Fault diagnosis method, system and equipment suitable for digital converter station and medium

Abstract

The invention provides a fault diagnosis method and system suitable for a digital converter station, equipment and a medium. The method comprises the following steps: acquiring equipment operation data in the digital converter station; based on the equipment operation data, utilizing an FP-Growth algorithm to obtain associated data information corresponding to the equipment operation data; based on the associated data information, using a pre-trained fault diagnosis model to output a fault type; wherein the fault diagnosis model is trained on the basis of a Softmax classifier; the FP-Growth algorithm is used to calculate the relevance between the equipment operation data, and the fault type is finally obtained through the pre-established fault diagnosis model based on the Softmax classifier. According to the method, the fault type can be quickly and accurately judged, the operation and maintenance level of the digital converter station is improved, and reliable guarantee is provided for safe and stable operation of a converter station system.

Description

Technical Field

[0001] The present invention belongs to the technical field of digital converter stations, and particularly relates to a fault diagnosis method, system, device and medium applicable to digital converter stations. Background Art

[0002] At present, UHV converter stations are important components in the power transmission and transformation process. With the large-scale operation of the UHV all-region DC power grid, the complexity of digital converter station equipment has been continuously increasing, generating a large amount of heterogeneous and polymorphic operation data during operation, which brings great difficulties to the daily operation and maintenance of the power grid. The traditional fault diagnosis method for digital converter station equipment is through regular inspections, routine maintenance, and post-fault repairs. However, with the continuous increase of monitoring data, it is difficult to accurately and comprehensively detect faults, which may lead to the expansion of the fault range of digital converter stations.

[0003] In the prior art, the main methods for fault diagnosis of power equipment generally adopt fault diagnosis methods based on mathematical models and data-driven fault diagnosis methods. The fault diagnosis method based on a mathematical model establishes a model for the information of the equipment to be diagnosed and uses corresponding mathematical methods for judgment. Due to the complexity of modeling and existing errors, the accuracy rate of this method is relatively low, and the method for diagnosing equipment faults is single. Generally, a threshold comparison method with a single parameter is used for diagnosis, and the correlation between different parameters of the equipment is not considered during the diagnosis process, which easily leads to inaccurate fault diagnosis results for power equipment. Summary of the Invention

[0004] In order to solve the problem in the prior art that the correlation between different parameters of the equipment is not considered during the fault diagnosis of the converter station, resulting in inaccurate fault diagnosis results for power equipment, the present invention proposes a fault diagnosis method applicable to digital converter stations, including:

[0005] Obtain the equipment operation data in the digital converter station;

[0006] Based on the equipment operation data, use the FP-Growth algorithm to obtain the associated data information corresponding to the equipment operation data;

[0007] Based on the associated data information, use a pre-trained fault diagnosis model to output the fault type;

[0008] Wherein, the fault diagnosis model is trained based on a Softmax classifier.

[0009] Optionally, the step of using a pre-trained fault diagnosis model to output the fault type based on the associated data information includes:

[0010] Perform data preprocessing on the associated data information to obtain the state operation data;

[0011] Use the principal component analysis method to reduce the dimension of the state operation data to obtain the dimension-reduced operation data;

[0012] Use the pre-constructed fault diagnosis model to perform fault diagnosis on the dimension-reduced operation data and output the fault type.

[0013] Optionally, the fault diagnosis model includes the following training process:

[0014] Select a preset group from the historical equipment operation data as the input of the training data;

[0015] Use the fault type corresponding to the selected equipment operation data as the output of the training data;

[0016] Based on the input and output of the training data, train the preset Softmax classifier to obtain the fault diagnosis model.

[0017] Optionally, the using the principal component analysis method to reduce the dimension of the state operation data to obtain the dimension-reduced operation data includes:

[0018] Perform centering processing on the state operation data to obtain the corresponding sample distribution data;

[0019] Based on the sample distribution data, obtain the corresponding covariance matrix;

[0020] According to the covariance matrix, obtain the eigenvalues and eigenvectors corresponding to the covariance matrix;

[0021] Reverse-order the eigenvectors according to the corresponding eigenvalues, select a specified number of eigenvectors in the arrangement to form the principal component matrix, and use the principal component matrix as the dimension-reduced operation data.

[0022] Optionally, the expression corresponding to the centering processing is as follows:

[0023]

[0024] where data j represents the value of the j-th state operation data; j = 1…n; n represents the total number of data; data i represents the value of the i-th state operation data; data i′ represents the value of the i-th sample distribution data.

[0025] Optionally, the equipment operation data includes one or more of the following: equipment number, operation time, environmental acquisition data, and process quantity data.

[0026] Optionally, obtaining the associated data information corresponding to the device operation data by using the FP-Growth algorithm based on the device operation data includes:

[0027] Performing a correlation analysis on the device operation data by using the FP-Growth algorithm to obtain the correlation degree between the device operation data;

[0028] Selecting the device operation data with the correlation degree greater than the set correlation degree threshold according to the correlation degree between the device operation data, and performing data fusion on the device operation data with the correlation degree greater than the set correlation degree threshold to obtain the associated data information.

[0029] Optionally, performing a correlation analysis on the device operation data by using the FP-Growth algorithm to obtain the correlation degree between the device operation data includes:

[0030] Scanning the device operation data to obtain a linear set composed of the device operation data;

[0031] Calculating the correlation degree between the data in the linear set by using the FP-Growth algorithm according to the linear set;

[0032] Mapping the positions of the data in the linear set and the positions of the corresponding device operation data, and obtaining the correlation degree between the device operation data according to the correlation degree between the data in the linear set.

[0033] Optionally, the fault type includes one or more of the following: winding fault, insulation fault, short circuit fault, coil fault, and discharge fault.

[0034] Based on the same inventive concept, the present invention also provides a fault diagnosis system applicable to a digital converter station, including:

[0035] A data acquisition module: configured to acquire device operation data in the digital converter station;

[0036] A data association module: configured to obtain the associated data information corresponding to the device operation data by using the FP-Growth algorithm based on the device operation data;

[0037] A fault diagnosis module: configured to output a fault type by using a pre-trained fault diagnosis model based on the associated data information;

[0038] Wherein, the fault diagnosis model in the fault diagnosis module is trained based on a Softmax classifier.

[0039] Optionally, the fault diagnosis module is specifically configured to:

[0040] Perform data preprocessing on the associated data information to obtain status operation data;

[0041] Use the principal component analysis method to perform data dimensionality reduction on the status operation data to obtain dimensionality-reduced operation data;

[0042] Use the pre-constructed fault diagnosis model to perform fault diagnosis on the dimensionality-reduced operation data and output the fault type.

[0043] Optionally, the fault diagnosis model in the fault diagnosis module includes the following training process:

[0044] Select a preset group from the historical equipment operation data as the input of the training data;

[0045] Use the fault type corresponding to the selected equipment operation data as the output of the training data;

[0046] Based on the input and output of the training data, train the preset Softmax classifier to obtain a fault diagnosis model.

[0047] Optionally, the use of the principal component analysis method in the fault diagnosis module to perform data dimensionality reduction on the status operation data to obtain dimensionality-reduced operation data includes:

[0048] Perform centering processing on the status operation data to obtain corresponding sample distribution data;

[0049] Based on the sample distribution data, obtain the corresponding covariance matrix;

[0050] According to the covariance matrix, obtain the eigenvalues and eigenvectors corresponding to the covariance matrix;

[0051] Reverse-order the eigenvectors according to the corresponding eigenvalues, select a specified number of the arranged eigenvectors to form a principal component matrix, and use the principal component matrix as the dimensionality-reduced operation data.

[0052] Optionally, the expression corresponding to the centering processing is as follows:

[0053]

[0054] where, data j represents the value of the j-th status operation data; j = 1...n; n represents the total number of data; data i represents the value of the i-th status operation data; data i′ represents the value of the i-th sample distribution data.

[0055] Optionally, the device operation data in the data acquisition module includes one or more of the following: device number, operation time, environment acquisition data, and process variable data;

[0056] Optionally, the data association module is specifically configured to:

[0057] Perform correlation analysis on the device operation data using the FP-Growth algorithm to obtain the correlation degree between the device operation data;

[0058] Select the device operation data with the correlation degree greater than the set correlation degree threshold according to the correlation degree between the device operation data, and perform data fusion on the device operation data with the correlation degree greater than the set correlation degree threshold to obtain correlation data information.

[0059] Optionally, the performing correlation analysis on the device operation data using the FP-Growth algorithm to obtain the correlation degree between the device operation data in the data association module includes:

[0060] Scan the device operation data to obtain a linear set composed of the device operation data;

[0061] Calculate the correlation degree between the data in the linear set using the FP-Growth algorithm according to the linear set;

[0062] Map the positions of the data in the linear set and the positions of the corresponding device operation data, and obtain the correlation degree between the device operation data according to the correlation degree between the data in the linear set.

[0063] Optionally, the fault type includes one or more of the following: winding fault, insulation fault, short circuit fault, coil fault, and discharge fault.

[0064] Based on the same inventive concept, the present invention also provides a computer device, including: one or more processors;

[0065] A memory for storing one or more programs;

[0066] When the one or more programs are executed by the one or more processors, a fault diagnosis method applicable to a digital converter station as described above is implemented.

[0067] Based on the same inventive concept, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, a fault diagnosis method applicable to a digital converter station as described above is implemented.

[0068] Compared with the closest prior art, the beneficial effects of the present invention are as follows:

[0069] The present invention provides a fault diagnosis method, system, device and medium applicable to a digital converter station, including: obtaining device operation data in the digital converter station; based on the device operation data, using the FP-Growth algorithm to obtain associated data information in the device operation data; based on the associated data information, using a pre-constructed fault diagnosis model to output a fault type; wherein, the fault diagnosis model is constructed based on a Softmax classifier; the present invention calculates the correlation between device operation data through the FP-Growth algorithm, and finally obtains the fault type through a pre-established fault diagnosis model based on the Softmax classifier; through the method in the present invention, the fault type can be quickly and accurately judged, the operation and maintenance level of the digital converter station can be improved, and thus a reliable guarantee is provided for the safe and stable operation of the converter station system. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 It is a schematic flow chart of a fault diagnosis method applicable to a digital converter station provided by the present invention;

[0071] Figure 2 It is a schematic flow chart of data dimensionality reduction for state operation data in a fault diagnosis method applicable to a digital converter station provided by the present invention;

[0072] Figure 3 It is a schematic structural composition diagram of a fault diagnosis system applicable to a digital converter station provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0073] The following further elaborates on the specific embodiments of the present invention with reference to the accompanying drawings.

[0074] Embodiment 1:

[0075] A fault diagnosis method applicable to a digital converter station provided by the present invention, the schematic flow chart is as Figure 1 shown, including:

[0076] Step 1: Obtain device operation data in the digital converter station;

[0077] Step 2: Based on the device operation data, use the FP-Growth algorithm to obtain the associated data information corresponding to the device operation data;

[0078] Step 3: Based on the associated data information, use a pre-trained fault diagnosis model to output a fault type;

[0079] Wherein, the fault diagnosis model is trained based on a Softmax classifier.

[0080] Specifically, the device operation data in step 1 includes one or more of the following: device number, operation time, environmental acquisition data, and process variable data. The devices in a digital converter station are generally divided into primary devices and secondary devices. Primary devices refer to those directly involved in power distribution, including transformers, circuit breakers, disconnectors, and automatic switches, etc. Secondary devices refer to auxiliary devices for monitoring, measuring, controlling, regulating, and protecting primary devices, including watt-hour meters, voltmeters, and measuring meters, etc. The present invention mainly conducts fault diagnosis on the primary devices of a digital converter station.

[0081] Step 2 includes:

[0082] Using the FP-Growth algorithm to perform correlation analysis on the device operation data to obtain the correlation degree between the device operation data;

[0083] According to the correlation degree between the device operation data, select the device operation data with a correlation degree greater than the set correlation degree threshold, and perform data fusion on the device operation data with a correlation degree greater than the set correlation degree threshold to obtain correlation data information;

[0084] The using the FP-Growth algorithm to perform correlation analysis on the device operation data to obtain the correlation degree between the device operation data includes:

[0085] Scan the device operation data to obtain a linear set composed of the device operation data;

[0086] According to the linear set, use the FP-Growth algorithm to calculate the correlation degree between the data in the linear set;

[0087] Map the positions of the data in the linear set and the positions of the corresponding device operation data, and according to the correlation degree between the data in the linear set, obtain the correlation degree between the device operation data.

[0088] Aiming at the problem of a single fault diagnosis method in a digital converter station, by performing data fusion according to the correlation degree between device operation data, the present invention can distinguish the correlation and redundancy between data.

[0089] Step 3 includes:

[0090] Perform data preprocessing on the correlation data information to obtain state operation data;

[0091] Use the principal component analysis method to perform data dimensionality reduction on the state operation data to obtain dimensionality-reduced operation data;

[0092] Use a pre-constructed fault diagnosis model to perform fault diagnosis on the dimensionality-reduced operation data and output the fault type;

[0093] By using the principal component analysis method to reduce the dimension of data, the present invention can solve the problem of high computational complexity caused by too high data dimension, which is beneficial to improving the generalization ability of the fault diagnosis model;

[0094] The fault types include one or more of the following: winding fault, insulation fault, short circuit fault, coil fault and discharge fault;

[0095] When preprocessing the associated data information, the methods adopted in the present invention mainly include: removing outliers of data, supplementing missing values and standardizing processing. By using the principal component analysis method to reduce the dimension of the preprocessed associated data information, the accuracy and effectiveness of the data can be improved, and the redundancy of the data can be reduced, thereby improving the correct rate of fault diagnosis.

[0096] The fault diagnosis model includes the following training process:

[0097] Select a preset group from the historical device operation data as the input of the training data;

[0098] Take the fault type corresponding to the selected device operation data as the output of the training data;

[0099] Based on the input and output of the training data, train a preset Softmax classifier to obtain a fault diagnosis model;

[0100] By using the Softmax regression classifier to classify and identify the characteristic data of the equipment in the digital converter station, after the input of the training data of the Softmax classifier, it can be mapped from the N-dimensional space to the fault type, and the labeled characteristic data can be classified accurately, and the output result will be expressed in the form of probability, making the fault diagnosis display result more intuitive.

[0101] As Figure 2 shown, using the principal component analysis method to reduce the dimension of the state operation data to obtain the reduced-dimension operation data includes:

[0102] S1: Centralize the state operation data to obtain the corresponding sample distribution data;

[0103] S2: Based on the sample distribution data, obtain the corresponding covariance matrix;

[0104] S3: According to the covariance matrix, obtain the eigenvalues and eigenvectors corresponding to the covariance matrix;

[0105] S4: Reverse-order the eigenvectors according to the corresponding eigenvalues, select a specified number of eigenvectors in the arrangement to form a principal component matrix, and use the principal component matrix as the reduced-dimension operation data;

[0106] The expression corresponding to the centralization process is as follows:

[0107]

[0108] Among them, data j represents the value of the operating data of the j-th state; j = 1...n; n represents the total number of data; data i represents the value of the operating data of the i-th state; data i′ represents the value of the i-th sample distribution data.

[0109] Embodiment 2:

[0110] Based on the same inventive concept, the present invention also provides a fault diagnosis system applicable to a digital converter station. The schematic diagram of the structural composition is as Figure 3 shown, including:

[0111] Data acquisition module: used to acquire the device operation data in the digital converter station;

[0112] Data association module: used to obtain the associated data information corresponding to the device operation data based on the device operation data by using the FP-Growth algorithm;

[0113] Fault diagnosis module: used to output the fault type based on the associated data information by using a pre-trained fault diagnosis model;

[0114] Among them, the fault diagnosis model in the fault diagnosis module is trained based on a Softmax classifier.

[0115] The device operation data in the data acquisition module includes one or more of the following: device number, operation time, environmental acquisition data, and process quantity data;

[0116] The data association module is specifically used for:

[0117] Performing correlation analysis on the device operation data by using the FP-Growth algorithm to obtain the correlation degree between the device operation data;

[0118] Selecting the device operation data with the correlation degree greater than the set correlation degree threshold according to the correlation degree between the device operation data, and performing data fusion on the device operation data with the correlation degree greater than the set correlation degree threshold to obtain the associated data information.

[0119] Performing correlation analysis on the device operation data by using the FP-Growth algorithm in the data association module to obtain the correlation degree between the device operation data, including:

[0120] Scan the device operation data to obtain a linear set composed of the device operation data;

[0121] According to the linear set, use the FP-Growth algorithm to calculate the correlation degree between the data in the linear set;

[0122] Map the positions of the data in the linear set and the positions of the corresponding device operation data, and obtain the correlation degree between the device operation data according to the correlation degree between the data in the linear set.

[0123] The fault diagnosis module is specifically used for:

[0124] Perform data preprocessing on the correlation data information to obtain state operation data;

[0125] Use the principal component analysis method to reduce the dimension of the state operation data to obtain reduced-dimension operation data;

[0126] Use a pre-constructed fault diagnosis model to perform fault diagnosis on the reduced-dimension operation data and output the fault type.

[0127] The fault type includes one or more of the following: winding fault, insulation fault, short circuit fault, coil fault, and discharge fault.

[0128] The fault diagnosis model in the fault diagnosis module includes the following training process:

[0129] Select a preset group from the historical device operation data as the input of the training data;

[0130] Use the fault type corresponding to the selected device operation data as the output of the training data;

[0131] Based on the input and output of the training data, train a preset Softmax classifier to obtain a fault diagnosis model.

[0132] The fault diagnosis module uses the principal component analysis method to reduce the dimension of the state operation data to obtain reduced-dimension operation data, including:

[0133] Perform centering processing on the state operation data to obtain corresponding sample distribution data;

[0134] Based on the sample distribution data, obtain the corresponding covariance matrix;

[0135] According to the covariance matrix, obtain the eigenvalues and eigenvectors corresponding to the covariance matrix;

[0136] Arrange the feature vectors in reverse order according to the corresponding eigenvalues, select a specified number of feature vectors in the arrangement to form a principal component matrix, and use the principal component matrix as the data for dimensionality reduction operation;

[0137] The expression corresponding to the centering process in the fault diagnosis module is as follows:

[0138]

[0139] where data j represents the value of the j-th state operation data; j = 1…n; n represents the total number of data; data i represents the value of the i-th state operation data; data i′ represents the value of the i-th sample distribution data.

[0140] Embodiment 3:

[0141] Based on the same inventive concept, the present invention also provides a computer device, which includes a processor and a memory. The memory is used to store a computer program, the computer program includes program instructions, and 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 in the computer storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of a fault diagnosis method applicable to a digital converter station in the above embodiment.

[0142] Embodiment 4:

[0143] Based on the same inventive concept, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in a computer 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 computer device and, of course, the extended storage medium supported by the computer device. The computer-readable storage medium provides a storage space, and this storage space stores the operating system of the terminal. Moreover, one or more instructions suitable for being loaded and executed by the processor are stored in this storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. One or more instructions stored in the computer-readable storage medium can be loaded and executed by the processor to implement the steps of a fault diagnosis method applicable to a digital converter station in the above-mentioned embodiments.

[0144] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0145] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified function in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0146] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and this instruction device implements the specified function in Figure 1 one flow or multiple flows and / or blocksFigure 1 The functions specified in one or more boxes.

[0147] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for implementing the steps of the functions specified in one or more processes and / or boxes. Figure 1 One process or more processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes.

[0148] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit the scope of its protection. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that after reading the present invention, various changes, modifications or equivalent replacements can still be made to the specific implementation manners of the application. However, these changes, modifications or equivalent replacements are all within the scope of protection of the claims pending for approval of the application.

Claims

1. A fault diagnosis method applicable to a digital converter station, characterized in that, Including: Obtain the device operation data in the digital converter station; Based on the device operation data, use the FP-Growth algorithm to obtain the associated data information corresponding to the device operation data; Based on the associated data information, use a pre-trained fault diagnosis model to output the fault type; Among them, the fault diagnosis model is trained based on a Softmax classifier.

2. The method according to claim 1, characterized in that, The step of using the pre-trained fault diagnosis model to output the fault type based on the associated data information includes: Perform data preprocessing on the associated data information to obtain the status operation data; Use the principal component analysis method to reduce the dimension of the status operation data to obtain the reduced-dimension operation data; Use the pre-constructed fault diagnosis model to perform fault diagnosis on the reduced-dimension operation data and output the fault type.

3. The method according to claim 2, characterized in that, The fault diagnosis model includes the following training process: Select a preset group from the historical device operation data as the input of the training data; Use the fault type corresponding to the selected device operation data as the output of the training data; Based on the input and output of the training data, train a preset Softmax classifier to obtain a fault diagnosis model.

4. The method according to claim 2, characterized in that, The step of using the principal component analysis method to reduce the dimension of the status operation data to obtain the reduced-dimension operation data includes: Perform centering processing on the status operation data to obtain the corresponding sample distribution data; Based on the sample distribution data, obtain the corresponding covariance matrix; According to the covariance matrix, obtain the eigenvalues and eigenvectors corresponding to the covariance matrix; Reverse-order the eigenvectors according to the corresponding eigenvalues, select a specified number of arranged eigenvectors to form a principal component matrix, and use the principal component matrix as the reduced-dimension operation data.

5. The method according to claim 4, characterized in that, The expression corresponding to the centering processing is as follows: Among them, data j represents the value of the operating data in the j-th state; j = 1...n; n represents the total number of data; data i represents the value of the operating data in the i-th state; data i′ represents the value of the sample distribution data in the i-th state.

6. The method according to claim 1, characterized in that, The device operation data includes one or more of the following: device number, operation time, environmental acquisition data, and process quantity data.

7. The method according to claim 1, characterized in that, The step of using the FP-Growth algorithm to obtain the associated data information corresponding to the device operation data based on the device operation data includes: Use the FP-Growth algorithm to perform correlation analysis on the device operation data to obtain the correlation degree between the device operation data; According to the correlation degree between the device operation data, select the device operation data with the correlation degree greater than the set correlation degree threshold, and perform data fusion on the device operation data with the correlation degree greater than the set correlation degree threshold to obtain the associated data information.

8. The method according to claim 7, characterized in that, The step of using the FP-Growth algorithm to perform correlation analysis on the device operation data to obtain the correlation degree between the device operation data includes: Scan the device operation data to obtain a linear set composed of the device operation data; According to the linear set, use the FP-Growth algorithm to calculate the correlation degree between the data in the linear set; Map the positions of the data in the linear set and the positions of the corresponding device operation data, and according to the correlation degree between the data in the linear set, obtain the correlation degree between the device operation data.

9. The method according to claim 1, characterized in that, The fault types include one or more of the following: winding fault, insulation fault, short - circuit fault, coil fault, and discharge fault.

10. A fault diagnosis system applicable to a digital converter station, characterized in that,including: Data acquisition module: used to acquire the device operation data in the digital converter station; Data association module: used to obtain the associated data information corresponding to the device operation data based on the device operation data by using the FP - Growth algorithm; Fault diagnosis module: used to output the fault type based on the associated data information by using a pre - trained fault diagnosis model; Among them, the fault diagnosis model in the fault diagnosis module is trained based on a Softmax classifier.

11. The system according to claim 10, wherein, The data association module is specifically used for: Performing correlation analysis on the device operation data by using the FP - Growth algorithm to obtain the correlation degree between the device operation data; According to the correlation degree between the device operation data, selecting the device operation data with the correlation degree greater than the set correlation degree threshold, and performing data fusion on the device operation data with the correlation degree greater than the set correlation degree threshold to obtain the associated data information.

12. The system according to claim 10, wherein, The fault diagnosis module is specifically used for: Performing data pre - processing on the associated data information to obtain the state operation data; Performing data dimensionality reduction on the state operation data by using the principal component analysis method to obtain the dimensionality - reduced operation data; Performing fault diagnosis on the dimensionality - reduced operation data by using a pre - constructed fault diagnosis model and outputting the fault type.

13. The system according to claim 12, wherein, The fault diagnosis module performs data dimensionality reduction on the state operation data by using the principal component analysis method to obtain the dimensionality - reduced operation data, including: Performing centering processing on the state operation data to obtain the corresponding sample distribution data; Based on the sample distribution data, obtaining the corresponding covariance matrix; According to the covariance matrix, obtaining the eigenvalues and eigenvectors corresponding to the covariance matrix; Arranging the eigenvectors in reverse order according to the corresponding eigenvalues, selecting a specified number of eigenvectors in the arrangement to form a principal component matrix, and using the principal component matrix as the dimensionality - reduced operation data.

14. A computer device, wherein, including: One or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, implementing a fault diagnosis method for a digital converter station as described in any one of claims 1 to 9.

15. A computer-readable storage medium, wherein, There is a computer program stored thereon, and when the computer program is executed, implementing a fault diagnosis method for a digital converter station as described in any one of claims 1 to 9.

Images