Fault diagnosis method and device and computer program product

Abstract

The invention discloses a fault diagnosis method and device and a computer program product, and relates to the technical field of fault diagnos.The fault diagnosis method comprises the steps that operation parameters of power generation equipment are monitored, and monitoring data are obtained; performing feature extraction on the monitoring data to obtain frequency domain features and time domain features, and performing fusion processing on the frequency domain features and the time domain features to obtain fusion features; and inputting the fusion features into a fault diagnosis model to obtain a fault type output by the fault diagnosis model. By adopting the technical scheme, the problem of how to improve the fault diagnosis accuracy of the power generation equipment is solved.

Description

Technical Field

[0001] The present application relates to the technical field of fault diagnosis, and in particular to a fault diagnosis method, device and computer program product. Background Art

[0002] Wind turbines often experience various faults during operation due to environmental conditions, structural wear, material fatigue, etc., such as blade damage, gear wear, bearing failure, etc. If these faults cannot be discovered and handled in time, they will seriously affect the power generation efficiency and safety of the wind turbine. At present, wind turbine anomaly detection methods mainly include statistical anomaly detection, distance or proximity-based anomaly detection methods, and prediction-based anomaly detection methods. The statistical anomaly detection method is simple and easy to use, but it is not effective for non-normally distributed data or complex data distribution. And it has high requirements on data quality, and it is necessary to clean and preprocess the data in advance. The distance or proximity-based anomaly detection method can handle high-dimensional data and complex data distribution, but the computational complexity is high and it is sensitive to the selection of parameters. The prediction-based anomaly detection method relies on the accuracy of the prediction model, and the overall accuracy and robustness are easily affected by the data quality and the selection of threshold size.

[0003] Therefore, in the related art, there is a problem of how to improve the accuracy of fault diagnosis of power generation equipment.

[0004] With regard to the problem of how to improve the accuracy of fault diagnosis of power generation equipment in related technologies, no effective solution has been proposed so far.

[0005] Therefore, it is necessary to improve the related technology to overcome the above-mentioned defects in the related technology. Summary of the invention

[0006] The embodiments of the present application provide a fault diagnosis method, apparatus, and computer program product to at least solve the problem in the related art of how to improve the accuracy of fault diagnosis of power generation equipment.

[0007] According to one aspect of an embodiment of the present application, a fault diagnosis method is provided, comprising: monitoring operating parameters of a power generation device to obtain monitoring data; performing feature extraction on the monitoring data to obtain frequency domain features and time domain features, and fusing the frequency domain features and the time domain features to obtain fused features; inputting the fused features into a fault diagnosis model to obtain a fault type output by the fault diagnosis model.

[0008] In an exemplary embodiment, feature extraction is performed on the monitoring data to obtain frequency domain features and time domain features, including: converting the time series of the monitoring data from the time domain to the frequency domain to obtain frequency domain data; adjusting weight values ​​of data of different frequencies in the frequency domain data through an encoder, wherein the encoder is constructed based on an attention mechanism; and feature extraction is performed on the frequency domain data according to the weight values ​​to obtain the frequency domain features.

[0009] In an exemplary embodiment, feature extraction is performed on the monitoring data to obtain frequency domain features and time domain features, including: inputting the monitoring data into multiple causal convolutional networks to obtain multiple feature matrices output by the multiple causal convolutional networks, wherein the multiple causal convolutional networks have different convolution kernel sizes; and average pooling is performed on the multiple feature matrices to obtain the time domain features.

[0010] In an exemplary embodiment, the frequency domain features and the time domain features are fused to obtain fused features, including: performing feature splicing processing on the frequency domain features and the time domain features to obtain spliced ​​features; inputting the spliced ​​features into a feature fusion network, and learning the nonlinear relationship between different features in the spliced ​​features through the feature fusion network to obtain the fused features output by the feature fusion network.

[0011] In an exemplary embodiment, before inputting the fusion feature into the fault diagnosis model to obtain the fault type output by the fault diagnosis model, the method also includes: obtaining historical fault records of the power generation equipment, wherein the historical fault records include the fault type of the historical fault and historical fault data collected when the historical fault occurred; using the historical fault data as a training data set and the historical fault type as a verification data set to train the initial model to obtain the fault diagnosis model.

[0012] In an exemplary embodiment, after obtaining the fault diagnosis model, the method further includes: determining the loss function of the fault diagnosis model based on the accuracy of the fault type output by the fault diagnosis model; adjusting the parameters of the fault diagnosis model according to the loss function to obtain an adjusted fault diagnosis model, wherein the loss function value of the adjusted fault diagnosis model is less than the loss function value of the fault diagnosis model before adjustment.

[0013] According to another aspect of an embodiment of the present application, a fault diagnosis device is also provided, including: a monitoring module, used to monitor the operating parameters of the power generation equipment to obtain monitoring data; a fusion module, used to extract features from the monitoring data to obtain frequency domain features and time domain features, and to fuse the frequency domain features and the time domain features to obtain fused features; a diagnosis module, used to input the fused features into a fault diagnosis model to obtain the fault type output by the fault diagnosis model.

[0014] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned fault diagnosis method when running.

[0015] According to another aspect of the embodiments of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the fault diagnosis method through the computer program.

[0016] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the method described in each embodiment of the present application are implemented.

[0017] Through this application, frequency domain features and time domain features can be extracted from the monitoring data obtained by monitoring the operating parameters of the power generation equipment, and then the frequency domain features and the time domain features are fused to obtain fused features, and the fused features are input into the fault diagnosis model for diagnosis, and then the fault type of the wind turbine is determined according to the model output results. This solves the problem of how to improve the accuracy of fault diagnosis of power generation equipment in the related technology, and achieves the effect of improving the accuracy of fault diagnosis of power generation equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 It is a hardware structure block diagram of a computer terminal of a fault diagnosis method according to an embodiment of the present application;

[0021] Figure 2is a flow chart of a fault diagnosis method according to an embodiment of the present application;

[0022] Figure 3 is a schematic diagram of a fault diagnosis method according to an embodiment of the present application;

[0023] Figure 4 is a schematic diagram of a fault diagnosis method according to an embodiment of the present application;

[0024] Figure 5 is a schematic diagram of a fault diagnosis method according to an embodiment of the present application;

[0025] Figure 6 It is a structural block diagram of a fault diagnosis device according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal or a similar computing device. Taking running on a computer terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a computer terminal of a fault diagnosis method according to an embodiment of the present application. Figure 1 As shown, the computer terminal may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor (Central Processing Unit, MCU) or a programmable logic device (Field Programmable Gate Array, FPGA)) and a memory 104 for storing data, wherein the above-mentioned computer terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0029] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the fault diagnosis method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0030] A wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0031] In this embodiment, a fault diagnosis method is provided. Figure 2 is a flow chart of a fault diagnosis method according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps:

[0032] Step S202, monitoring the operating parameters of the power generation equipment to obtain monitoring data;

[0033] Optionally, in the above step S202, the parameter data of the actual operation of the generator set can be collected through the SCADA (Supervisory Control And Data Acquisition) system to obtain monitoring data. The collected monitoring data also needs to be cleaned to process missing values, abnormal values, duplicate data, etc. to ensure data quality, and then the time series data after cleaning is standardized for subsequent processing.

[0034] Step S204, extracting features from the monitoring data to obtain frequency domain features and time domain features, and fusing the frequency domain features and the time domain features to obtain fused features;

[0035] Step S206: input the fusion feature into a fault diagnosis model to obtain the fault type output by the fault diagnosis model.

[0036] Through the above steps, the frequency domain features and time domain features can be extracted from the monitoring data obtained by monitoring the operating parameters of the power generation equipment, and then the frequency domain features and the time domain features are fused to obtain fused features, and the fused features are input into the fault diagnosis model for diagnosis, and then the fault type of the wind turbine is determined according to the model output results. This solves the problem of how to improve the accuracy of fault diagnosis of power generation equipment in the related technology, and achieves the effect of improving the accuracy of fault diagnosis of power generation equipment.

[0037] In an exemplary embodiment, feature extraction is performed on the monitoring data to obtain frequency domain features and time domain features, including: converting the time series of the monitoring data from the time domain to the frequency domain to obtain frequency domain data; adjusting weight values ​​of data of different frequencies in the frequency domain data through an encoder, wherein the encoder is constructed based on an attention mechanism; and feature extraction is performed on the frequency domain data according to the weight values ​​to obtain the frequency domain features.

[0038] Optionally, in the above embodiment, a fast Fourier transform can be applied to convert the time series of the monitoring data from the time domain to the frequency domain to obtain spectrum data. An encoder model based on the Attention mechanism is constructed to learn key feature information in the frequency domain features. The Attention mechanism can dynamically adjust the weights of different frequency components and enhance the sensitivity of the model to important frequency components. The frequency domain data is converted back to the time domain through an inverse Fourier transform to retain the information of the key frequency components.

[0039] In an alternative embodiment, Figure 3 This is a schematic diagram of the frequency domain attention calculation process, where X represents the input, and the frequency domain Attention mechanism is expressed as follows:

[0040]

[0041] Where F(·) represents Fourier transform, F -1 (·) represents the inverse Fourier transform, represents the conjugate function of F(·), σ(·) represents the softmax activation function, Represents the scaling factor. After feature extraction, the output frequency domain feature is recorded as V (F) .

[0042] In an exemplary embodiment, feature extraction is performed on the monitoring data to obtain frequency domain features and time domain features, including: inputting the monitoring data into multiple causal convolutional networks to obtain multiple feature matrices output by the multiple causal convolutional networks, wherein the multiple causal convolutional networks have different convolution kernel sizes; and average pooling is performed on the multiple feature matrices to obtain the time domain features.

[0043] Optionally, in the above embodiment, multiple causal convolutional networks with different convolution kernel sizes are used as feature extractors. Average pooling is applied to the output of each feature extractor to fuse the features extracted by different convolution kernel sizes, and a comprehensive time domain feature can be obtained. By setting different convolution kernel sizes, it is possible to automatically learn which length of time window is more effective for extracting trend items without pre-defining the time window length, thereby avoiding underfitting or overfitting problems caused by improper time window length setting.

[0044] In an optional embodiment, if Figure 4 As shown, V represents the input, and there are a total of L+1 convolution kernels of different sizes, where h is the length of the lookback window, and the size of the i-th convolution kernel is 2 i For each causal convolution, the feature matrix of the i-th causal convolution output is:

[0045]

[0046] After average pooling, the final time domain features are:

[0047]

[0048] In an exemplary embodiment, the frequency domain features and the time domain features are fused to obtain fused features, including: performing feature splicing processing on the frequency domain features and the time domain features to obtain spliced ​​features; inputting the spliced ​​features into a feature fusion network, and learning the nonlinear relationship between different features in the spliced ​​features through the feature fusion network to obtain the fused features output by the feature fusion network.

[0049] Optionally, in the above embodiment, the feature representations in the frequency domain and the time domain may be spliced ​​to form a unified feature vector (equivalent to the spliced ​​feature), and a fully connected layer may be applied to the spliced ​​feature vector to learn the nonlinear relationship between different features for further fusion to obtain the fused feature.

[0050] Optionally, in the above embodiment, after obtaining the fused features, the reconstruction loss of the fused features can also be calculated, the fused feature vector is mapped back to the original sequence space, and the feature reconstruction loss between the reconstructed sequence and the original observed data is calculated, measured by the mean square error. The calculation formula is:

[0051]

[0052] Among them, L Rec represents feature reconstruction loss, h represents the number of features, x i and v' i represent the original sequence and the reconstructed sequence respectively.

[0053] In an exemplary embodiment, before inputting the fusion feature into the fault diagnosis model to obtain the fault type output by the fault diagnosis model, the method also includes: obtaining historical fault records of the power generation equipment, wherein the historical fault records include the fault type of the historical fault and historical fault data collected when the historical fault occurred; using the historical fault data as a training data set and the historical fault type as a verification data set to train the initial model to obtain the fault diagnosis model.

[0054] Optionally, in the above embodiment, the fault diagnosis model may use a multilayer perceptron (MLP), a support vector machine (SVM), or a deep learning model.

[0055] In an exemplary embodiment, after obtaining the fault diagnosis model, the method further includes: determining the loss function of the fault diagnosis model based on the accuracy of the fault type output by the fault diagnosis model; adjusting the parameters of the fault diagnosis model according to the loss function to obtain an adjusted fault diagnosis model, wherein the loss function value of the adjusted fault diagnosis model is less than the loss function value of the fault diagnosis model before adjustment.

[0056] Optionally, in the above embodiment, a joint loss function including the cross entropy loss of the fault diagnosis output result and the feature reconstruction loss can also be constructed. The model parameters are optimized by the back propagation algorithm to minimize the joint loss. The joint loss function is:

[0057] L=L CE +α·L Rec;

[0058] Among them, L represents the joint loss function, L CE represents the cross entropy loss, L Rec represents the feature reconstruction loss, and α is a hyperparameter used to balance the two losses.

[0059] Obviously, the above-described embodiments are only a part of the embodiments of the present application, not all of the embodiments. In order to better understand the above-mentioned method for determining the power generation area, the above-mentioned process is described below in conjunction with the embodiments, but it is not intended to limit the technical solutions of the embodiments of the present application, specifically:

[0060] In an optional embodiment, in combination Figure 5 The fault diagnosis method of the present application is further described. Figure 5 As shown, the original sequence monitoring data X is first input, and the frequency domain feature extraction and time domain feature extraction are performed through the encoder to obtain the frequency domain feature V (F) And the time domain characteristics V (T) , and then the frequency domain feature V (F) And the time domain characteristics V (T) The feature concatenation is performed and input into the fully connected layer for feature fusion to obtain the fused feature V, and then the fused feature V is input into the classifier (equivalent to the fault diagnosis model) to obtain the output predicted fault result.

[0061] Through the above embodiments, by extracting and fusing frequency domain features and time domain features, a fusion feature containing rich information is constructed, which improves the ability to capture abnormal data in complex time series data. The Attention mechanism is introduced in the frequency domain feature extraction, so that the model can pay attention to important frequency components and improve the sensitivity to abnormal data. By calculating the reconstruction loss and optimizing the fusion strategy, the accuracy and completeness of the features after feature fusion are ensured, and the accuracy and efficiency of the fault diagnosis model are improved, which can better ensure the stable operation of the wind farm and improve the economic benefits.

[0062] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0063] In the present embodiment, a fault diagnosis device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the equipment described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0064] Figure 6 is a structural block diagram of a fault diagnosis device according to an embodiment of the present application, the device comprising:

[0065] A monitoring module 62 is used to monitor the operating parameters of the power generation equipment and obtain monitoring data;

[0066] A fusion module 64 is used to extract features from the monitoring data to obtain frequency domain features and time domain features, and to fuse the frequency domain features and the time domain features to obtain fused features;

[0067] The diagnosis module 66 is used to input the fusion feature into the fault diagnosis model to obtain the fault type output by the fault diagnosis model.

[0068] Through the above device, the frequency domain features and time domain features can be extracted from the monitoring data obtained by monitoring the operating parameters of the power generation equipment, and then the frequency domain features and the time domain features are fused to obtain fused features, and the fused features are input into the fault diagnosis model for diagnosis, and then the fault type of the wind turbine is determined according to the model output result. This solves the problem of how to improve the accuracy of fault diagnosis of power generation equipment in the related technology, and achieves the effect of improving the accuracy of fault diagnosis of power generation equipment.

[0069] In an exemplary embodiment, the above-mentioned fusion module 64 is also used to: convert the time series of the monitoring data from the time domain to the frequency domain to obtain frequency domain data; adjust the weight values ​​of data of different frequencies in the frequency domain data through an encoder, wherein the encoder is constructed based on an attention mechanism; and extract features of the frequency domain data according to the weight values ​​to obtain the frequency domain features.

[0070] In an exemplary embodiment, the fusion module 64 is further used to: input the monitoring data into multiple causal convolutional networks to obtain multiple feature matrices output by the multiple causal convolutional networks, wherein the multiple causal convolutional networks have different convolution kernel sizes; and perform average pooling on the multiple feature matrices to obtain the time domain features.

[0071] In an exemplary embodiment, the fusion module 64 is further used to: perform feature splicing processing on the frequency domain features and the time domain features to obtain spliced ​​features; input the spliced ​​features into a feature fusion network, and learn the nonlinear relationship between different features in the spliced ​​features through the feature fusion network to obtain the fusion features output by the feature fusion network.

[0072] In an exemplary embodiment, the above-mentioned diagnostic module 66 is also used to obtain historical fault records of the power generation equipment, wherein the historical fault records include the fault type of the historical fault and the historical fault data collected when the historical fault occurred; the initial model is trained using the historical fault data as a training data set and the historical fault type as a verification data set to obtain the fault diagnosis model.

[0073] In an exemplary embodiment, the above-mentioned diagnostic module 66 is also used to determine the loss function of the fault diagnosis model based on the accuracy of the fault type output by the fault diagnosis model; adjust the parameters of the fault diagnosis model according to the loss function to obtain an adjusted fault diagnosis model, wherein the loss function value of the adjusted fault diagnosis model is less than the loss function value of the fault diagnosis model before adjustment.

[0074] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0075] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0076] S1, monitor the operating parameters of the power generation equipment to obtain monitoring data;

[0077] S2, extracting features from the monitoring data to obtain frequency domain features and time domain features, and fusing the frequency domain features and the time domain features to obtain fused features;

[0078] S3, inputting the fusion feature into a fault diagnosis model to obtain the fault type output by the fault diagnosis model.

[0079] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0080] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0081] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0082] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0083] S1, monitor the operating parameters of the power generation equipment to obtain monitoring data;

[0084] S2, extracting features from the monitoring data to obtain frequency domain features and time domain features, and fusing the frequency domain features and the time domain features to obtain fused features;

[0085] S3, inputting the fusion feature into a fault diagnosis model to obtain the fault type output by the fault diagnosis model.

[0086] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0087] An embodiment of the present application further provides a computer program product, comprising a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program product, and when the computer program is executed by a processor, the steps of the method described in each embodiment of the present application are implemented.

[0088] Optionally, in this embodiment, the above computer program may be configured to implement the following steps when executed by a processor:

[0089] S1, monitor the operating parameters of the power generation equipment to obtain monitoring data;

[0090] S2, extracting features from the monitoring data to obtain frequency domain features and time domain features, and fusing the frequency domain features and the time domain features to obtain fused features;

[0091] S3, inputting the fusion feature into a fault diagnosis model to obtain the fault type output by the fault diagnosis model.

[0092] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0093] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0094] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A fault diagnosis method, characterized in that: include: Monitor the operating parameters of power generation equipment and obtain monitoring data; Extracting features from the monitoring data to obtain frequency domain features and time domain features, and fusing the frequency domain features and the time domain features to obtain fused features; The fusion feature is input into a fault diagnosis model to obtain the fault type output by the fault diagnosis model.

2. The method according to claim 1, characterized in that Feature extraction is performed on the monitoring data to obtain frequency domain features and time domain features, including: Converting the time series of the monitoring data from the time domain to the frequency domain to obtain frequency domain data; Adjusting weight values ​​of data of different frequencies in the frequency domain data through an encoder, wherein the encoder is constructed based on an attention mechanism; Feature extraction is performed on the frequency domain data according to the weight value to obtain the frequency domain feature.

3. The method according to claim 1, characterized in that Feature extraction is performed on the monitoring data to obtain frequency domain features and time domain features, including: Inputting the monitoring data into a plurality of causal convolutional networks to obtain a plurality of feature matrices output by the plurality of causal convolutional networks, wherein the plurality of causal convolutional networks have different convolution kernel sizes; Average pooling is performed on the multiple feature matrices to obtain the time domain features.

4. The method according to claim 1, characterized in that: The frequency domain feature and the time domain feature are fused to obtain a fused feature, including: Performing feature splicing processing on the frequency domain feature and the time domain feature to obtain a splicing feature; The spliced ​​features are input into a feature fusion network, and the nonlinear relationship between different features in the spliced ​​features is learned through the feature fusion network to obtain the fusion features output by the feature fusion network.

5. The method according to claim 1, characterized in that Before inputting the fusion feature into a fault diagnosis model to obtain the fault type output by the fault diagnosis model, the method further includes: Acquire a historical fault record of the power generation equipment, wherein the historical fault record includes a fault type of the historical fault and historical fault data collected when the historical fault occurs; The historical fault data is used as a training data set, and the historical fault types are used as a verification data set to train the initial model to obtain the fault diagnosis model.

6. The method according to claim 5, characterized in that After obtaining the fault diagnosis model, the method further includes: Determining a loss function of the fault diagnosis model according to the accuracy of the fault type output by the fault diagnosis model; The parameters of the fault diagnosis model are adjusted according to the loss function to obtain an adjusted fault diagnosis model, wherein the loss function value of the adjusted fault diagnosis model is less than the loss function value of the fault diagnosis model before the adjustment.

7. A fault diagnosis device, characterized in that: include: A monitoring module is used to monitor the operating parameters of the power generation equipment and obtain monitoring data; A fusion module is used to extract features from the monitoring data to obtain frequency domain features and time domain features, and to fuse the frequency domain features and the time domain features to obtain fusion features; The diagnosis module is used to input the fusion feature into the fault diagnosis model to obtain the fault type output by the fault diagnosis model.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 6 when executed.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 6 through the computer program.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images