A method and system for fault diagnosis of wind turbine units based on CNN and heatmap
By using a CNN-based and heatmap-based approach, and employing a ResNet50 convolutional neural network model to process and classify wind turbine data, this method solves the problems of high cost and false alarms in traditional wind turbine fault diagnosis, and achieves efficient fault identification and prediction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI UNIVERSITY OF ELECTRIC POWER
- Filing Date
- 2022-09-19
- Publication Date
- 2026-05-26
AI Technical Summary
Traditional wind turbine fault diagnosis technologies are expensive, prone to false alarms, have poor applicability, and lack effective predictive capabilities.
A CNN-based and heatmap-based approach is adopted. Data from wind turbines is acquired through a data acquisition and monitoring system, preprocessed, and converted into heatmaps. A ResNet50 convolutional neural network model is then used for training and testing to identify and classify faults.
It improves the classification accuracy of fault diagnosis, reduces the dimensionality of system parameters, and enhances the accuracy and efficiency of fault prediction.
Smart Images
Figure CN115690482B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of fault diagnosis technology, and in particular to a method and system for fault diagnosis of wind turbine units based on CNN and heatmap. Background Technology
[0002] Population growth, accompanied by rapid urbanization and industrialization, has accelerated the energy crisis. The massive consumption of oil and natural gas severely threatens the ecology and environment. Currently, renewable energy is considered a promising alternative to address the energy crisis and climate change. Wind energy plays a crucial role in power generation and is already regarded as one of the major energy types. Therefore, wind turbine generators have received widespread attention due to their excellent wind energy conversion capabilities. A wind turbine generator consists of hundreds of components and subsystems, including the rotor hub, blades, gearbox, and generator. Operating under complex wind conditions and harsh weather, wind turbine generators are prone to various sensor, actuator, and component failures. Therefore, developing a fault detection system to provide early warnings of impending failures is essential.
[0003] Current research often focuses on instantaneous signal changes, which easily verifies the occurrence of faults. However, considering the operation and maintenance of wind farms, the predictive capability of fault diagnosis systems is particularly important. Generally, before a mechanical failure occurs, certain specific characteristics of the fault spontaneously emerge, affecting the machine's performance. Thus, the collected state parameters of the wind turbine can contain valuable information that can be used to predict failures. Therefore, studying the state parameters before failure is of great significance for predicting failures and analyzing failure mechanisms. Summary of the Invention
[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.
[0005] In view of the aforementioned existing problems, the present invention is proposed.
[0006] Therefore, this invention provides a method and system for wind turbine fault diagnosis based on CNN and heatmap, which can solve the problems of high cost, frequent false alarms, and poor applicability of traditional wind turbine fault diagnosis technology.
[0007] To address the aforementioned technical problems, this invention provides the following technical solution: a wind turbine fault diagnosis method based on CNN and heatmaps, comprising:
[0008] Data is collected from the data acquisition and monitoring system under different operating conditions of the wind turbine, and the data is preprocessed.
[0009] The preprocessed data is converted into a heat map, and then divided into training and test sets.
[0010] Construct a ResNet50 convolutional neural network model, input the training set and the test set into the ResNet50 convolutional neural network model, and determine the optimal ResNet50 convolutional neural network model;
[0011] The system collects operational data from the 24 hours prior to a new fault, preprocesses it, generates a heatmap, and inputs it into the optimal ResNet50 convolutional neural network model to achieve fault identification and classification.
[0012] As a preferred embodiment of the wind turbine fault diagnosis method based on CNN and heatmap described in this invention, the data from the data acquisition and monitoring system under different operating conditions includes normal operation status data and operation data for the 24 hours prior to the fault.
[0013] When performing correlation analysis on normal operating parameters, parameters are selected based on the magnitude of the correlation to reduce the dimensionality of system parameters in the data acquisition and monitoring system.
[0014] After the parameter dimension is reduced, the correlation analysis is performed again on the data of the 24 hours before the failure and the normal operation data based on the reduced state parameters, and then converted into a heat map to divide the training set and the test set.
[0015] As a preferred embodiment of the wind turbine fault diagnosis method based on CNN and heatmap described in this invention, the correlation analysis includes:
[0016]
[0017] Where R represents the Pearson correlation coefficient, x i ={x1,x2,…,x n}, y i ={y1,y2,…,y n}, The Pearson correlation coefficient reflects the degree of correlation between two variables. The value ranges from -1 to 1. A value of 0 indicates that there is no significant linear relationship between the two variables, while -1 and 1 indicate that the two are completely negative or positively correlated. i is the sample value and n is the total sample size.
[0018] As a preferred embodiment of the wind turbine fault diagnosis method based on CNN and heatmap described in this invention, the optimal ResNet50 convolutional neural network model includes,
[0019] The training set is input into the ResNet50 convolutional neural network model for iterative learning and training, and the parameters are optimized until the trained ResNet50 convolutional neural network model converges.
[0020] The test set is input into the trained ResNet50 convolutional neural network model to determine the fault classification, evaluate the diagnostic accuracy, optimize the structure and parameters until the optimal model is reached, and save the optimal ResNet50 convolutional neural network model.
[0021] As a preferred embodiment of the wind turbine fault diagnosis method based on CNN and heatmaps described in this invention, the training set and test set include:
[0022] The first sample set consists of the training set comprising 80% of the total samples and the test set comprising 20% of the total samples.
[0023] The second sample set consists of the training set comprising 60% of the total samples and the test set comprising 40% of the total samples.
[0024] As a preferred embodiment of the wind turbine fault diagnosis method based on CNN and heatmap described in this invention, the optimal ResNet50 convolutional neural network model further includes the following: when the accuracy of the neural network model reaches 85% after being fed into the training set, the ResNet50 convolutional neural network model converges.
[0025] As a preferred embodiment of the wind turbine fault diagnosis method based on CNN and heatmap described in this invention, the optimal ResNet50 convolutional neural network model further includes the following: when the accuracy of the neural network model reaches 95% after being fed into the test set, the ResNet50 convolutional neural network model training reaches its optimal state.
[0026] A wind turbine fault diagnosis system based on CNN and heatmaps, characterized by comprising a data acquisition and processing module, a data conversion and classification module, a model building module, and a testing module.
[0027] The data acquisition and processing module collects data from the data acquisition and monitoring system of the wind turbine under different operating conditions and performs preprocessing on the data.
[0028] The data transformation and classification module converts the preprocessed data into a heat map and divides it into a training set and a test set.
[0029] The model building module constructs a ResNet50 convolutional neural network model, inputs the training set and the test set into the ResNet50 convolutional neural network model, and determines the optimal ResNet50 convolutional neural network model.
[0030] The testing module collects operational data from the 24 hours prior to a new fault, preprocesses it, generates a heatmap, and inputs it into the optimal ResNet50 convolutional neural network model to achieve fault identification and classification.
[0031] A computer device includes a memory and a processor, the memory storing a computer program, characterized in that the processor executes the computer program to implement the steps of the method described above.
[0032] A computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps of the method described above.
[0033] The beneficial effects of this invention: This invention proposes a method and system for fault diagnosis of wind turbine units based on CNN and heat map. This invention obtains data on normal operation and the 24 hours before the fault from the data acquisition and monitoring system, reduces the dimensionality of state parameters by using correlation analysis, and combines multi-layer convolutional neural networks to identify and process heat map, thereby improving the accuracy of fault diagnosis classification. Attached Figure Description
[0034] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:
[0035] Figure 1 A flowchart of a method and system for diagnosing wind turbine faults based on CNN and heatmaps, provided as an embodiment of the present invention;
[0036] Figure 2 A basic flowchart of a wind turbine fault diagnosis method and system based on CNN and heatmap provided in one embodiment of the present invention;
[0037] Figure 3 A schematic diagram of the algorithm model of a wind turbine fault diagnosis method and system based on CNN and heat map provided in one embodiment of the present invention;
[0038] Figure 4This invention provides a method for diagnosing wind turbine faults based on CNN and heatmaps, as well as a parameter correlation heatmap of the system under normal conditions.
[0039] Figure 5 This invention provides a method and system for fault diagnosis of wind turbine units based on CNN and heatmaps, and a heatmap showing the correlation of parameters 24 hours before the fault.
[0040] Figure 6 A bar chart showing the accuracy of generator brush fault diagnosis under different training set ratios for a wind turbine fault diagnosis method and system based on CNN and heatmap, provided as an embodiment of the present invention;
[0041] Figure 7 A bar chart showing the accuracy of pitch system driver fault diagnosis under different training set ratios for different training set proportions in a wind turbine fault diagnosis method and system based on CNN and heatmap, as provided in an embodiment of the present invention.
[0042] Figure 8 A bar chart showing the classification accuracy of two types of faults (generator brush faults and pitch system drive faults) with different training set proportions for wind turbine fault diagnosis method and system based on CNN and heatmap, provided as an embodiment of the present invention;
[0043] Figure 9 An internal structural diagram of a computer device for a wind turbine fault diagnosis method and system based on CNN and heatmap provided in one embodiment of the present invention; Detailed Implementation
[0044] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.
[0045] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.
[0046] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.
[0047] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.
[0048] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.
[0049] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.
[0050] Example 1
[0051] Reference Figure 1-3 This is the first embodiment of the present invention, which provides a wind turbine fault diagnosis method based on CNN and heatmap, including:
[0052] Step 102: Collect data from the data acquisition and monitoring system of the wind turbine under different operating conditions, and preprocess the data;
[0053] This includes collecting data from the data acquisition and monitoring system under different operating conditions, including normal operating status data and operating data for the 24 hours prior to a failure.
[0054] Step 104: Convert the preprocessed data into a heat map and divide it into training and test sets;
[0055] Specifically, correlation analysis is used to reduce the dimensionality of system parameters in the data acquisition and monitoring system during normal operation. Based on the dimensionality-reduced state parameters, correlation analysis is performed again on the data from the 24 hours before the fault and the normal operation data, and the data is converted into a heat map to divide the training set and the test set.
[0056] Step 106: Construct a ResNet50 convolutional neural network model by inputting the training set and the test set into the ResNet50 convolutional neural network model and determining the optimal ResNet50 convolutional neural network model.
[0057] Specifically, a ResNet50 convolutional neural network model is constructed; the training set is input into the ResNet50 convolutional neural network model for iterative learning and training, and the parameters are optimized until the trained ResNet50 convolutional neural network model converges; the test set is input into the trained ResNet50 convolutional neural network model to determine the fault classification, evaluate the diagnostic accuracy, optimize the structure and parameters until the optimal value is achieved, and save the optimal ResNet50 convolutional neural network model.
[0058] Furthermore, the expression for the Pearson correlation coefficient is:
[0059]
[0060] Where R represents the Pearson correlation coefficient, x i ={x1,x2,…,x n}, y i ={y1,y2,…,y n}, The Pearson correlation coefficient reflects the degree of correlation between two variables. The value ranges from -1 to 1. A value of 0 indicates that there is no significant linear relationship between the two variables, while -1 and 1 indicate that the two are completely negative or positively correlated. i is the sample value and n is the total sample size.
[0061] Furthermore, heatmaps are drawn, and fault classification labels are labeled, dividing the data into training and test sets as inputs to the ResNet50 convolutional neural network. The training set consists of 80% of the total samples and the test set consists of 20% of the total samples, while the test set consists of 60% of the total samples and the test set consists of 40% of the total samples.
[0062] It should be noted that, based on the dimension of the fault feature vector, a multi-layer convolutional neural network is designed, namely the ResNet50 convolutional neural network, which includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer.
[0063] Furthermore, the ResNet50 convolutional neural network model is defined as converging when the accuracy reaches 85%.
[0064] Step 108: Collect the operating data of the 24 hours prior to the new fault, perform preprocessing, and generate a heat map. Input the heat map into the optimal ResNet50 convolutional neural network model to achieve fault identification and classification.
[0065] It should be noted that, based on the accuracy of the diagnostic results, the network structure weight and parameters of the ResNet50 convolutional neural network model in step S4 are adjusted, and the model is retrained to further improve its accuracy.
[0066] Specifically, the ResNet50 convolutional neural network model is considered to have reached its optimal training level when the accuracy reaches 90%.
[0067] A wind turbine fault diagnosis system based on CNN and heatmaps, characterized by comprising a data acquisition and processing module, a data conversion and classification module, a model building module, and a testing module.
[0068] The data acquisition and processing module collects data from the data acquisition and monitoring system of the wind turbine under different operating conditions and performs preprocessing on the data.
[0069] The data transformation and classification module converts the preprocessed data into a heat map and divides it into a training set and a test set.
[0070] The model building module constructs a ResNet50 convolutional neural network model, inputs the training set and the test set into the ResNet50 convolutional neural network model, and determines the optimal ResNet50 convolutional neural network model.
[0071] The testing module collects operational data from the 24 hours prior to a new fault, preprocesses it, generates a heatmap, and inputs it into the optimal ResNet50 convolutional neural network model to achieve fault identification and classification.
[0072] The above-mentioned unit modules can be embedded in the processor of the computer device in hardware form or independent of it, or they can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of the above modules.
[0073] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 9As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a wind turbine fault diagnosis method and system based on CNN and heatmaps. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device casing, or an external keyboard, touchpad, or mouse.
[0074] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:
[0075] Data is collected from the data acquisition and monitoring system under different operating conditions of the wind turbine, and the data is preprocessed.
[0076] The preprocessed data is converted into a heat map, and then divided into training and test sets.
[0077] Construct a ResNet50 convolutional neural network model, input the training set and the test set into the ResNet50 convolutional neural network model, and determine the optimal ResNet50 convolutional neural network model;
[0078] The system collects operational data from the 24 hours prior to a new fault, preprocesses it, generates a heatmap, and inputs it into the optimal ResNet50 convolutional neural network model to achieve fault identification and classification.
[0079] Example 2
[0080] Reference Figure 4-9 As an embodiment of the present invention, a method and system for diagnosing wind turbine faults based on CNN and heatmap are provided. To verify the beneficial effects of the present invention, comparative experiments are conducted for scientific demonstration.
[0081] Table 1. Accuracy of Generator Brush Fault Diagnosis
[0082]
[0083] Table 2. Accuracy of pitch system drive fault diagnosis for wind turbine fault diagnosis methods under different training set proportions (with selected parameters and all parameters).
[0084]
[0085]
[0086] Table 3. Classification accuracy of two types of faults (generator brush faults and pitch system drive faults) under different training set proportions for wind turbine fault diagnosis methods with and without parameters.
[0087]
[0088] As can be seen from Tables 1-3, when selecting parameters for the training set, the accuracy may be slightly higher with a 60% training set percentage than with an 80% training set percentage. However, when considering all parameters, the accuracy with an 80% training set percentage is significantly better than that with a 60% training set percentage.
[0089] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.
[0090] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.
[0091] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.
[0092] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0093] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0094] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0095] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.
[0096] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.
Claims
1. A wind turbine unit fault diagnosis method based on CNN and hotspot map, characterized in that: include, Data is collected from the data acquisition and monitoring system under different operating conditions of the wind turbine, and the data is preprocessed. The preprocessed data is converted into a heat map, and then divided into training and test sets. Construct a ResNet50 convolutional neural network model, input the training set and the test set into the ResNet50 convolutional neural network model, and determine the optimal ResNet50 convolutional neural network model; Collect operational data from the 24 hours prior to a new fault, preprocess it, and generate a heatmap. Input the heatmap into the optimal ResNet50 convolutional neural network model to achieve fault identification and classification. The data from the data acquisition and monitoring system under different operating conditions includes normal operating status data and operating data for the 24 hours prior to the fault. When performing correlation analysis on normal operating parameters, parameters are selected based on the magnitude of the correlation to reduce the dimensionality of system parameters in the data acquisition and monitoring system. After the parameter dimension is reduced, the correlation analysis is performed again on the data of the 24 hours before the failure and the normal operation data based on the reduced state parameters, and the data is converted into a heat map to divide the training set and the test set. The optimal ResNet50 convolutional neural network model includes, The training set is input into the ResNet50 convolutional neural network model for iterative learning and training, and the parameters are optimized until the trained ResNet50 convolutional neural network model converges. The test set is input into the trained ResNet50 convolutional neural network model to determine the fault classification, evaluate the diagnostic accuracy, optimize the structure and parameters until the optimal result is achieved, and save the optimal ResNet50 convolutional neural network model. The training set and test set include, The first sample set consists of the training set comprising 80% of the total samples and the test set comprising 20% of the total samples. The second sample set consists of the training set comprising 60% of the total samples and the test set comprising 40% of the total samples. The optimal ResNet50 convolutional neural network model also includes the following: when the accuracy of the neural network model reaches 85% after being fed into the training set, the ResNet50 convolutional neural network model converges. The optimal ResNet50 convolutional neural network model also includes the condition that the neural network model achieves an accuracy of 95% when fed into the test set, indicating that the ResNet50 convolutional neural network model training has reached its optimal state.
2. The CNN and hotspot map based wind turbine fleet fault diagnosis method of claim 1, wherein: The correlation analysis includes, ， where R represents the Pearson correlation coefficient, , , , , reflecting the degree of correlation between the two variables, the Pearson correlation coefficient ranges from -1 to 1, a value of 0 indicates that there is no significant linear relationship between the two variables, -1 and 1 represent complete negative or positive correlation, i is the sample value, and n is the total sample amount.
3. A CNN and hotspot map based wind turbine fleet failure diagnosis system applying the method of any one of claims 1 to 2, characterized in that: It includes a data acquisition and processing module, a data transformation and classification module, a model building module, and a testing module. The data acquisition and processing module collects data from the data acquisition and monitoring system of the wind turbine under different operating conditions and performs preprocessing on the data. The data transformation and classification module converts the preprocessed data into a heat map and divides it into a training set and a test set. The model building module constructs a ResNet50 convolutional neural network model, inputs the training set and the test set into the ResNet50 convolutional neural network model, and determines the optimal ResNet50 convolutional neural network model. The testing module collects operational data from the 24 hours prior to a new fault, preprocesses it, generates a heatmap, and inputs it into the optimal ResNet50 convolutional neural network model to achieve fault identification and classification.
4. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 2.
5. A computer-readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 2.