditions are inferred through the association information in the knowledge graph, and possible faults associated with them are identified in advance to form risk warnings.

[0235] Step 4: Maintenance suggestion generation

[0236] 1. Fault type identification:

[0237] Maintenance measure matching: The system searches the knowledge base for the corresponding maintenance plan based on the diagnosed fault type and extracts the content of the maintenance measure node.

[0238] 2. Generate maintenance recommendations:

[0239] Personalized maintenance: The system combines the actual status of the equipment and environmental factors (such as equipment load, age, etc.) to generate customized maintenance recommendations, including specific information such as tools, materials, and steps required for maintenance.

[0240] Preventive maintenance recommendations: If a device is detected to have a high potential failure risk, the system will generate preventive maintenance recommendations to remind operation and maintenance personnel to check the relevant equipment in advance to prevent the failure from escalating.

[0241] 3. Dynamic Update:

[0242] Fault information feedback: Feedback information after each maintenance is uploaded to the knowledge base, and the knowledge graph will dynamically update the association relationship of the new data to provide a reference for future fault diagnosis and maintenance optimization.

[0243] Knowledge graph optimization: Through continuous updates, the relationship between fault nodes and maintenance measure nodes in the knowledge graph is made more accurate, improving the quality of maintenance recommendations.

[0244] Step 5: Visualization of operation and maintenance

[0245] 1. Fault and maintenance suggestion display:

[0246] Graphical display: Visualize the knowledge graph and display the relationship between each fault node and related maintenance measures on the interface to help operation and maintenance personnel intuitively understand the cause of the current equipment failure and possible maintenance solutions.

[0247] Multi-dimensional display of data: The visual interface allows operation and maintenance personnel to filter data according to different dimensions and display information such as single device status, fault trends, maintenance progress, etc.

[0248] 2. Equipment status tracking:

[0249] Real-time data update: The system interface refreshes the equipment status, fault trend and warning information in real time. Operation and maintenance personnel can check the latest equipment operation status at any time to improve the timeliness of monitoring and response.

[0250] Dynamic alarm: When the equipment status is abnormal, the system will immediately alarm on the interface to help operation and maintenance personnel find and handle faults in time.

[0251] 3.Maintenance data backtracking:

[0252] Historical data tracing: Through the visual interface, you can view the historical maintenance records and fault details of the equipment, which helps to summarize the causes of the faults and optimize future maintenance plans.

[0253] Fault and maintenance graph: The system displays the historical fault nodes and corresponding maintenance measures of the equipment in the form of a graph, which is convenient for operation and maintenance personnel to summarize the experience rules of equipment maintenance.

[0254] Significant technological advancement brought by the system

[0255] 1. Improved fault diagnosis accuracy: Through the combination of knowledge graph technology and intelligent algorithms, the system can identify complex equipment fault associations, avoid false positives and false negatives caused by single parameter judgment, and improve fault diagnosis accuracy.

[0256] 2. Enhanced prediction and prevention capabilities: The combination of time series analysis and knowledge graph reasoning enables the system to detect potential faults in advance, promptly remind operation and maintenance personnel to take preventive maintenance measures, and reduce the risk of equipment downtime.

[0257] 3. Improved maintenance efficiency: The system generates customized maintenance suggestions and provides graphical displays to help operation and maintenance personnel quickly and accurately handle faults, shorten repair time and save maintenance costs.

[0258] 4. Dynamic optimization of the knowledge base: With the continuous updating of data, the system knowledge graph is continuously expanded and optimized, gradually forming an industry knowledge accumulation and equipment operation and maintenance experience base, providing a reliable basis for future diagnosis and maintenance.

[0259] 5. Visual support for operation and maintenance decisions: The visual fault diagnosis and maintenance suggestion display interface enables operation and maintenance personnel to intuitively view equipment status and fault information, thereby supporting efficient maintenance decisions.

[0260] The intelligent diagnosis module uses Bayesian theorem to calculate the fault probability. The specific calculation formula is as follows:

[0261]

[0262] in:

[0263] P(FD) is the posterior probability of fault F occurring when data D is observed;

[0264] P(DF) represents the probability of observing data D when fault F occurs;

[0265] P(F) represents the prior probability of fault F;

[0266] P(D) represents the total probability of observing data D.

[0267] By applying the above Bayesian theorem, the intelligent diagnosis module can accurately calculate the occurrence probability of different faults \(F\) based on the real-time collected data \(D\), thereby improving the accuracy and reliability of fault identification.

[0268] The data acquisition and preprocessing module uses Fourier Transform to perform frequency domain analysis on the collected power equipment operation data. The specific mathematical expression is as follows:

[0269]

[0270] in:

[0271] x(t) represents the time domain signal;

[0272] X(f) represents the corresponding frequency domain signal;

[0273] f represents frequency;

[0274] ·j is an imaginary unit.

[0275] By applying Fourier transform, the data acquisition and preprocessing module can convert time domain signals into frequency domain signals and extract the frequency characteristics of equipment operation. This frequency domain analysis method can effectively identify periodic anomalies and noise in equipment operation, enhance data analysis capabilities, and improve the accuracy and reliability of fault diagnosis.

[0276] Bayesian theorem is introduced to calculate the posterior probability of fault occurrence. Bayesian theorem is a statistical method based on probability theory that can combine prior knowledge and new observation data to update the estimate of the probability of fault occurrence. With this method, the intelligent diagnosis module can more accurately identify and predict potential faults of power equipment and improve the overall diagnostic capability of the system.

[0277] Fourier transform is introduced to convert time domain signals into frequency domain signals. Fourier transform is a mathematical tool widely used in signal processing, which can effectively analyze and extract frequency components in signals. Through frequency domain analysis, the data acquisition and preprocessing module can identify periodic anomalies and noise in equipment operation, improve the analysis depth of data and the accuracy of fault diagnosis.

[0278] The system not only has intelligent diagnosis and maintenance capabilities based on knowledge graphs, but also combines advanced mathematical formulas to further improve the accuracy and efficiency of fault identification and prediction, thereby significantly enhancing the technical level and application value of the entire system.

[0279] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. It can be understood by a person of ordinary skill in the art that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0280] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims

1. An intelligent diagnosis and maintenance system for power equipment based on knowledge graph, characterized in that: include: Data collection and preprocessing module, used to collect real-time operation data and historical data of power equipment, including temperature, humidity, current, voltage, as well as historical fault records and maintenance logs, and generate high-quality data sets through data standardization processing; The knowledge graph construction module is used to construct the power equipment information into a knowledge graph, convert the equipment, fault, and maintenance measures information into a node and edge relationship library, determine the association distance between different nodes based on the shortest path algorithm of the weighted graph, and generate the fault propagation path to identify the key fault nodes; The intelligent diagnosis module, based on the knowledge graph and Bayesian network algorithm, performs probabilistic reasoning on fault data, calculates the probability of occurrence of various fault modes, and predicts potential failures of equipment; Maintenance suggestion module, which automatically generates detailed maintenance plans based on diagnosis results, including troubleshooting steps and preventive maintenance suggestions; The operation and maintenance visualization module is used to display fault diagnosis results and maintenance suggestions. It supports multi-level data display and provides operation and maintenance personnel with a clear view of equipment status.

2. The power equipment intelligent diagnosis and maintenance system based on knowledge graph according to claim 1 is characterized in that: The intelligent diagnosis module uses Bayesian theorem to calculate the fault probability, and its specific calculation formula is as follows: in: P(F|D) is the posterior probability of fault F occurring when data D is observed; P(D|F) represents the probability of observing data D when fault F occurs; P(F) represents the prior probability of fault F; P(D) represents the total probability of observing data D.

3. The power equipment intelligent diagnosis and maintenance system based on knowledge graph according to claim 1 is characterized in that: The data acquisition and preprocessing module uses Fourier Transform to perform frequency domain analysis on the collected power equipment operation data. The specific mathematical expression is as follows: in: x(t) represents the time domain signal; X(f) represents the corresponding frequency domain signal; f represents frequency; ·j is an imaginary unit.

4. The power equipment intelligent diagnosis and maintenance system based on knowledge graph according to claim 1, characterized in that: The intelligent diagnosis module includes: Failure mode identification: Pattern recognition: Through the knowledge graph-based pattern matching algorithm, the current equipment status is matched with the historical failure patterns in the knowledge graph to identify possible failure types; Use graph neural networks (GNNs) to further mine complex equipment-fault association information and identify hidden fault modes; Fault reasoning: Rule reasoning: Using the relationship between equipment-fault and fault-cause in the knowledge graph, the possible cause of the current fault can be automatically deduced through a rule-based reasoning engine; Machine learning diagnosis: Use random forest or support vector machine (SVM) models to analyze multi-dimensional equipment data to assist in identifying abnormal conditions and potential fault types that are not clearly defined in the knowledge graph; Failure prediction: Use time series models (ARIMA, LSTM) to predict equipment operation data, detect possible failures in advance and issue warnings to operation and maintenance personnel; Conduct trend analysis on equipment status data, combine predicted fault information with the associations in the knowledge graph, and further analyze possible chain reactions.

5. The power equipment intelligent diagnosis and maintenance system based on knowledge graph according to claim 1, characterized in that: The maintenance advice module includes: Automatically generate maintenance recommendations: Automatically generate specific maintenance suggestions based on the "fault-maintenance measures" association relationship in the knowledge graph, including maintenance steps, tool lists, and maintenance materials; For complex fault conditions, the system will recommend corresponding preventive maintenance measures to help the equipment avoid the recurrence of the same type of fault; Personalized maintenance plan: The system generates a personalized maintenance plan based on the actual use of the equipment. For key equipment, more frequent inspections and maintenance are recommended, while for minor faults, less frequent maintenance is arranged. By analyzing the equipment health index and empirical rules in the knowledge graph, detailed operation suggestions are provided to shorten maintenance time and improve equipment health level; Dynamically update the knowledge graph: After the maintenance suggestions are generated, the actual operation records are fed back to the knowledge graph library, and the graph content is dynamically updated to continuously improve the accuracy and timeliness of fault diagnosis and maintenance suggestions.

6. The power equipment intelligent diagnosis and maintenance system based on knowledge graph according to claim 1, characterized in that: The operation and maintenance visualization module includes: Fault and device status display: Use a graphical interface to display the equipment operating status and real-time fault conditions; the interface design includes equipment parameters, fault information, and prediction results; Fault information is presented in a visual way, showing the cause of the fault, affected components and related equipment, helping operation and maintenance personnel to intuitively understand the cause and impact of the fault; Multi-level data display: Set different data levels in the system interface to support single information display and global overview of equipment, and provide integrated information display from "equipment-fault-maintenance"; The visual interface can display the health status of the equipment in different time periods, and support viewing of specific fault details and diagnostic analysis results; Visual tracking of maintenance process: The system dynamically displays the maintenance progress during the maintenance process, helping operation and maintenance personnel to grasp the maintenance progress in real time; Visualize historical maintenance records and diagnostic results to support operation and maintenance personnel in comparing equipment conditions at different stages, helping to summarize equipment operation rules and optimize future maintenance strategies.

7. A method for intelligent diagnosis and maintenance of power equipment based on knowledge graph according to any one of claims 1 to 6, characterized in that: The following steps are involved: Step 1: Data collection and preprocessing (1) Data collection: Through sensors and monitoring systems, real-time data of power equipment is collected, including temperature, current, and voltage operating data, combined with historical fault records and maintenance logs of the equipment; (2) Data cleaning: clean up outliers and fill in missing values ​​in the collected data to ensure the integrity and accuracy of the data; (3) Data preprocessing: standardize the data and convert the equipment status parameters into a unified numerical format for subsequent modeling and analysis; Step 2: Knowledge graph construction (1) Knowledge base establishment: The equipment type, fault type, fault cause, fault phenomenon, and maintenance measures information are modeled through knowledge graph construction technology to form a knowledge base; (2) Knowledge graph modeling: Based on the working principle and failure mode of power equipment, a knowledge graph of power equipment is constructed, which includes different types of nodes such as equipment nodes, failure nodes, cause nodes, and maintenance measure nodes, and their relationships are described by edges; (3) Data relationship definition: Define the relationships between different nodes, including equipment-fault, fault-cause, and cause-maintenance measures, and convert the relationships into edges in the graph to form a semantically rich association relationship network; Step 3: Smart Diagnosis (1) Fault pattern recognition: Through knowledge graphs and intelligent algorithms, including rule-based reasoning and graph neural networks, the associations between different nodes are analyzed to identify common fault patterns of power equipment; (2) Fault reasoning analysis: Using the association relationship of the knowledge graph, we can perform reasoning analysis on the abnormal data of the equipment to determine the possible cause and type of the fault. (3) Intelligent prediction: Based on the historical data and current operating status of the equipment, potential failure risks are predicted, and possible failures are identified in advance through reasoning based on the associated information in the knowledge graph; Step 4: Maintenance suggestion generation (1) Fault type identification: According to the diagnosed fault type, the maintenance plan in the knowledge base is matched and the maintenance measures and processes associated with the fault are extracted; (2) Generate maintenance suggestions: Based on the specific equipment conditions, the system generates personalized maintenance suggestions, including detailed maintenance steps and preventive maintenance suggestions; (3) Dynamic update: When the system receives new maintenance results, it updates the fault information to the knowledge base and continuously optimizes the content of the knowledge graph to make maintenance recommendations more complete; Step 5: Visualization of operation and maintenance (1) Fault and maintenance suggestion display: The operation and maintenance visualization module graphically displays fault nodes and related maintenance measures, and provides visual analysis of the power equipment status; (2) Equipment status tracking: Displays the real-time status, fault trends, and warning information of the equipment, helping operation and maintenance personnel to intuitively view the operation status of the equipment; (3) Maintenance data backtracking: Supports operation and maintenance personnel to trace historical fault information and maintenance data through a visual interface, improving the targeted handling of equipment faults.

8. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the knowledge graph-based intelligent diagnosis and maintenance method for power equipment as described in claim 7.

9. A computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to execute the steps of the method for intelligent diagnosis and maintenance of power equipment based on knowledge graph as described in claim 7.

10. An information data processing terminal, characterized in that: The information data processing terminal includes the knowledge graph-based intelligent diagnosis and maintenance system for power equipment as described in any one of claims 1 to 6.

Images