Fault diagnosis method and device for power equipment, equipment and medium

By cooperating with real-time online fault monitoring and fault diagnosis models for power plant equipment, fault diagnosis reports are generated, and problems of low fault diagnosis efficiency and high labor costs in the existing technology are solved, automated fault diagnosis is achieved, and diagnostic accuracy is improved. Sex and consistency.

CN118886884APending Publication Date: 2024-11-01LINGSHU TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411030958.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-30
Publication Date
2024-11-01

AI Technical Summary

Technical Problem

The existing power plant equipment fault diagnosis system has not yet achieved high intelligence and automation, resulting in low fault diagnosis efficiency, high labor costs, and lack of effective mechanisms to update the fault knowledge base in real time, resulting in the diagnosis results not including the latest fault cases and Solution.

Method used

By conducting real-time online fault monitoring of the to-diagnostic equipment, obtain equipment abnormal data, and input it into the trained fault diagnosis model, use the pre-constructed fault knowledge base to find fault association data, generate fault diagnosis reports, and realize automated fault diagnosis.

Benefits of technology

Improves fault diagnosis efficiency, reduces labor costs, ensures that the diagnostic results include the latest fault cases and solutions, improves the accuracy and consistency of diagnosis, and can effectively identify and handle complex fault patterns to meet personalized and customized Troubleshooting requirements.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118886884A_ABST
    Figure CN118886884A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a fault diagnosis method and device for power equipment, equipment and a medium. The method comprises the steps of performing real-time online fault monitoring on to-be-diagnosed equipment, and if a monitoring result is abnormal, obtaining equipment abnormal data of the to-be-diagnosed equipment; determining an equipment fault mode according to the equipment abnormal data, inputting the equipment abnormal data and the equipment fault mode into a trained fault diagnosis model, and searching fault associated data in a pre-constructed fault knowledge base by the fault diagnosis model according to the equipment abnormal data and the equipment fault mode, generating and outputting a fault diagnosis report according to the fault associated data; and performing equipment maintenance on the to-be-diagnosed equipment according to the fault diagnosis report. According to the scheme, automatic fault diagnosis of the to-be-diagnosed equipment is realized, the fault diagnosis efficiency is improved, and the labor cost is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of equipment fault processing, and in particular to a fault diagnosis method, device, equipment and medium for electric power equipment. Background Art

[0002] In the existing power plant equipment fault diagnosis system, many existing fault diagnosis systems have not yet achieved a high degree of intelligence and automation, and require manual intervention to complete fault diagnosis. Therefore, how to improve the efficiency of fault diagnosis and reduce labor costs is crucial. Summary of the invention

[0003] The present invention provides a fault diagnosis method, device, equipment and medium for electric equipment, so as to realize automatic fault diagnosis of electric equipment, improve fault diagnosis efficiency and reduce labor cost.

[0004] According to one aspect of the present invention, there is provided a method for diagnosing a fault of an electric power device, comprising:

[0005] Performing real-time online fault monitoring on the device to be diagnosed, and if the monitoring result is abnormal, obtaining device abnormality data of the device to be diagnosed;

[0006] Determine a device failure mode according to the device abnormal data, and input the device abnormal data and the device failure mode into a trained fault diagnosis model, wherein the fault diagnosis model searches for fault-related data in a pre-built fault knowledge base according to the device abnormal data and the device failure mode, and generates and outputs a fault diagnosis report according to the fault-related data;

[0007] Perform equipment maintenance on the device to be diagnosed according to the fault diagnosis report.

[0008] According to another aspect of the present invention, there is provided a fault diagnosis device for electric power equipment, comprising:

[0009] The device abnormality data acquisition module is used to perform real-time online fault monitoring on the device to be diagnosed, and if the monitoring result is abnormal, obtain the device abnormality data of the device to be diagnosed;

[0010] A fault diagnosis report generation module, used to determine a device failure mode according to the device abnormal data, and input the device abnormal data and the device failure mode into a trained fault diagnosis model, wherein the fault diagnosis model searches for fault-related data in a pre-built fault knowledge base according to the device abnormal data and the device failure mode, and generates and outputs a fault diagnosis report according to the fault-related data;

[0011] The equipment maintenance module is used to perform equipment maintenance on the equipment to be diagnosed according to the fault diagnosis report.

[0012] According to another aspect of the present invention, there is provided an electronic device, comprising:

[0013] one or more processors;

[0014] A memory for storing one or more programs;

[0015] When one or more programs are executed by one or more processors, the one or more processors can execute any one of the fault diagnosis methods for electric power equipment provided by the embodiments of the present invention.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions, and the computer instructions are used to enable a processor to implement any one of the fault diagnosis methods for electric power equipment provided in the embodiments of the present invention when executed.

[0017] The embodiment of the present invention provides a fault diagnosis scheme for power equipment, which performs real-time online fault monitoring on the equipment to be diagnosed. If the monitoring result is abnormal, the equipment abnormality data of the equipment to be diagnosed is obtained; the equipment failure mode is determined according to the equipment abnormality data, and the equipment abnormality data and the equipment failure mode are input into a trained fault diagnosis model. The fault diagnosis model searches for fault-related data in a pre-built fault knowledge base according to the equipment abnormality data and the equipment failure mode, and generates and outputs a fault diagnosis report according to the fault-related data; and the equipment to be diagnosed is maintained according to the fault diagnosis report. The above scheme, by introducing a fault diagnosis model and a fault knowledge base, generates a fault diagnosis report through the mutual cooperation of the fault diagnosis model and the fault knowledge base, realizes the automated fault diagnosis of the equipment to be diagnosed, improves the fault diagnosis efficiency, and reduces the labor cost.

[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 is a flow chart of a method for diagnosing a fault of an electric power device provided in the first embodiment of the present invention;

[0021] Figure 2is a flow chart of a method for diagnosing a fault of an electric power device provided in Embodiment 2 of the present invention;

[0022] Figure 3 It is a structural schematic diagram of a fault diagnosis device for electric power equipment provided by a fourth embodiment of the present invention;

[0023] Figure 4 It is a structural schematic diagram of an electronic device for implementing a fault diagnosis method for electric power equipment provided in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0025] In the existing power plant equipment fault diagnosis system, there may be a problem of low efficiency in retrieving historical fault cases, resulting in a long time for fault diagnosis. There may be a lack of effective mechanisms to update the fault knowledge base in real time, so that the diagnosis results may not contain the latest fault cases and solutions. Due to the lack of effective information retrieval and knowledge integration mechanisms, the diagnosis results may be inconsistent in different situations, affecting the accuracy of fault handling. It may be difficult to effectively integrate and analyze data from different sources to identify and handle complex fault modes. Many existing fault diagnosis systems have not yet achieved a high degree of intelligence and automation, and manual intervention is required to complete fault diagnosis. Different power plants may have different equipment configurations and operating environments, and existing systems may not be able to meet personalized and customized fault diagnosis needs.

[0026] Embodiment 1

[0027] Figure 1 It is a flow chart of a fault diagnosis method for electric power equipment provided in Embodiment 1 of the present invention. This embodiment can be applicable to situations where fault diagnosis of electric power equipment is performed. The method can be executed by a fault diagnosis device for electric power equipment. The device can be implemented in software and / or hardware and can be configured in an electronic device that carries the fault diagnosis function of the electric power equipment.

[0028] See also Figure 1 The fault diagnosis method of the electric power equipment shown comprises:

[0029] S110 , performing real-time online fault monitoring on the device to be diagnosed, and if the monitoring result is abnormal, obtaining device abnormality data of the device to be diagnosed.

[0030] The device to be diagnosed refers to the power device that needs to be diagnosed. The embodiment of the present invention does not limit the type of the device to be diagnosed, and the type can be set by the technician based on experience. The device abnormality data refers to the operating data of the device to be diagnosed when a fault occurs.

[0031] Exemplarily, at least one device to be diagnosed is subjected to real-time or periodic fault monitoring to obtain device operation data of each device to be diagnosed; preset standard operation data corresponding to each device to be diagnosed is determined respectively; the device operation data of the device to be diagnosed is matched with the corresponding preset standard operation data; and the monitoring result of the device to be diagnosed is determined according to the matching result. The preset standard operation data refers to the data of the device to be diagnosed in normal operation state which is preset.

[0032] Exemplarily, matching the device operation data of the device to be diagnosed with the corresponding preset standard operation data includes: determining any operation sub-data in the device operation data of the device to be diagnosed, and determining the standard sub-data corresponding to the operation sub-data in the preset standard operation data; matching the operation sub-data with the standard sub-data; correspondingly, determining the monitoring result of the device to be diagnosed according to the matching result, including: if the matching result is that the operation sub-data matches the standard sub-data, then determining the monitoring sub-result of the device to be diagnosed as normal monitoring; if the matching result is that the operation sub-data does not match the standard sub-data, then determining the monitoring sub-result of the device to be diagnosed as abnormal monitoring; and determining the monitoring result of the device to be diagnosed according to the monitoring sub-result. Among them, the operation sub-data refers to a sub-data in the device operation data. The standard sub-data refers to a sub-data in the preset standard operation data. The monitoring sub-result refers to the device monitoring result corresponding to the operation sub-data determined according to any operation sub-data in the device operation data.

[0033] Exemplarily, if the monitoring result is abnormal, obtaining device abnormality data of the device to be diagnosed includes: using the operation sub-data corresponding to the monitoring abnormality in the monitoring sub-result of the monitoring result as the device abnormality data.

[0034] Exemplarily, respectively determining the preset standard operation data corresponding to each device to be diagnosed includes: for any device to be diagnosed, determining the device operation mode of the device to be diagnosed; selecting the preset standard operation data corresponding to the device to be diagnosed from a pre-built standard operation database according to the device operation mode. Among them, the device operation mode may include the device type of the device to be diagnosed, and the device operation status of the device to be diagnosed. The device type refers to the type of the device to be diagnosed. The device operation status refers to the device operation stage of the device to be diagnosed at the current moment. For example, the device operation status may include the start stage, the no-load stage, and the load stage.

[0035] S120. Determine the equipment failure mode according to the equipment abnormality data, and input the equipment abnormality data and the equipment failure mode into the trained fault diagnosis model. The fault diagnosis model searches for fault-related data in a pre-built fault knowledge base according to the equipment abnormality data and the equipment failure mode, and generates and outputs a fault diagnosis report according to the fault-related data.

[0036] Among them, the equipment failure mode may include the equipment type, equipment operating status and equipment failure type. The equipment failure type refers to the type of failure of the equipment to be diagnosed. The fault diagnosis model has a retrieval mechanism and a generation mechanism, that is, the fault diagnosis model can retrieve the fault knowledge base according to the equipment abnormal data and the equipment failure mode, and generate a fault diagnosis report according to the retrieval results. The embodiment of the present invention does not impose any limitation on the structure adopted by the fault diagnosis model, which can be set by the technician based on experience. Exemplarily, the fault diagnosis model can be a large language model. For example, the fault diagnosis model is a RAG (Retrieval-Augmented Generation) model. The advantage of using the RAG model is to improve the retrieval efficiency. Design and train the fault diagnosis model so that it can understand the equipment data and failure cases.

[0037] Among them, the fault knowledge base refers to a pre-built database for storing equipment fault information. The fault knowledge base may include equipment information, fault cases and maintenance strategies. Exemplarily, the fault knowledge base can be constructed based on the following methods: obtaining historical operation data, historical fault cases and historical maintenance logs of power equipment; constructing the fault knowledge base based on historical operation data, historical fault cases and historical maintenance logs. The fault knowledge base in the embodiment of the present invention can be constructed based on the technical framework of RAG, so that the fault knowledge base can be dynamically updated.

[0038] Among them, historical operation data refers to the previous operation data of the power equipment. Exemplarily, the historical operation data may include historical normal operation data and historical abnormal operation data. Historical normal operation data refers to the equipment operation data of the power equipment when there was no fault in the past. Historical abnormal operation data refers to the equipment operation data of the power equipment when there was an abnormality in the past. Historical failure cases refer to the previous failure instances of the power equipment. Historical maintenance logs refer to the previous fault repair strategies of the power equipment.

[0039] Exemplarily, in order to improve the usability of the subsequent fault knowledge base, the acquired historical operation data, historical fault cases and historical maintenance logs may be preprocessed to facilitate subsequent fault analysis and processing. The embodiment of the present invention does not impose any limitation on the preprocessing method, which may be set by a technician based on experience. Exemplarily, the preprocessing may include at least one of data cleaning, standardization and formatting.

[0040] The historical operation data in the embodiment of the present invention is numerical data, which is cleaned, standardized and formatted to facilitate subsequent fault analysis and processing; historical fault cases and historical maintenance logs are text data, which are segmented to generate different text fragments, which are then vectorized and stored in a vector database; a fault knowledge base containing equipment information, fault cases and maintenance strategies is constructed through the preprocessed data.

[0041] The fault-related data refers to data used to generate a fault diagnosis report. The fault diagnosis report refers to a textual statement that can be used to instruct a user to perform maintenance on the device to be diagnosed. Exemplarily, the fault diagnosis report may include at least one of the cause of the fault of the device to be diagnosed, the recommended checkpoints in the device to be diagnosed, and the maintenance strategy of the device to be diagnosed.

[0042] It should be noted that the fault diagnosis model and the fault knowledge base in the embodiment of the present invention are bundled together. The fault diagnosis model can be understood as a tool for data retrieval and report generation of the fault knowledge base, that is, the fault diagnosis model searches the fault knowledge base according to the input device abnormal data and device failure mode, and generates a fault diagnosis report according to the retrieval results.

[0043] S130. Perform equipment maintenance on the device to be diagnosed according to the fault diagnosis report.

[0044] Specifically, according to the fault diagnosis report, the fault point, fault cause and maintenance strategy of the equipment to be diagnosed are determined to achieve equipment maintenance for the equipment to be diagnosed.

[0045] The embodiment of the present invention provides a fault diagnosis scheme for power equipment, which performs real-time online fault monitoring on the equipment to be diagnosed. If the monitoring result is abnormal, the equipment abnormality data of the equipment to be diagnosed is obtained; the equipment failure mode is determined according to the equipment abnormality data, and the equipment abnormality data and the equipment failure mode are input into a trained fault diagnosis model. The fault diagnosis model searches for fault-related data in a pre-built fault knowledge base according to the equipment abnormality data and the equipment failure mode, and generates and outputs a fault diagnosis report according to the fault-related data; and the equipment to be diagnosed is maintained according to the fault diagnosis report. The above scheme, by introducing a fault diagnosis model and a fault knowledge base, generates a fault diagnosis report through the mutual cooperation of the fault diagnosis model and the fault knowledge base, realizes the automated fault diagnosis of the equipment to be diagnosed, improves the fault diagnosis efficiency, and reduces the labor cost.

[0046] Embodiment 2

[0047] Figure 2It is a flow chart of a fault diagnosis method for electric power equipment provided in the second embodiment of the present invention. Based on the above embodiments, this embodiment further refines the operation of "searching for fault-related data in a pre-built fault knowledge base according to equipment abnormal data and equipment failure mode, and generating and outputting a fault diagnosis report according to the fault-related data" into "selecting a reference fault mode from the candidate fault modes in the fault knowledge base according to the equipment failure mode; matching reference abnormal data in the candidate abnormal data under the reference fault mode according to the equipment abnormal data, and determining a target fault mode according to the reference fault mode corresponding to the reference abnormal data, and using the reference abnormal data under the target fault mode as the target abnormal data; determining fault-related data according to the target abnormal data, the target failure mode and a preset fault knowledge template, and generating and outputting a fault diagnosis report according to the fault-related data" to improve the determination mechanism of the fault diagnosis report. It should be noted that for the parts not described in detail in the embodiments of the present invention, reference may be made to the descriptions of other embodiments.

[0048] See also Figure 2 The fault diagnosis method of the electric power equipment shown comprises:

[0049] S210: Perform real-time online fault monitoring on the device to be diagnosed. If the monitoring result is abnormal, obtain device abnormality data of the device to be diagnosed.

[0050] S220, determining the equipment failure mode according to the equipment abnormality data, and inputting the equipment abnormality data and the equipment failure mode into the trained fault diagnosis model, and the fault diagnosis model selects a reference failure mode from the candidate failure modes in the fault knowledge base according to the equipment failure mode.

[0051] The candidate failure mode refers to the equipment failure mode stored in the failure knowledge base, and the reference failure mode refers to the candidate failure mode that matches the equipment failure mode.

[0052] S230 . Match reference abnormal data in candidate abnormal data under a reference fault mode according to the device abnormal data, determine a target fault mode according to a reference fault mode corresponding to the reference abnormal data, and use the reference abnormal data under the target fault mode as the target abnormal data.

[0053] Among them, candidate abnormal data refers to device failure data under candidate device mode. Reference abnormal data refers to candidate abnormal data that matches the device abnormal data. Target failure mode refers to a reference failure mode that can be used to generate a fault diagnosis report. Exemplarily, the target failure mode can be understood as a reference failure mode with a high similarity to the device failure mode. Target abnormal data refers to reference abnormal data under the target failure mode. Exemplarily, the target abnormal data can be understood as reference abnormal data with a high similarity to the device abnormal data.

[0054] Specifically, the fault diagnosis model selects reference abnormal data from candidate abnormal data under a reference fault mode according to the input device abnormal data, determines a target fault mode according to a reference fault mode corresponding to the reference abnormal data, and uses the reference abnormal data under the target fault mode as the target abnormal data.

[0055] In an optional embodiment, a target fault mode is determined according to a reference fault mode corresponding to reference abnormal data, including: for each reference abnormal data under the reference fault mode, respectively determining the similarity between each reference abnormal data and the device abnormal data; sorting the reference fault modes according to the similarity between the reference abnormal data and the device abnormal data, and determining the target fault mode corresponding to the device abnormal data based on the sorting result.

[0056] The similarity can be used to quantify the similarity between the reference abnormal data and the device abnormal data.

[0057] Exemplarily, for any reference abnormal data, a data vector of the reference abnormal data is determined, and a data vector of the device abnormal data is determined; based on the Euclidean distance, the similarity between the reference abnormal data and the device abnormal data is determined according to the data vector of the reference abnormal data and the data vector of the device abnormal data.

[0058] Furthermore, according to the similarity, the reference fault modes are sorted from large to small to obtain a sorting result.

[0059] It can be understood that by introducing similarity, the target failure mode is selected from the reference failure mode, thereby improving the accuracy of the selected target failure mode.

[0060] In an optional embodiment, determining the target failure mode corresponding to the device abnormal data based on the sorting result includes: selecting the target failure modes corresponding to a preset threshold number of device abnormal data from the sorting result.

[0061] The embodiment of the present invention does not impose any limitation on the size of the preset threshold, which can be set by a technician based on experience or repeatedly determined through a large number of experiments.

[0062] Specifically, the reference fault mode that is in front of a preset threshold in the sorting result is used as the target fault mode.

[0063] It can be understood that by introducing a preset threshold and selecting a preset threshold number of target fault modes from the reference fault modes, the number of target fault modes is limited, avoiding the situation where a large number of target fault modes with low similarity result in cumbersome subsequent generation of fault diagnosis reports, thereby improving the generation efficiency and accuracy of fault diagnosis reports.

[0064] S240 , determining fault-related data according to target abnormal data, target fault mode and preset fault knowledge template, and generating and outputting a fault diagnosis report according to the fault-related data.

[0065] The fault knowledge template refers to a fault information template pre-set in the fault knowledge base. For example, the fault knowledge template may include equipment information, fault causes, and maintenance strategies.

[0066] Specifically, the fault diagnosis model generates fault-related data according to target abnormal data, target fault mode and fault knowledge template, generates a fault diagnosis report according to the fault-related data, and outputs the fault diagnosis report.

[0067] S250. Perform equipment maintenance on the device to be diagnosed according to the fault diagnosis report.

[0068] The embodiment of the present invention provides a fault diagnosis scheme for electric power equipment, which refines the operation of searching for fault-related data in a pre-built fault knowledge base according to equipment abnormal data and equipment failure mode, and generating and outputting a fault diagnosis report according to the fault-related data into selecting a reference fault mode from candidate fault modes in the fault knowledge base according to the equipment failure mode; matching reference abnormal data in candidate abnormal data under the reference fault mode according to the equipment abnormal data, and determining a target fault mode according to the reference fault mode corresponding to the reference abnormal data, and taking the reference abnormal data under the target fault mode as the target abnormal data; determining fault-related data according to the target abnormal data, the target fault mode and a preset fault knowledge template, and generating and outputting a fault diagnosis report according to the fault-related data, thereby improving the determination mechanism of the fault diagnosis report. The above scheme, by combining equipment failure mode and equipment abnormal data, jointly determines the target failure mode and the target abnormal data, avoids the omission of the determined target abnormal data and the target failure mode, and improves the comprehensiveness of the target abnormal data and the target failure mode; at the same time, introduces the fault knowledge template, and improves the accuracy of generating the fault diagnosis report.

[0069] On the basis of the above technical solution, an embodiment of the present invention further provides a method for automatically updating a fault knowledge base. Exemplarily, after determining a target fault mode according to a reference fault mode corresponding to reference abnormal data, the method further includes: if the number of target fault modes is 0, the fault diagnosis model generates a target fault mode based on the input device abnormal data and device fault mode; and updates the fault knowledge base according to the target fault mode.

[0070] Specifically, if the fault diagnosis model does not find the target fault mode in the fault knowledge base, the fault diagnosis model infers at least one target fault mode based on the input device abnormality data and device failure mode; the fault diagnosis model feeds back the target failure mode to the fault knowledge base so that the fault knowledge base is automatically updated according to the target failure mode.

[0071] It can be understood that by automatically updating the fault knowledge base according to the target fault mode generated by the fault diagnosis model, the real-time and comprehensiveness of the information in the fault knowledge base are improved.

[0072] Embodiment 3

[0073] Based on the above technical solution, a fault diagnosis system for power equipment is provided, which aims to improve the accuracy and efficiency of fault diagnosis through efficient information retrieval and intelligent generation technology. The system may include an equipment monitoring module, a data acquisition module, a fault diagnosis module and a fault display module. The fault diagnosis module includes a fault diagnosis model and a fault knowledge base. Exemplarily, the fault display module can be a user interaction interface. The user interaction interface allows the maintenance team to input the equipment status, view the fault diagnosis report, and provide feedback; the interface should support the query of fault knowledge, the browsing of fault cases and the recommendation of maintenance strategies.

[0074] Among them, the equipment monitoring module can be used to monitor faults of the equipment to be diagnosed. The data acquisition module can be used to obtain equipment abnormality data of the equipment to be diagnosed when the monitoring result is abnormal. The fault diagnosis module can be used to determine the fault diagnosis report based on the equipment abnormality data and the equipment failure mode. The fault diagnosis model is the core algorithm, which is responsible for the logical processing of fault diagnosis. The fault knowledge base is used to store equipment information, historical fault cases and maintenance strategies. The fault display interface can be used for fault diagnosis reporting, diagnostic result viewing and fault knowledge base management. The fault diagnosis system in the embodiment of the present invention also includes a communication interface for allowing the fault diagnosis system to exchange data with other systems. Other systems may be SCADA systems (Supervisory Control And Data Acquisition)

[0075] Exemplarily, historical operation data, historical fault cases, and historical maintenance logs of power equipment are collected and pre-processed using a data collection module. Specifically, the operation data of power plant equipment is numerical data, and the data is cleaned, standardized, and formatted to facilitate subsequent fault analysis and processing; the fault record text data (i.e., historical fault cases and historical maintenance logs) is processed, the text is segmented, different text segments are generated, and then vectorized and stored in a vector database.

[0076] Furthermore, a fault knowledge base is constructed and ensured to be dynamically updated. Specifically, a fault knowledge base including equipment information, fault cases and maintenance strategies is constructed using the preprocessed data; the fault knowledge base should support dynamic updates to include the latest fault cases and solutions.

[0077] Furthermore, when the equipment to be diagnosed is monitored and the monitoring result is abnormal, the fault diagnosis process is triggered. The RAG model retrieves relevant information from the fault knowledge base, and generates a fault diagnosis report in combination with the abnormalities in the equipment operation data. Specifically, according to the equipment failure mode of the equipment to be diagnosed, the reference failure mode is determined, and the similarity between the equipment abnormal data and each reference abnormal data under the reference failure mode is determined. The top k similar target failure modes are retrieved from the fault knowledge base and returned; the top k target failure modes, the target abnormal data under the target failure mode, and the fault knowledge template are input into the RAG generation module to obtain the corresponding fault knowledge, failure mode, corresponding fault cause and maintenance strategy, and generate a fault diagnosis report.

[0078] Furthermore, the system analyzes the generated fault diagnosis report and feeds back the diagnosis results and maintenance strategies to the maintenance team. The maintenance personnel troubleshoot the fault according to the strategy and record the final processing results on the interface. The system updates the fault knowledge base based on the feedback.

[0079] The embodiments of the present invention can effectively improve the accuracy and efficiency of fault diagnosis of power plant equipment, while reducing maintenance costs and improving operational safety.

[0080] By introducing RAG technology in the embodiment of the present invention, the following improvements are achieved: Improve retrieval efficiency: Use RAG (Retrieval-Augmented Generation) technology to quickly retrieve relevant fault cases and information, shortening the fault diagnosis time; Dynamically update the fault knowledge base: Through the retrieval enhancement capability of RAG, the fault knowledge base is updated in real time to ensure that the diagnosis results contain the latest fault cases and solutions. Improve diagnostic consistency and accuracy: By integrating the retrieved information, the consistency and accuracy of fault diagnosis are improved. Enhance the recognition of complex fault patterns: Use RAG technology to integrate multi-source data and improve the ability to recognize complex fault patterns. Meet personalized needs: RAG technology can provide personalized and customized fault diagnosis services based on different power plant environments and equipment configurations.

[0081] On the basis of the above technical solution, the embodiment of the present invention takes the failure of the induced draft fan of a power plant as an example for illustration.

[0082] For example, equipment type: induced draft fan of thermal power plant; fault phenomenon: efficiency decline, air volume reduction, abnormal vibration and noise during operation of induced draft fan. Specifically, fault monitoring: the sensor of induced draft fan detects efficiency decline and air volume reduction, and vibration and noise exceed normal range; data collection: the system automatically collects equipment abnormality data of induced draft fan, including air volume, pressure, temperature and vibration frequency, etc.; fault reporting: the operator receives fault alarm and records fault phenomenon. Knowledge base retrieval: After receiving the fault report (i.e., equipment abnormality data and equipment failure mode), the RAG model starts to retrieve historical cases and related information in the fault knowledge base; case matching: The RAG model matches the topk similar historical fault cases (i.e., target fault mode) by comparing the equipment abnormality data and historical data (i.e., reference abnormality data); fault cause analysis: The RAG model analyzes the matched cases to determine the possible causes of the fault, such as blade damage, bearing wear, foreign object blockage, etc.; generate diagnostic report: The RAG model combines the retrieved target fault mode and target abnormal data to generate a detailed fault diagnosis report, including the cause of the fault, recommended checkpoints, and maintenance suggestions; maintenance team response: The maintenance team conducts on-site inspection and maintenance work according to the fault diagnosis report; fault handling: According to the guidance of the fault diagnosis report, the maintenance team may need to replace damaged blades, repair or replace bearings, clean foreign objects, etc.; result verification: After the maintenance work is completed, the induced draft fan is restarted, and the system monitors its operating status to confirm whether the fault has been resolved; knowledge base update: The detailed information and results of this fault handling are recorded in the knowledge base for future fault learning.

[0083] In the embodiments of the present invention, the fault diagnosis method and device based on RAG technology can provide fast and accurate fault diagnosis for key equipment such as induced draft fans in thermal power plants, helping the maintenance team to take timely measures, reduce downtime, and improve power generation efficiency and safety.

[0084] Embodiment 4

[0085] Figure 3 This is a schematic diagram of the structure of a fault diagnosis device for electric equipment provided in Embodiment 4 of the present invention. This embodiment is applicable to the case of performing fault diagnosis on electric equipment, and the method can be performed by a fault diagnosis device for electric equipment, which can be implemented in software and / or hardware, and can be configured in an electronic device that carries the fault diagnosis function of the electric equipment.

[0086] like Figure 3 As shown, the device includes: an equipment abnormality data acquisition module 310, a fault diagnosis report generation module 320 and an equipment maintenance module 330. Among them,

[0087] The device abnormality data acquisition module 310 is used to perform real-time online fault monitoring on the device to be diagnosed, and if the monitoring result is abnormal, obtain the device abnormality data of the device to be diagnosed;

[0088] A fault diagnosis report generating module 320 is used to determine a device fault mode according to the device abnormal data, and input the device abnormal data and the device fault mode into a trained fault diagnosis model, wherein the fault diagnosis model searches for fault-related data in a pre-built fault knowledge base according to the device abnormal data and the device fault mode, and generates and outputs a fault diagnosis report according to the fault-related data;

[0089] The equipment maintenance module 330 is used to perform equipment maintenance on the equipment to be diagnosed according to the fault diagnosis report.

[0090] The embodiment of the present invention provides a fault diagnosis scheme for power equipment, which performs real-time online fault monitoring on the equipment to be diagnosed. If the monitoring result is abnormal, the equipment abnormality data of the equipment to be diagnosed is obtained; the equipment failure mode is determined according to the equipment abnormality data, and the equipment abnormality data and the equipment failure mode are input into a trained fault diagnosis model. The fault diagnosis model searches for fault-related data in a pre-built fault knowledge base according to the equipment abnormality data and the equipment failure mode, and generates and outputs a fault diagnosis report according to the fault-related data; and the equipment to be diagnosed is maintained according to the fault diagnosis report. The above scheme, by introducing a fault diagnosis model and a fault knowledge base, generates a fault diagnosis report through the mutual cooperation of the fault diagnosis model and the fault knowledge base, realizes the automated fault diagnosis of the equipment to be diagnosed, improves the fault diagnosis efficiency, and reduces the labor cost.

[0091] Optionally, the fault diagnosis report generating module 320 includes:

[0092] A reference failure mode determination unit, configured to select a reference failure mode from candidate failure modes in the failure knowledge base according to the device failure mode;

[0093] a target fault mode determination unit, configured to match reference abnormal data in candidate abnormal data under the reference fault mode according to the device abnormal data, determine a target fault mode according to a reference fault mode corresponding to the reference abnormal data, and use the reference abnormal data under the target fault mode as the target abnormal data;

[0094] The fault diagnosis report generating unit is used to determine the fault association data according to the target abnormal data, the target fault mode and the preset fault knowledge template, and to generate and output the fault diagnosis report according to the fault association data.

[0095] Optionally, the target failure mode determination unit includes:

[0096] A similarity determination subunit, configured to determine, for each of the reference abnormal data under the reference fault mode, a similarity between each of the reference abnormal data and the device abnormal data;

[0097] The target fault mode determination subunit is used to sort the reference fault modes according to the similarity between the reference abnormal data and the device abnormal data, and determine the target fault mode corresponding to the device abnormal data based on the sorting result.

[0098] Optionally, the target failure mode determination subunit is specifically used to:

[0099] A target failure mode corresponding to a preset threshold number of device abnormal data is selected from the sorting results.

[0100] Optionally, the device further comprises:

[0101] a target failure mode generating unit, configured to generate a target failure mode based on the input device abnormality data and device failure mode by the fault diagnosis model if the number of the target failure modes is 0;

[0102] A knowledge base updating unit is used to update the fault knowledge base according to the target fault mode.

[0103] Optionally, the fault diagnosis model is a RAG model.

[0104] The fault diagnosis device for electric power equipment provided in the embodiment of the present invention can execute the fault diagnosis method for electric power equipment provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the fault diagnosis method for each electric power equipment.

[0105] In the technical solution of the present invention, the collection, storage, use, processing, transmission, provision and disclosure of the equipment abnormality data and fault knowledge base involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0106] Embodiment 5

[0107] Figure 4It is a structural diagram of an electronic device for implementing a fault diagnosis method for power equipment provided by Embodiment 5 of the present invention. The electronic device 410 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0108] like Figure 4 As shown, the electronic device 410 includes at least one processor 411, and a memory connected to the at least one processor 411 in communication, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 to the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0109] Multiple components in the electronic device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, an optical disk, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0110] The processor 411 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 411 executes the various methods and processes described above, such as a fault diagnosis method for power equipment.

[0111] In some embodiments, the fault diagnosis method of the electric power device may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the fault diagnosis method of the electric power device described above may be performed. Alternatively, in other embodiments, the processor 411 may be configured to execute the fault diagnosis method of the electric power device in any other appropriate manner (e.g., by means of firmware).

[0112] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0114] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0115] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0116] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0117] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0118] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0119] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for diagnosing a fault of an electric power device, characterized in that: include: Performing real-time online fault monitoring on the device to be diagnosed, and if the monitoring result is abnormal, obtaining device abnormality data of the device to be diagnosed; Determine a device failure mode according to the device abnormal data, and input the device abnormal data and the device failure mode into a trained fault diagnosis model, wherein the fault diagnosis model searches for fault-related data in a pre-built fault knowledge base according to the device abnormal data and the device failure mode, and generates and outputs a fault diagnosis report according to the fault-related data; Perform equipment maintenance on the device to be diagnosed according to the fault diagnosis report.

2. The method according to claim 1, characterized in that: The searching for fault-related data in a pre-built fault knowledge base according to the device abnormal data and the device failure mode, and generating and outputting a fault diagnosis report according to the fault-related data, includes: According to the equipment failure mode, selecting a reference failure mode from candidate failure modes in the failure knowledge base; According to the device abnormal data, matching reference abnormal data in the candidate abnormal data under the reference fault mode, determining a target fault mode according to the reference fault mode corresponding to the reference abnormal data, and using the reference abnormal data under the target fault mode as the target abnormal data; According to the target abnormal data, the target fault mode and a preset fault knowledge template, fault-related data is determined, and a fault diagnosis report is generated and output according to the fault-related data.

3. The method according to claim 2, characterized in that The determining of the target failure mode according to the reference failure mode corresponding to the reference abnormal data includes: For each of the reference abnormal data under the reference fault mode, respectively determine the similarity between each of the reference abnormal data and the device abnormal data; The reference fault modes are sorted according to the similarity between the reference abnormal data and the device abnormal data, and based on the sorting result, a target fault mode corresponding to the device abnormal data is determined.

4. The method according to claim 3, characterized in that The determining, based on the sorting result, a target failure mode corresponding to the abnormal data of the device includes: A target failure mode corresponding to a preset threshold number of device abnormal data is selected from the sorting results.

5. The method according to any one of claims 2 to 4, characterized in that: After determining the target fault mode according to the reference fault mode corresponding to the reference abnormal data, the method further includes: If the number of the target failure modes is 0, the fault diagnosis model generates a target failure mode based on the input device abnormality data and device failure mode; The fault knowledge base is updated according to the target fault mode.

6. The method according to any one of claims 1 to 4, characterized in that The fault diagnosis model is a RAG model.

7. A fault diagnosis device for electric power equipment, characterized in that: include: The device abnormality data acquisition module is used to perform real-time online fault monitoring on the device to be diagnosed, and if the monitoring result is abnormal, obtain the device abnormality data of the device to be diagnosed; A fault diagnosis report generation module, used to determine a device failure mode according to the device abnormal data, and input the device abnormal data and the device failure mode into a trained fault diagnosis model, wherein the fault diagnosis model searches for fault-related data in a pre-built fault knowledge base according to the device abnormal data and the device failure mode, and generates and outputs a fault diagnosis report according to the fault-related data; The equipment maintenance module is used to perform equipment maintenance on the equipment to be diagnosed according to the fault diagnosis report.

8. The device according to claim 7, characterized in that The fault diagnosis report generating module comprises: A target device mode selection unit, configured to select a reference fault mode from candidate fault modes in the fault knowledge base according to the device fault mode; a target device data matching unit, configured to match reference abnormal data in candidate abnormal data under the reference fault mode according to the device abnormal data, determine a target fault mode according to a reference fault mode corresponding to the reference abnormal data, and use the reference abnormal data under the target fault mode as the target abnormal data; The fault diagnosis report generating unit is used to determine the fault association data according to the target abnormal data, the target fault mode and the preset fault knowledge template, and to generate and output the fault diagnosis report according to the fault association data.

9. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement a fault diagnosis method for electric power equipment as described in any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a fault diagnosis method for electric power equipment as described in any one of claims 1 to 6 is implemented.