Improved DBSCAN dry-type transformer vibration signal fault early warning method and system

Abstract

The invention provides an improved DBSCAN dry-type transformer vibration signal fault early warning method and system, and belongs to the technical field of dry-type transformer fault diagnosis, and the method comprises the steps: obtaining a traction rectifier transformer vibration signal of a to-be-detected urban rail power supply system; processing the acquired vibration signal by using a pre-trained fault diagnosis model to obtain a fault diagnosis result; and if the number of the abnormal points in the fault diagnosis result exceeds a set threshold value, performing early warning. According to the method, the DBSCAN parameters are automatically optimized through multi-objective optimization and a simulated annealing algorithm, so that the judgment of abnormal points reaches a most accurate state, and the workload is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of dry-type transformer fault diagnosis, and particularly relates to an improved DBSCAN (Density-Based Spatial Clustering of Applications with Noise) dry-type transformer vibration signal fault warning method and system. Background Art

[0002] In the urban rail power supply system, as one of the key devices, the stability and safety of dry-type transformers play a crucial role in ensuring the normal operation of urban rail trains and the travel safety of passengers. However, due to the complexity and particularity of the urban rail power supply system, the traction rectifier transformers therein are prone to be affected by various factors during operation, thus generating fault risks. Traditional fault diagnosis methods often rely on empirical judgment or threshold-based monitoring, and these methods are often difficult to accurately judge the health status of transformers in complex environments.

[0003] In order to timely detect and prevent faults of dry-type transformers in the urban rail power supply system, the fault warning method based on vibration signals has become an important technical means. In recent years, the neural network technology, which has strong signal processing capabilities, has been widely used by domestic and foreign scholars in the vibration signal fault diagnosis of electrical equipment. However, the neural network requires a large amount of different types of data for model training. Since the actually collected vibration signals are mostly normal signals and the fault signal samples are small, it will affect the accuracy of model training, thus affecting the final accuracy.

[0004] To solve the problem of unbalanced data collection in actual fault diagnosis, an outlier detection algorithm can be used to diagnose faults for the actually collected data. First, collect the vibration signals of the traction rectifier transformers in the actual urban rail power supply system, and preprocess the data, including filtering, key feature extraction, and data standardization to ensure the effectiveness of the distance metric of DBSCAN. Secondly, use the silhouette coefficient and DBI as objective functions, select the simulated annealing algorithm for the optimization algorithm, build a parameter optimization model, and optimize the parameters of DBSCAN. Then, use DBSCAN to cluster the data. Normal data samples may form one or more high-density clusters, while fault samples will be marked as outliers or form independent clusters. Finally, check the output of DBSCAN, identify outliers and independent clusters, and mine potential fault patterns from them. The core concept of DBSCAN is to perform clustering according to the density of data points. It can identify sparse regions in the data as noise, which is very useful for discovering uncommon fault patterns. In the case of scarce fault samples, DBSCAN can help identify those abnormal data points that are significantly different from normal samples, that is, potential fault samples. However, in current research, for the determination of outliers and independent clusters, it often needs to be combined with the actual situation for manual secondary determination, being in a semi-automatic state. Summary of the Invention

[0005] The object of the present invention is to provide an improved DBSCAN dry-type transformer vibration signal fault warning method and system to solve at least one of the technical problems existing in the above-mentioned background technology.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] In the first aspect, the present invention provides an improved DBSCAN dry-type transformer vibration signal fault warning method, including:

[0008] Obtain the vibration signal of the traction rectifier transformer of the urban rail power supply system to be detected;

[0009] Process the obtained vibration signal by using a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein, the training of the fault diagnosis model includes: collecting the vibration signal of the traction rectifier transformer of the actual urban rail power supply system, establishing an unbalanced data set; performing preprocessing of filtering and key feature extraction on the data set; building an improved multi-objective optimization parameter algorithm model to optimize the DBSCAN parameters; inputting the optimized parameters into DBSCAN for clustering analysis;

[0010] If the number of abnormal points in the fault diagnosis result exceeds the set threshold, a warning is given.

[0011] As a further limitation of the first aspect of the present invention, the unbalanced data set is collected during the normal operation of the urban rail. Most of them are normal signals and there are very few abnormal samples.

[0012] As a further limitation of the first aspect of the present invention, the filtering process needs to filter out unnecessary interference in the environment. Since the actual acquisition environment is complex, there may be interference from train sounds, human voices, and vibrations of other electrical equipment to the collected signal. Therefore, the db8 wavelet is used to perform wavelet threshold denoising on the signal.

[0013] As a further limitation of the first aspect of the present invention, the key feature extraction is specifically: a total of eight key features including standard deviation, kurtosis, spectral mean, spectral root mean square value, frequency centroid, linear frequency axis, power spectrum entropy, and energy entropy, and a (1000*8) feature matrix is established. The first two of them are time-domain features, the next four are frequency-domain spectral features, and the last two are entropy features.

[0014] As a further limitation of the first aspect of the present invention, the improvement of multi-objective parameter optimization is mainly to optimize the values of the two main parameters Eps and Minpts of DBSCAN, and use the global silhouette coefficient and DBI of clustering as the objective function for optimization, and the optimization algorithm adopts the simulated annealing algorithm.

[0015] As a further limitation of the first aspect of the present invention, the clustering analysis in S4 mainly performs clustering according to the density of data points and is an unsupervised learning algorithm that does not rely on label information for training. If the transformer fault samples form sparse density regions in the data space while the normal samples are in the dense regions, DBSCAN can help identify these sparse regions, thereby marking possible fault patterns.

[0016] Furthermore, for the evaluation method in S5, the evaluation parameters are the silhouette coefficient and DBI, which can measure the compactness and separation degree of clustering respectively. Finally, the number of outliers is output, the results are observed, and a threshold is set for early warning.

[0017] In a second aspect, the present invention provides an improved DBSCAN dry-type transformer vibration signal fault early warning system, including:

[0018] An acquisition module for acquiring the vibration signals of the traction rectifier transformer of the urban rail power supply system to be detected;

[0019] A processing module for processing the acquired vibration signals by using a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein, the training of the fault diagnosis model includes: collecting the vibration signals of the traction rectifier transformer of the actual urban rail power supply system, establishing an unbalanced data set; performing preprocessing such as filtering and key feature extraction on the data set; building an improved multi-objective optimization parameter algorithm model to optimize the DBSCAN parameters; inputting the optimized parameters into DBSCAN for clustering analysis;

[0020] An early warning module for giving an early warning if the number of outliers in the fault diagnosis result exceeds the set threshold.

[0021] In a third aspect, the present invention provides a non-transitory computer-readable storage medium, which is used to store computer instructions. When the computer instructions are executed by a processor, the improved DBSCAN dry-type transformer vibration signal fault early warning method as described in the first aspect is implemented.

[0022] In a fourth aspect, the present invention provides a computer device, including a memory and a processor, where the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the improved DBSCAN dry-type transformer vibration signal fault early warning method as described in the first aspect.

[0023] Fifth aspect, the present invention provides an electronic device, including: a processor, a memory, and a computer program; wherein, the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device runs, the processor executes the computer program stored in the memory so that the electronic device executes instructions for implementing the improved DBSCAN dry-type transformer vibration signal fault warning method as described in the first aspect.

[0024] Advantages of the present invention: The DBSCAN parameters are automatically optimized through multi-objective optimization and simulated annealing algorithm to make the determination of abnormal points reach the most accurate state, thereby reducing the workload.

[0025] The advantages of the additional aspects of the present invention will be more clearly given in the following description part, or understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0027] Figure 1 It is a flowchart of the improved DBSCAN dry-type transformer vibration signal fault diagnosis according to the embodiment of the present invention.

[0028] Figure 2 It is a flowchart of the improved multi-objective optimization parameter algorithm according to the embodiment of the present invention.

[0029] Figure 3 It is a DBSCAN clustering structure diagram according to the embodiment of the present invention.

[0030] Figure 4 It is a flowchart of the improved DBSCAN algorithm according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] The embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals indicate the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0032] Those skilled in the art of the present technology can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the general understanding of those of ordinary skill in the art in the field to which the present invention belongs.

[0033] It should also be understood that terms such as those defined in a general dictionary should be understood as having a meaning consistent with their meaning in the context of the prior art, and will not be interpreted with an idealized or overly formal meaning unless defined as such here.

[0034] Those skilled in the art of the present technology can understand that, unless specifically stated otherwise, the singular forms "a", "an", "the", and "said" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the description of the present invention means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, and / or groups thereof.

[0035] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. Without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0036] For the convenience of understanding the present invention, the following further explains the present invention with specific embodiments in conjunction with the accompanying drawings, and the specific embodiments do not constitute a limitation to the embodiments of the present invention.

[0037] Those skilled in the art should understand that the drawings are only schematic diagrams of the embodiments, and the components in the drawings are not necessarily essential for implementing the present invention.

[0038] Embodiment 1

[0039] In this Embodiment 1, first, an improved DBSCAN dry-type transformer vibration signal fault early warning system is provided, including: an acquisition module for acquiring the vibration signal of the traction rectifier transformer of the urban rail power supply system to be detected; a processing module for processing the acquired vibration signal by using a pre-trained fault diagnosis model to obtain a fault diagnosis result; and an early warning module for giving an early warning if the number of abnormal points in the fault diagnosis result exceeds the set threshold.

[0040] In this embodiment, an improved DBSCAN dry-type transformer vibration signal fault warning method is implemented by using the above system, including: obtaining the vibration signal of the traction rectifier transformer of the urban rail power supply system to be detected; using a pre-trained fault diagnosis model to process the obtained vibration signal to obtain a fault diagnosis result; wherein, the training of the fault diagnosis model includes: collecting the vibration signal of the traction rectifier transformer of the actual urban rail power supply system, establishing an unbalanced data set; performing preprocessing of filtering and key feature extraction on the data set; building an improved multi-objective optimization parameter algorithm model to optimize the DBSCAN parameters; inputting the optimized parameters into DBSCAN for clustering analysis. If the number of abnormal points in the fault diagnosis result exceeds the set threshold, a warning is issued.

[0041] Among them, the db8 wavelet is used to perform wavelet threshold denoising on the signal. The key feature extraction includes: standard deviation, kurtosis, spectral mean, spectral root mean square value, frequency centroid, linear frequency axis, power spectrum entropy and energy entropy, a total of eight key features, and a 1000*8 feature matrix is established. The improvement of multi-objective parameter optimization includes optimizing the values of two main parameters Eps and Minpts of DBSCAN, and using the global silhouette coefficient and DBI of clustering as the objective function for optimization. The optimization algorithm adopts the simulated annealing algorithm. The clustering analysis includes clustering according to the density of data points. If the transformer fault samples form a sparse density region in the data space, while the normal samples are in the dense region, these sparse regions are identified through a density-based clustering algorithm to mark the fault mode. The evaluation parameters of the fault diagnosis model are the silhouette coefficient and DBI, which measure the compactness and separation of clustering respectively.

[0042] Embodiment 2

[0043] As Figure 1 shown, Embodiment 2 of the present invention provides an improved DBSCAN dry-type transformer vibration signal fault warning method.

[0044] First, the collected signal is extracted as an unbalanced data set, with an advance interval of 1000 and a default number of rows of 50. The number of rows can be expanded according to the amount of collected data. In terms of filtering, the db8 wavelet is used for denoising to filter out unnecessary interference.

[0045] Secondly, key features of the dataset are extracted. Due to the particularity of urban rail transit, the signal changes with the periodic variation of the load. Therefore, selecting suitable features can help improve the accuracy of diagnosis. The present invention selects to conduct comprehensive analysis by combining multiple features. The eight selected features form a feature matrix, namely: standard deviation, kurtosis, spectral mean, spectral root mean square value, frequency centroid, linear frequency axis, power spectrum entropy, and energy entropy. The first two of them are time-domain features, the last four are frequency-domain features, and the last two are entropy features. Their calculation formulas are listed below.

[0046]

[0047] Among them, X i is the i-th sample point, n is the total number of samples, X is the mean value of the signal, N is the total number of frequency components, S(f i ) is the power spectral density value of the i-th frequency component, f max is the highest frequency, f min is the lowest frequency, P(f i ) is the normalized power spectral density value of the i-th frequency component, E i is the energy of the i-th time window or frequency band.

[0048] Figure 2 The flow chart of the improved multi-objective optimization parameter algorithm provided by the present invention is shown. Using multi-objective optimization aims to optimize multiple objective functions simultaneously and further optimize the parameters of DBSCAN.

[0049] First of all, two objective functions are defined: F(1): global silhouette coefficient, F(2): Davies-Bouldin Index (DBI), which measure the compactness and separation degree of clustering respectively, and combine them into a comprehensive objective function.

[0050] The global silhouette coefficient is used to evaluate the quality of the clustering result and measure the difference between the similarity of each sample with other samples in the same cluster and the similarity with the nearest neighbor cluster. The value of the silhouette coefficient ranges from -1 to 1. A value close to 1 indicates that the sample is well clustered in the same cluster, close to 0 indicates that the sample is on the boundary between two clusters, and close to -1 indicates that the sample is misclustered in other clusters. Its calculation formula is:

[0051]

[0052] Among them, i is the number of samples, and the cluster it belongs to is defined as C i , a(i) is the average distance from sample i to other samples in the same cluster (intra-cluster compactness), b(i) is the average distance from sample i to all samples in the nearest neighbor cluster C i (inter-cluster separation), and n is the total number of samples.

[0053] The DBI is used to evaluate the separation and compactness of clusters. It calculates the similarity between each pair of clusters and takes the maximum value of the similarities among all clusters as an index. A smaller DBI value indicates a better clustering result because it means better separation between clusters and higher compactness within clusters. Its calculation formula is as follows:

[0054]

[0055] Among them, S i is the average distance from the samples within a cluster to the cluster center, u i is the center of the cluster, |C i | is the number of samples in the cluster, ||μ i -μ j || calculates the distance between clusters i and j, N is the total number of clusters, and by calculating the maximum value of the Davies - Bouldin ratios for each pair of clusters, the average value of all clusters is finally calculated.

[0056] Secondly, select the optimization algorithm of simulated annealing and set the initial parameters, such as the initial temperature, temperature decay rate, initial solution, etc. The detailed parameter setting ranges are shown in Table 1, and the initial solutions Eps' and Minpts' are obtained through the algorithm.

[0057] Table 1 Specific initial parameter settings of the improved algorithm

[0058]

[0059]

[0060] Finally, calculate the objective function again to obtain F(1)' and F(2)', decide whether to accept the new solution, and update the current new solution and temperature. Retrain DBSCAN using the optimized parameters and verify the quality of the clustering result.

[0061] Figure 3 This is the DBSCAN clustering structure diagram provided by the embodiment of the present invention.

[0062] As a density - based unsupervised training algorithm, the DBSCAN algorithm can adaptively determine the number of partitions without setting the number of partitions and achieve the classification effect, and has a good effect on the processing of unbalanced data sets. Select the two optimized parameters: neighborhood and minimum number of neighborhood points.

[0063] Neighborhood (Eps): Defines the radius of a point's neighborhood, indicating that the points within this radius will be considered neighborhood points.

[0064] Minimum number of neighborhood points (Minpts): Defines the minimum number of neighborhood points required for a point to become a core point.

[0065] Due to different data sets, the parameters will be different. After optimizing the parameters of the improved algorithm through the data set provided by the present invention, the results of DBSCAN clustering are as follows:

[0066] Initial DBSCAN parameters: eps = 1, min_samples = 8

[0067] Initial clustering result evaluation metrics: Silhouette Score = 0.29, Davies - Bouldin Index = 1.19

[0068] Optimized DBSCAN parameters: eps = 1.61, min_samples = 5.05

[0069] Optimized clustering result evaluation metrics: Silhouette Score = 0.86, Davies - Bouldin Index = 0.63. The evaluation metrics are the silhouette coefficient and DBI. From the results, the silhouette coefficient is closer to 1, indicating a relatively high sample compactness, and the DBI is lower, indicating a high separation between clusters and a high compactness within clusters, suggesting that a good clustering effect has been achieved.

[0070] Figure 4 It is the flow chart of the improved DBSCAN algorithm provided by the embodiment of the present invention.

[0071] The optimized parameters obtained from the above steps are input into DBSCAN for clustering analysis. To evaluate the effect of outlier detection, two groups of signals are collected for comparison. One group is the normal signal D1, and the other group is the artificially deliberately knocked interference signal D2. The improved clustering process is performed on the two groups of signals respectively, and the results are shown in Table 2.

[0072] Table 2 Improved DBSCAN clustering results

[0073]

[0074] From the results, it can be seen that the number of outliers in the normal signal generally does not exceed 5, while when there is knocking, the number of outliers significantly exceeds 10. Therefore, the alarm threshold can be set to 5, that is, when the number of outliers exceeds 5, a fault warning signal is released to achieve the effect of automatic fault warning.

[0075] Example 3

[0076] This Example 3 provides a non - transient computer - readable storage medium. The non - transient computer - readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the improved DBSCAN dry - type transformer vibration signal fault warning method described above is implemented. The method includes:

[0077] Obtain the vibration signal of the traction rectifier transformer of the urban rail power supply system to be detected;

[0078] Process the obtained vibration signal by using a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein, the training of the fault diagnosis model includes: collecting the vibration signal of the traction rectifier transformer of the actual urban rail power supply system, establishing an unbalanced data set; performing preprocessing of filtering and key feature extraction on the data set; building an improved multi-objective optimization parameter algorithm model to optimize the DBSCAN parameters; inputting the optimized parameters into DBSCAN for clustering analysis;

[0079] If the number of abnormal points in the fault diagnosis result exceeds the set threshold, give an early warning.

[0080] Embodiment 4

[0081] Embodiment 4 of the present invention provides a computer device, including a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the improved DBSCAN dry-type transformer vibration signal fault warning method as described above. This method includes:

[0082] Obtain the vibration signal of the traction rectifier transformer of the urban rail power supply system to be detected;

[0083] Process the obtained vibration signal by using a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein, the training of the fault diagnosis model includes: collecting the vibration signal of the traction rectifier transformer of the actual urban rail power supply system, establishing an unbalanced data set; performing preprocessing of filtering and key feature extraction on the data set; building an improved multi-objective optimization parameter algorithm model to optimize the DBSCAN parameters; inputting the optimized parameters into DBSCAN for clustering analysis;

[0084] If the number of abnormal points in the fault diagnosis result exceeds the set threshold, give an early warning.

[0085] Embodiment 5

[0086] Embodiment 5 of the present invention provides an electronic device, including: a processor, a memory, and a computer program; wherein, the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device runs, the processor executes the computer program stored in the memory so that the electronic device executes the instructions for implementing the improved DBSCAN dry-type transformer vibration signal fault warning method as described above. This method includes:

[0087] Obtain the vibration signal of the traction rectifier transformer of the urban rail power supply system to be detected;

[0088] Process the acquired vibration signals using a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein, the training of the fault diagnosis model includes: collecting the vibration signals of the traction rectifier transformer in the actual urban rail power supply system, and establishing an unbalanced data set; performing preprocessing on the data set including filtering and extracting key features; building an improved multi-objective optimization parameter algorithm model to optimize the DBSCAN parameters; inputting the optimized parameters into DBSCAN for clustering analysis;

[0089] If the number of outliers in the fault diagnosis result exceeds the set threshold, a warning is issued.

[0090] 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 an entirely hardware embodiment, an entirely 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 storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0091] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (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 flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, 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, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0092] 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, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operation steps are performed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocksFigure 1 Steps of functions specified in one or more boxes.

[0094] Although the specific embodiments of the present invention have been described in conjunction with the accompanying drawings, they do not limit the protection scope of the present invention. Those skilled in the art should understand that based on the technical solutions disclosed in the present invention, various modifications or deformations that can be made by those skilled in the art without creative efforts should be covered within the protection scope of the present invention.

Claims

1. An improved DBSCAN dry-type transformer vibration signal fault warning method, characterized in that, Including: Obtain the vibration signal of the traction rectifier transformer of the urban rail power supply system to be detected; Process the obtained vibration signal by using a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein, the training of the fault diagnosis model includes: collecting the vibration signal of the traction rectifier transformer of the actual urban rail power supply system, establishing an unbalanced data set; preprocessing the data set by filtering and extracting key features; building an improved multi-objective optimization parameter algorithm model to optimize the DBSCAN parameters; inputting the optimized parameters into DBSCAN for clustering analysis; If the number of abnormal points in the fault diagnosis result exceeds the set threshold, give an early warning.

2. The improved DBSCAN dry-type transformer vibration signal fault warning method according to claim 1, characterized in that, Perform wavelet threshold denoising on the signal using db8 wavelet.

3. The improved DBSCAN dry-type transformer vibration signal fault warning method according to claim 1, characterized in that, Key feature extraction includes: standard deviation, kurtosis, spectral mean, spectral root mean square value, frequency centroid, linear frequency axis, power spectrum entropy, and energy entropy, a total of eight key features, and establish a 1000*8 feature matrix.

4. The improved DBSCAN dry-type transformer vibration signal fault early warning method according to claim 1, characterized in that Improve multi-objective parameter optimization, including optimizing the values of two main parameters Eps and Minpts of DBSCAN, and using the global silhouette coefficient and DBI of clustering as the objective function for optimization. The optimization algorithm adopts the simulated annealing algorithm.

5. The improved DBSCAN dry-type transformer vibration signal fault early warning method according to claim 1, wherein, Clustering analysis includes clustering according to the density of data points. If the transformer fault samples form a sparse density region in the data space, while the normal samples are in the dense region, identify these sparse regions through a density-based clustering algorithm and mark the fault patterns.

6. The improved DBSCAN dry-type transformer vibration signal fault warning method according to claim 1, characterized in that, The evaluation parameters of the fault diagnosis model are the silhouette coefficient and DBI, which measure the compactness and separation of clustering respectively.

7. An improved DBSCAN dry-type transformer vibration signal fault early warning system, characterized in that, Including: An acquisition module for obtaining the vibration signal of the traction rectifier transformer of the urban rail power supply system to be detected; A processing module for processing the obtained vibration signal by using a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein, the training of the fault diagnosis model includes: collecting the vibration signal of the traction rectifier transformer of the actual urban rail power supply system, establishing an unbalanced data set; preprocessing the data set by filtering and extracting key features; building an improved multi-objective optimization parameter algorithm model to optimize the DBSCAN parameters; inputting the optimized parameters into DBSCAN for clustering analysis; An early warning module for giving an early warning if the number of abnormal points in the fault diagnosis result exceeds the set threshold.

8. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the improved DBSCAN dry-type transformer vibration signal fault early warning method as described in any one of claims 1-6 is implemented.

9. A computer device, characterized in that, Including a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the improved DBSCAN dry-type transformer vibration signal fault early warning method as described in any one of claims 1-6.

10. An electronic device, characterized in that, Including: A processor, a memory, and a computer program; wherein, the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device runs, the processor executes the computer program stored in the memory so that the electronic device executes instructions for implementing the improved DBSCAN dry-type transformer vibration signal fault warning method according to any one of claims 1-6.

Images