Power transformation equipment fault intelligent diagnosis expert system and analysis method

Abstract

The invention discloses a power transformation equipment fault intelligent diagnosis expert system and an analysis method. The system integrates four core modules including a multi-source data acquisition module, a data preprocessing module, an intelligent diagnosis module and a decision support module. The multi-source data acquisition module is responsible for comprehensively collecting operation parameters of power transformation equipment; the data preprocessing module performs cleaning and noise reduction processing on the original data, extracts key features and generates feature data; the intelligent diagnosis module performs deep analysis on the feature data by using a hybrid model of a convolutional neural network and a long-short term memory network, performs logical reasoning in combination with expert knowledge, and accurately outputs fault information; and finally, a decision support module automatically generates a maintenance suggestion, a shutdown plan and a risk assessment report according to an intelligent diagnosis result, and provides a scientific and reasonable decision basis for operation and maintenance personnel. According to the system, efficient diagnosis and scientific management of power transformation equipment faults are realized through an intelligent means, and the safety and the stability of power grid operation are effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of operation monitoring and fault diagnosis of power equipment, and relates to an intelligent fault diagnosis expert system and analysis method for substation equipment. Background Art

[0002] As a core component of the power system, substation equipment undertakes the key tasks of power transmission and distribution. The stability and reliability of its operating state are crucial for ensuring the safe operation of the entire power system. However, during the operation of substation equipment, due to long-term high load and complex working conditions, its mechanical, electrical, and thermal characteristics are easily interfered by various external factors, thus causing various faults. If these faults are not detected and handled in a timely manner, they will not only lead to equipment shutdown and increased maintenance costs, but also pose a serious threat to the overall stability and safety of the power system.

[0003] At present, certain progress has been made in the operation state monitoring and fault diagnosis technology of substation equipment, but there are still many challenges. Traditional fault diagnosis methods mainly rely on manual diagnosis. Although this method can, to a certain extent, judge equipment faults based on the experience and knowledge of professionals, it has great subjectivity and limitations, and it is difficult to ensure the accuracy and consistency of the diagnosis results.

[0004] With the development of information technology, logic reasoning technology based on a rule base has gradually been applied to the fault diagnosis of substation equipment. This method analyzes the equipment operation data through preset rule relationships, and can improve the accuracy and efficiency of diagnosis to a certain extent. However, due to the complex and changeable fault types of substation equipment, and the uncertainty of actual working conditions, the method based on a rule base is often difficult to handle these complex situations in practical applications, resulting in the accuracy of the diagnosis results being affected.

[0005] In recent years, intelligent fault diagnosis technologies have gradually emerged, such as neural network models, support vector machines, etc. These technologies analyze and model equipment operation data through machine learning methods, and can improve the efficiency and accuracy of diagnosis to a certain extent. However, these intelligent fault diagnosis technologies still have some deficiencies. For example, they can often only process single-modal data, and have weak multi-modal data fusion capabilities; at the same time, they have insufficient processing capabilities for unstructured data (such as text records, video monitoring, etc.), and it is difficult to make full use of the useful information in these data; in addition, these technologies have a lag in identifying new faults and are difficult to respond to new fault types in a timely manner.

[0006] In summary, the existing fault diagnosis technologies for substation equipment are still unable to comprehensively and efficiently integrate multi-source data and accurately identify potential equipment faults in real time. Under complex working conditions, the existing methods have insufficient collaborative analysis capabilities for multi-modal data and limitations in processing unstructured data. At the same time, traditional diagnosis methods lack the ability of dynamic optimization and cannot adapt to changes in equipment status in a timely manner. Summary of the Invention

[0007] The purpose of the present invention is to solve the technical problems of insufficient collaborative analysis capabilities for multi-modal data and limitations in processing unstructured data in the existing technology, and to provide an intelligent fault diagnosis expert system and analysis method for substation equipment.

[0008] To achieve the above object, the present invention adopts the following technical solutions: The first aspect of the present invention provides an intelligent fault diagnosis expert system for substation equipment, including: A multi-source data acquisition module for collecting operation parameters of substation equipment; A data preprocessing module for performing data cleaning, noise reduction processing, and feature extraction on the operation parameters to generate feature data; An intelligent diagnosis module for performing fault mode analysis on the feature data based on a hybrid model of a convolutional neural network and a long short-term memory network, and performing logical reasoning in combination with expert knowledge to output fault information; A decision support module for generating maintenance suggestions, outage plans, and risk assessment reports according to the fault information output by the intelligent diagnosis module.

[0009] Further, the operation data of the substation equipment includes voltage, current, temperature, vibration, noise, and gas composition.

[0010] Further, it further includes an expert knowledge base module, which includes a rule base and a case base. The rule base is used to store logical reasoning rules for common faults, and the case base is used to store historical fault data and their processing solutions; the expert knowledge base module provides expert knowledge for the intelligent diagnosis module.

[0011] Further, it further includes a human-computer interaction module, which is used to visualize the equipment operation status, fault types, maintenance suggestions, outage plans, and risk assessment reports.

[0012] Further, the fault information includes the fault type and the location where the fault occurs.

[0013] The second aspect of the present invention provides an intelligent fault diagnosis expert analysis method for substation equipment, including the following steps: Obtain equipment operation data through a multi-source data acquisition module, and perform data cleaning, noise reduction, and feature extraction on the data; Input the said features into the intelligent diagnosis module, and use the deep learning model to combine the rule base and case base of the expert knowledge base module to generate the diagnosis results of the fault type and location; Generate a risk assessment report, an outage plan, and maintenance suggestions according to the diagnosis results.

[0014] Furthermore, the device operation data obtained by the multi-source data acquisition module adopts a voltage transformer, a current transformer, a vibration acceleration sensor, an infrared temperature sensor, and a gas detection sensor.

[0015] Furthermore, the deep learning model is a hybrid model of a convolutional neural network and a long short-term memory network.

[0016] The third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned intelligent diagnosis expert analysis method for substation equipment faults is implemented.

[0017] The fourth aspect of the present invention provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned intelligent diagnosis expert analysis method for substation equipment faults is implemented.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses an intelligent diagnostic expert system for substation equipment failures. The multi-source data acquisition module can collect various operation parameters of substation equipment in real time and comprehensively, including but not limited to key indicators such as current, voltage, temperature, vibration, etc., providing a rich and accurate data basis for subsequent fault analysis; the data preprocessing module effectively eliminates invalid information and noise interference by cleaning and denoising the original data, improving the data quality. At the same time, the feature extraction step can accurately identify the feature variables closely related to the faults, laying a solid foundation for subsequent intelligent diagnosis; the intelligent diagnosis module adopts a hybrid model of convolutional neural network (CNN) and long short-term memory network (LSTM), combining the advantages of CNN in feature extraction and spatial structure recognition and the strengths of LSTM in time series data processing to achieve efficient and accurate fault mode analysis of the feature data. In addition, logical reasoning is combined with the expert knowledge base to further enhance the reliability and practicality of the diagnostic results. The decision support module automatically generates maintenance suggestions, outage plans and risk assessment reports according to the fault information output by the intelligent diagnosis module, providing a scientific and reasonable decision-making basis for maintenance personnel. This not only helps to detect and handle potential faults in a timely manner, but also effectively optimizes the allocation of maintenance resources, reduces the operation and maintenance costs, and improves the safety and stability of the power grid operation. The entire system greatly reduces the work burden of maintenance personnel and improves work efficiency through an automated and intelligent way. At the same time, the intelligent diagnosis and decision support functions make the management of substation equipment failures more refined and intelligent, providing a strong guarantee for the safe and reliable operation of the power system.

[0019] Furthermore, the introduction of the expert knowledge base module provides rich expert knowledge support for the intelligent diagnosis module. The common fault logical reasoning rules stored in the rule base enable the system to perform rapid and accurate fault location and preliminary diagnosis based on these rules. This not only improves the diagnostic efficiency but also ensures the accuracy and reliability of the diagnostic results. The case base, as an important part of the expert knowledge base, stores a large amount of historical fault data and their handling solutions. These cases provide valuable reference for the intelligent diagnosis module, enabling the system to refer to the handling methods of historical similar cases when facing new faults, so as to formulate solutions more quickly and accurately. By continuously learning and updating the rules and cases in the expert knowledge base, the system can gradually accumulate more fault handling experience and improve its self-adaptive ability and intelligent level; the expert knowledge base module provides more comprehensive and in-depth expert knowledge support for the decision support module. This enables the decision support module to more accurately consider factors such as fault type, severity and historical handling experience when generating maintenance suggestions, outage plans and risk assessment reports, so as to formulate a more scientific and reasonable decision-making plan.

[0020] Furthermore, the present invention provides an intelligent diagnostic expert analysis method for substation equipment failures. First, a multi-source data acquisition module widely collects the operation data of substation equipment, covering various key parameters such as current, voltage, temperature, and vibration, ensuring the comprehensiveness and diversity of the data. Subsequently, the collected data is cleaned and noise-reduced, effectively eliminating noise and outliers, and improving the accuracy and reliability of the data. The feature extraction step further refines the key features closely related to the failures, providing a precise data basis for subsequent intelligent diagnosis. The preprocessed feature data is input into the intelligent diagnosis module, which utilizes the powerful analysis capabilities of a deep learning model (such as a hybrid model of convolutional neural network and long short-term memory network), combined with the rule base and case base in the expert knowledge base module, to achieve an accurate diagnosis of the failure type and location. The application of the deep learning model enables the diagnostic process to automatically learn and extract failure features, improving the accuracy and comprehensiveness of the diagnosis. At the same time, the integration of expert knowledge enhances the reliability and practicality of the diagnostic results, making the diagnostic results more in line with the actual operation and maintenance requirements. According to the diagnostic results output by the intelligent diagnosis module, the method automatically generates a risk assessment report, an outage plan, and maintenance suggestions. The risk assessment report details the possible risks and impacts brought by the failures, providing a clear risk awareness for the operation and maintenance personnel. The outage plan reasonably arranges the outage time and scope of the equipment according to the failure type and severity, ensuring the safety and stability of the power grid operation. The maintenance suggestions, based on the failure handling experience and expert knowledge, propose specific repair measures and maintenance suggestions, which help to extend the service life of the equipment and reduce the operation and maintenance costs. This method realizes the real-time monitoring and efficient diagnosis of the operation status of substation equipment through an automated and intelligent manner, greatly reducing the workload of the operation and maintenance personnel and improving the work efficiency. At the same time, the intelligent decision support function enables the operation and maintenance personnel to formulate operation and maintenance strategies more scientifically and reasonably, enhancing the intelligent level of operation and maintenance management. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a module schematic diagram of an intelligent diagnostic expert system for substation equipment failures in Embodiment 1 of the present invention; Figure 2 It is a flowchart of an analysis method for intelligent diagnosis of substation equipment failures in Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Components of the embodiments of the present invention described and marked in the accompanying drawings here can be arranged and designed in various different configurations.

[0024] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0025] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0026] The present invention will be further described in detail below in conjunction with the accompanying drawings: Embodiment 1 An embodiment of the present invention provides an intelligent diagnostic expert system for substation equipment failures, including: A multi-source data acquisition module for collecting operating parameters of substation equipment; the parameters of substation equipment include but are not limited to key indicators such as current, voltage, temperature, vibration, noise, and gas composition.

[0027] A data preprocessing module that performs data cleaning, noise reduction processing, and feature extraction on the operating parameters to generate feature data; the data cleaning step aims to eliminate invalid data, outliers, and duplicate data to ensure the accuracy and consistency of the data. The noise reduction processing reduces noise interference in the data through a filtering algorithm to improve the data quality. The feature extraction step extracts key features closely related to failures from the original data to provide an accurate data basis for subsequent intelligent diagnosis.

[0028] An intelligent diagnosis module that analyzes the failure modes of the feature data based on a hybrid model of a convolutional neural network and a long short-term memory network, and performs logical reasoning in combination with expert knowledge to output failure information; the CNN model is good at capturing the spatial structure and local features of data, while the LSTM model can handle long-term dependencies in time series data. By combining the advantages of these two models, the intelligent diagnosis module can comprehensively and accurately analyze the feature data and output the failure type and location information. In addition, the module also combines the logical reasoning rules in the expert knowledge base to further enhance the reliability and practicality of the diagnosis results.

[0029] The decision support module generates maintenance suggestions, outage plans, and risk assessment reports based on the fault information output by the intelligent diagnosis module. The maintenance suggestion module puts forward specific maintenance measures and maintenance suggestions according to the fault type and severity. The outage plan module reasonably arranges the outage time and scope of the equipment according to the impact degree of the fault on the power grid operation. The risk assessment report details the possible risks and impacts brought by the fault, providing clear risk awareness for the operation and maintenance personnel. These decision support information helps the operation and maintenance personnel quickly and accurately formulate response strategies to ensure the safe and stable operation of the power grid.

[0030] Embodiment 2 Embodiment 2 provides an intelligent diagnosis expert system for substation equipment failures. Refer to Figure 1 , which includes the following modules: a multi-source data acquisition module, a data preprocessing module, an intelligent diagnosis module, an expert knowledge base module, a decision support module, and a human-computer interaction module. The multi-source data acquisition module collects the operation status data of substation equipment in real time and transmits it to the data preprocessing module for processing; the feature data generated by the data preprocessing module is input into the intelligent diagnosis module for analysis; the intelligent diagnosis module combines the expert knowledge base module for logical reasoning and outputs the diagnosis result; the decision support module generates a recommended solution according to the diagnosis result and presents it in a visual manner through the human-computer interaction module.

[0031] Specifically, the multi-source data acquisition module: This module is responsible for collecting the operation parameters of substation equipment, including voltage, current, temperature, vibration, noise, and gas composition. The following equipment is used for collection: Voltage transformers and current transformers: used to collect the voltage and current data of the equipment, supporting high-precision sampling.

[0032] Vibration acceleration sensors: monitor the vibration signals of the mechanical components of the equipment.

[0033] Infrared temperature sensors: record the surface temperature of the equipment in real time and detect potential hot spots.

[0034] Gas detection sensors: analyze the gas composition inside the substation equipment to assist in judging internal faults.

[0035] This module supports the text record collection function. It extracts the key fault information in the text records of the operation and maintenance personnel through natural language processing technology (NLP) and converts it into structured data to supplement the equipment operation parameters.

[0036] Data preprocessing module: This module processes the collected raw data as follows: Data cleaning: Using statistical analysis methods to eliminate outliers generated during the collection process.

[0037] Data denoising: Wavelet transform technology is used to denoise vibration and temperature signals to enhance the signal quality.

[0038] Feature extraction: The time-domain signal is transformed into a frequency-domain signal through the Fast Fourier Transform (FFT) to extract the main frequency features.

[0039] The formula is as follows:

[0040] Where, is the frequency-domain signal, is the time-domain signal, is the frequency.

[0041] Intelligent diagnosis module: This module is based on a hybrid model of Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM). CNN is responsible for extracting the spatial features of the device operation data, and LSTM is used to capture the time series features of the data.

[0042] The formula is as follows:

[0043] Where, is the hidden layer state, and are the weight matrices respectively, is the bias, is the activation function.

[0044] This module combines the rule base and case base of the expert knowledge base module for comprehensive logical reasoning and outputs the fault diagnosis results.

[0045] Expert knowledge base module, including: Rule base: Stores the logical reasoning rules for common faults of substation equipment, such as the corresponding relationship between faults and causes.

[0046] Case base: Records historical fault data and their processing solutions to provide data support for reasoning.

[0047] Decision support module: According to the fault information output by the intelligent diagnosis module, this module generates maintenance suggestions, including outage time, spare part requirements, and maintenance steps, etc. At the same time, it provides a risk assessment report to quantify the potential impact of the fault.

[0048] Human-computer interaction module: Displays the real-time operation status and diagnosis results of the device through a visual interface, generates a trend analysis chart, and intuitively presents the data changes.

[0049] The multi-source data acquisition module transfers the data to the data preprocessing module; the preprocessed data is sent to the intelligent diagnosis module for analysis, and the diagnosis results are generated through the decision support module to generate suggestions, and finally displayed through the human-computer interaction module. The intelligent diagnosis module calls the expert knowledge base module during the analysis process and realizes logical reasoning through rules and cases.

[0050] The workflow of the intelligent diagnosis expert system for substation equipment faults in this embodiment is as follows: Step 1. The multi-source data acquisition module obtains the operation data of the substation equipment in real time.

[0051] Step 2. The data preprocessing module cleans, reduces noise and extracts features from the raw data to generate feature data suitable for analysis.

[0052] Step 3. The intelligent diagnosis module combines the deep learning model and expert knowledge base to analyze the feature data and output the diagnosis results.

[0053] Step 4. The decision support module generates maintenance recommendations, risk assessment reports and optimization plans.

[0054] Step 5. The human-computer interaction module displays the results through a graphical interface for operation and maintenance personnel to view and use.

[0055] This system uses statistical analysis methods to remove outliers and uses wavelet transform technology to reduce noise on signals, which significantly improves data quality and provides a reliable basis for subsequent analysis; it converts time domain signals into frequency domain signals through fast Fourier transform, effectively extracts the main frequency features, and provides key information for fault diagnosis; it combines the hybrid model of convolutional neural network and long short-term memory network, which can not only extract the spatial features of equipment operation data, but also capture the time series features of data, significantly improving the accuracy and efficiency of fault diagnosis; it combines the rule library and case library of the expert knowledge base module to achieve comprehensive logical reasoning, further improving the accuracy and reliability of fault diagnosis; the present invention can accurately locate the fault type and location of substation equipment, significantly improving the efficiency of fault diagnosis. Through the collaborative work of the intelligent diagnosis module and the expert knowledge base module, multiple types of faults under complex working conditions can be quickly diagnosed, and the diagnostic accuracy rate reaches more than 95%.

[0056] Example 3 Example 3 provides a method for intelligent diagnosis and expert analysis of substation equipment faults. Figure 2 , the steps are as follows: Step 1. Data collection and processing Obtain the real-time operation data of substation equipment through the multi-source data acquisition module, including key parameters such as voltage, current, temperature, vibration, etc., and record the text description information of the operation and maintenance personnel. Subsequently, use the data preprocessing module to clean, denoise, and extract features from these data.

[0057] The formula is as follows:

[0058] Wherein, is the original signal, is the signal amplitude, is the signal angular frequency, is the initial phase, is the noise.

[0059] Step 2. Feature fusion and diagnostic analysis Input the extracted features into the intelligent diagnosis module, identify the fault mode through the deep learning model, and perform logical reasoning by combining the rule base and case base of the expert knowledge base module to generate the diagnostic results of the fault type and location.

[0060] The formula is as follows:

[0061] Wherein, is the posterior probability of a specific fault mode of, is the conditional probability of the feature data, is the prior probability.

[0062] Step 3. Decision generation According to the diagnostic results, combine the historical records of equipment operation and expert knowledge to generate a decision-making plan including a risk assessment report, an outage plan, and maintenance suggestions.

[0063] Step 4. Human-computer interaction and result visualization Through the human-computer interaction module, display the diagnostic results to the operation and maintenance personnel intuitively in the form of trend charts, schematic diagrams of fault locations, etc.

[0064] This method can achieve the deep integration and efficient analysis of multi-source data through the coordination of feature fusion and logical reasoning, improving the accuracy and reliability of fault diagnosis under complex working conditions. By implementing this method, the average diagnostic time of equipment faults can be reduced by more than 40%, and the misdiagnosis rate can be effectively reduced.

[0065] Example 4 This embodiment shows that during the high-load operation of the main transformer in a certain substation, the operation and maintenance personnel found that its vibration and temperature increased abnormally. The system analyzes the fault through the present invention: the multi-source data acquisition module of the system records the real-time current, voltage, vibration signal, and the temperature of the equipment shell. The specific manifestations are as follows: The current amplitude fluctuates periodically under the operating conditions, exceeding 10% of the normal value; The peak value of the vibration acceleration increases, and the frequency spectrum of the vibration signal shows that the main component frequency shifts; The temperature of the shell recorded by the infrared sensor exceeds 85 degrees Celsius.

[0066] The data preprocessing module cleans and denoises the collected signals and extracts features: The feature data is input into the intelligent diagnosis module. The diagnosis result shows that there may be a local overheating problem in the core of the main transformer, accompanied by early fault signs of mechanical looseness. Through the comparison with similar situations in the case library, the cause of the fault is further confirmed.

[0067] The decision support module generates the following suggestions: Immediately reduce the load of the main transformer to 75% of the rated capacity; Arrange for the disassembly and inspection of the core components in the short term; Check the mechanical fixing structure to confirm whether component replacement is required.

[0068] Through the human-computer interaction module, the operation and maintenance personnel can intuitively view the fault location and trend analysis diagram on the interface, ensuring that the maintenance work is well-founded. This diagnosis and decision minimize potential losses and avoid the full shutdown of the equipment.

[0069] In another embodiment of the present invention, an electronic device is provided. The electronic device includes a processor and a memory. The memory is used to store a computer program, and the computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function. The processor described in the embodiment of the present invention can be used for the operation of the intelligent diagnosis expert analysis method for substation equipment failures.

[0070] In another embodiment of the present invention, a storage medium is also provided, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is the memory device in the terminal device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and, of course, the extended storage medium supported by the terminal device. It can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or component. The computer-readable storage medium provides a storage space, and this storage space stores the operating system of the terminal. And, one or more instructions suitable for being loaded and executed by the processor are also stored in this storage space. These instructions can be one or more computer programs (including program codes). It should be noted that more specific examples (non-exhaustive list) of the computer-readable storage medium here include: electrical connections with one or more wires, portable disks, hard disks, Random Access Memories (RAMs), Read Only Memories (ROMs), Erasable Programmable Read Only Memories (EPROMs or flash memories), optical fibers, portable Compact Disc Read Only Memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0071] The computer-readable storage medium also includes a data signal propagated in a baseband or as part of a carrier wave, which carries the readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable storage medium can also be any readable medium other than the readable storage medium, and the readable medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0072] The program code for performing the operations of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., by using an Internet service provider to connect through the Internet).

[0073] One or more instructions stored in the computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the intelligent diagnosis expert analysis method for substation equipment faults in the above embodiments.

[0074] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent diagnosis expert system for substation equipment faults, characterized in that: include: Multi-source data acquisition module, used to collect operating parameters of substation equipment; A data preprocessing module performs data cleaning, noise reduction and feature extraction on the operating parameters to generate feature data; An intelligent diagnosis module, based on a hybrid model of a convolutional neural network and a long short-term memory network, performs fault mode analysis on the characteristic data, performs logical reasoning in combination with expert knowledge, and outputs fault information; The decision support module generates maintenance suggestions, outage plans and risk assessment reports based on the fault information output by the intelligent diagnosis module.

2. The intelligent diagnosis expert system for substation equipment faults according to claim 1 is characterized in that: The substation equipment operation data includes voltage, current, temperature, vibration, noise and gas composition.

3. The intelligent diagnosis expert system for substation equipment faults according to claim 1 is characterized in that: It also includes an expert knowledge base module, which includes a rule base and a case base. The rule base is used to store logical reasoning rules for common faults, and the case base is used to store historical fault data and its processing solutions; the expert knowledge base module provides expert knowledge for the intelligent diagnosis module.

4. The intelligent diagnosis expert system for substation equipment faults according to claim 1 is characterized in that: It also includes a human-computer interaction module, which is used to visualize the equipment operating status, new fault types, maintenance suggestions, outage plans and risk assessment reports.

5. The intelligent diagnosis expert system for substation equipment faults according to claim 1 is characterized in that: The fault information includes the fault type and the location where the fault occurs.

6. A method for intelligent diagnosis expert analysis of substation equipment faults, based on the intelligent diagnosis expert system for substation equipment faults according to claim 1, characterized in that: The following steps are involved: Acquire equipment operation data through a multi-source data acquisition module, and perform cleaning, noise reduction and feature extraction on the data; The features are input into the intelligent diagnosis module, and the diagnosis results of the fault type and location are generated by combining the deep learning model with the rule base and case base of the expert knowledge base module; Generate risk assessment reports, outage plans and maintenance recommendations based on the diagnostic results.

7. The intelligent diagnosis expert analysis method for substation equipment faults according to claim 6 is characterized in that: The multi-source data acquisition module is used to acquire the equipment operation data using a voltage transformer, a current transformer, a vibration acceleration sensor, an infrared temperature sensor and a gas detection sensor.

8. The intelligent diagnosis expert analysis method for substation equipment faults according to claim 6 is characterized in that: The deep learning model is a hybrid model of convolutional neural network and long short-term memory network.

9. An electronic device, characterized in that: It comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the expert analysis method for intelligent diagnosis of substation faults as claimed in any one of claims 6 to 8 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for intelligent diagnosis and expert analysis of substation faults according to any one of claims 6 to 8 is implemented.

Images