Transformer fault diagnosis method and system based on photoacoustic signal reconstruction sensitive field optimization

Abstract

The invention discloses a transformer fault diagnosis method and system based on photoacoustic signal reconstruction sensitive field optimization. The method specifically comprises the following steps: firstly, monitoring multiple gas photoacoustic signals in a transformer oil sample to obtain a multivariate sequence matrix of the signals; secondly, mapping the multivariate sequence matrix into a polar coordinate graph in a scattered point form through the idea of reconstructing a sensitive field; then extracting shallow local features, clustering the features into a plurality of mutually exclusive categories, taking the center of each category as a visual representation factor, and forming a visual feature table; and finally, realizing classification of transformer fault diagnosis based on an improved autonomous learning multi-space (ALMMo-0) classifier. According to the method, the multi-element photoacoustic signal reflecting the gas concentration is reconstructed into a sensitive field instead of a concentration threshold value or ratio form, diagnosis features hidden in the signal are better revealed, meanwhile, deep feature extraction and coding of the image are achieved, the transparency and interpretability of the model are improved, model parameters are automatically updated through data driving, and the accuracy of the detection result is improved. And the hyper-parameters do not need to be manually adjusted. The method is of great significance for improving the accuracy and practicability of transformer fault diagnosis.

Description

Technical Field

[0001] The present invention belongs to the field of transformer fault diagnosis, and in particular relates to a transformer fault diagnosis method and system based on photoacoustic signal reconstruction sensitive field optimization. Background Art

[0002] Transformers play a core role in the power system and are crucial to ensuring the stable operation of the system. Once a transformer fails, it may not only cause damage to related power facilities, but also affect the overall safety and stable operation of the power grid. In severe cases, it may even cause large-scale power outages with widespread impact. Therefore, monitoring the condition of the transformer and evaluating the condition of the transformer through fault diagnosis algorithms can predict the health status of the transformer, thereby improving the reliability, stability and safety of the power system.

[0003] At present, the main technology used for transformer operation status estimation and fault diagnosis is Dissolved Gas Analysis (DGA), which focuses on the detection of gases such as CO, CO, CH4, C2H4, C2H2, and CH2 dissolved in transformer oil. Common detection methods include: Gas Chromatography (GC), Photo Acoustic Spectroscopy (PAS), Raman Spectroscopy (RS), Fourier Transform Infrared Spectroscopy (FTIRS), Fiber Grating (FBG), etc. Gas chromatography is a commonly used means of transformer fault detection in power systems. However, gas chromatography requires regular calibration and is cumbersome to operate and has a long detection cycle, and cannot quickly and timely realize transformer fault diagnosis; the PAS method uses the photoacoustic effect to obtain the concentration of the gas by collecting and processing the photoacoustic signal, and has the characteristics of fast detection speed, high sensitivity and stable performance; the RS method analyzes the gas in the transformer oil based on the Raman scattering principle, and its characteristics are high scalability, but low detection sensitivity: the FTIRS method analyzes the gas in the transformer oil based on the Fourier transform infrared spectroscopy, and its characteristics are that it does not require carrier gas and is maintenance-free, but it is easily affected by interfering gases, and the spectral baseline is prone to distortion or drift; FBG detects dissolved gas in oil based on optical fiber sensors, and has the characteristics of small size, good coupling, polarization insensitivity, easy maintenance, and a large bandwidth range, but optical fiber only measures narrow bands, and measuring multi-component gases requires a variety of different fiber gratings, which makes engineering applications difficult. Summary of the invention

[0004] In order to achieve the above objectives, the present invention proposes a transformer fault diagnosis method and system based on photoacoustic signal reconstruction and sensitive field optimization, which reconstructs the multivariate photoacoustic signal reflecting the gas concentration into a sensitive field rather than in the form of a concentration threshold or ratio, so as to better reveal the diagnostic features hidden in the signal. At the same time, by realizing deep feature extraction and encoding of the image, it helps to improve the transparency and interpretability of the model. How to reduce the magnitude of diagnostic process parameters is of great significance to improving the accuracy and practicality of transformer fault diagnosis.

[0005] The first aspect is a transformer fault diagnosis method based on photoacoustic signal reconstruction and sensitive field optimization. Specifically, it includes:

[0006] Step 1: Obtain a multivariate sequence matrix of signals by monitoring photoacoustic signals of multiple gases in transformer oil samples;

[0007] Step 2: Map the multivariate sequence matrix in the polar coordinate diagram in the form of scattered points by reconstructing the sensitive field;

[0008] Step 3: Extract shallow local features and cluster them into multiple mutually exclusive categories. The shortest probability entropy of the center of each category is used as a visual representation factor to form a visual feature vector.

[0009] Step 4: Classify transformer fault diagnosis based on autonomous learning multi-space (ALMMo-0) classifier.

[0010] Furthermore, in the transformer fault diagnosis method based on photoacoustic signal reconstruction sensitive field optimization, the main contents of step 1 are:

[0011] A small amount of oil sample is extracted from the transformer, and the dissolved gas in the oil sample is converted into a gas sample through the oil-gas separation module. The modulated laser irradiates the gas sample at a specific wavelength (or band), causing a slight change in local temperature and pressure, thereby generating a sound wave signal sequence. The sound wave sequences generated by multiple groups of dissolved gases are photoacoustic signal sequences, which in turn form a multivariate sequence matrix V M N , M is the number of gas types, and N is the sequence sample length.

[0012] Furthermore, the transformer fault diagnosis method based on photoacoustic signal reconstruction of sensitive field optimization, the idea of ​​reconstructing the sensitive field in step 2, specifically includes the following contents.

[0013] Define xmax and xmin as V i N , i=1,2,…,the maximum and minimum values ​​of M. For each time point i, the corresponding amplitude is xi, the hysteresis coefficient a and the amplitude angle offset θ l , and the amplification factor ζ. The specific reconstruction relationship is defined by the following formula:

[0014] The polar radius r(i) is expressed as:

[0015]

[0016] The angular offset θ(i) is defined as:

[0017]

[0018] The reflection angle φ(i) is defined as:

[0019]

[0020] Angular offset θ l Defined as:

[0021]

[0022] The value range of l is from 0 to L-1, where L represents the total number of planes in the sensitive field. By adjusting the amplification factor ζ and the hysteresis coefficient a, any point in the multivariate signal matrix can be converted into an intuitive representation in polar coordinates to form a reconstructed sensitive field image.

[0023] Furthermore, in the transformer fault diagnosis method based on photoacoustic signal reconstruction sensitive field optimization, the extraction of shallow local features in step 3 is specifically performed by using SURF features and FAST features to extract two shallow features.

[0024] Furthermore, the transformer fault diagnosis method based on photoacoustic signal reconstruction sensitive field optimization also includes the step 3.

[0025] Use Kmeans++ to cluster the two shallow features into Kc clusters. The shortest probability entropy of each cluster is calculated by the following formula and used as the characterization factor of the cluster center. Finally, the shallow features are encoded into a feature vector with a dimension of 1*Kc.

[0026]

[0027] Among them, G is the cluster index, g is the feature point index in the Gth cluster, and D min is the shortest distance between the feature point and the cluster center within the cluster, and D(g) is the distance between the gth feature point and the cluster center.

[0028] Furthermore, in the transformer fault diagnosis method based on photoacoustic signal reconstruction sensitive field optimization, the specific content of the autonomous learning multi-space (ALMMo-0) classifier in step 4 is:

[0029] Define {g1,g2,g3,…,g τ} is the feature vector set with a dimension of 1*Kc and is used as the training data set. The number of transformer fault categories is set to q, that is, the number of subspaces, and each subspace corresponds to a set of feature classes.

[0030] First, we select individual eigenvectors to form a preliminary set of subspaces. In the training phase, {g1,g2,g3,…,g τ The single feature vectors of the set are input into the autonomous learning multi-space (ALMMo-0) classifier for training. τ The similarity between it and each subspace is calculated according to the following formula.

[0031]

[0032]

[0033]

[0034] in is the average value of all eigenvectors in the i-th subspace, is the average scalar product of the ith subspace, τ is the sample index of the eigenvector set, ‖‖ is the norm calculation, and g ini is a single eigenvector of the preliminary set.

[0035] Furthermore, the transformer fault diagnosis method based on photoacoustic signal reconstruction sensitive field optimization, the autonomous learning multi-space (ALMMo-0) classifier also includes.

[0036] For the input sample g τ , the classifier will calculate q R(g i τ ) value. τ Distribution and maximum R(g i τ ) and fill it into the corresponding subspace for the next round of training. After the training is completed, the feature vector of the collected samples can be tested in real time. The allocation result can be expressed as:

[0037] Class i = argmax i＝1,2,3,...,q (R i τ )

[0038] Second, the transformer fault diagnosis system based on photoacoustic signal reconstruction and sensitive field optimization includes:

[0039] Oil-gas separation module, photoacoustic spectroscopy detection sensor, edge detection device, and transformer fault diagnosis service platform.

[0040] The edge detection device adopts a modular design, and the hardware specifically includes a communication unit, a main control unit, a positioning unit, a power supply unit, and a storage unit. The communication unit supports wireless communications of WiFi and 4G, mainly realizing communication with the transformer fault diagnosis service platform, and supports RS232 and RS485 wired communications, mainly realizing data communication with the photoacoustic spectroscopy detection sensor. The main control unit contains the FPGA+D2000-CPU of V7-690T, and the positioning unit mainly realizes the position positioning of the edge detection device, supporting GPS and Beidou positioning. The power supply unit provides power to each module and unit of the device, and realizes functions such as charging and power detection of the backup battery. The storage unit supports SD card or SSD hard disk expansion, which is convenient for storing historical data on the edge side.

[0041] The software design includes: operating system, language environment, data preprocessing, edge computing and edge-service collaborative services. The edge detection device developed an edge computing model based on data preprocessing algorithm and transformer fault diagnosis in the Kylin operating system environment through Python, C, C++ and other languages, and built an edge-service collaborative service suitable for transformer fault diagnosis, which mainly includes the storage of edge computing results, the interaction of device data and service platform data, and the update of edge computing models.

[0042] The oil-gas separation module is connected to the transformer tank to separate the oil and gas in the transformer tank. The sample gas is used as the dissolved gas in the transformer oil and is connected to the photoacoustic spectrum detection sensor through the air inlet valve and the air outlet valve. The edge detection device controls the photoacoustic spectrum detection sensor to detect the photoacoustic signal of the sample gas. The transformer fault diagnosis model running on the edge detection device is used to perform real-time fault diagnosis on the transformer at the edge end, and the calculation results are uploaded to the transformer fault diagnosis service platform. The transformer fault diagnosis service platform can be used to view the transformer status, manage the edge detection device and sensors, and update the edge computing model. The operation and maintenance personnel can view the status of the transformer through the mobile terminal. When the transformer fails, the alarm information can be sent to the operation and maintenance personnel, so that the operation and maintenance personnel can take preventive measures quickly.

[0043] The beneficial effects of the present invention are as follows:

[0044] The multivariate photoacoustic signal reflecting the gas concentration is reconstructed into a sensitive field rather than in the form of a concentration threshold or ratio to better reveal the diagnostic features hidden in the signal. In order to solve the problem of weak diagnostic ability of high-dimensional shallow features, an image feature encoding method based on the shortest probability entropy is proposed to form a visual feature table to achieve deep feature extraction and encoding of the image. Finally, we use a data-driven multi-space model to handle complex parameter adjustment problems under different working conditions, which improves the transparency and interpretability of the model. The model parameters are automatically updated by data-driven, without the need to manually adjust hyperparameters, reducing the huge training cost and optimization cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Flow chart of the method of the present invention

[0046] Figure 2 The invention is sensitive to the reconstruction of the photoacoustic signal.

[0047] Figure 3 The local feature point clustering result of the present invention (Kc=5)

[0048] Figure 4 It is a system framework diagram of the present invention.

[0049] Specific implementation cases

[0050] The transformer fault diagnosis method and system based on photoacoustic signal reconstruction and sensitive field optimization described in the present invention will be further explained and illustrated below in conjunction with the drawings in the specification and specific embodiments. However, such explanation and illustration do not constitute an improper limitation on the technical solution of the present invention.

[0051] The fault diagnosis principle of transformer photoacoustic spectroscopy (PAS) is mainly based on the analysis of dissolved gases in transformer oil. Faults such as local overheating, discharge, and insulation aging inside the transformer will produce specific types and proportions of gases, which will then dissolve in the transformer's insulating oil. By monitoring the types and contents of these gases, the health status and potential faults of the transformer can be indirectly judged.

[0052] Currently, by analyzing the photoacoustic signals of different gases (such as methane CH4, ethane C2H6, ethylene C2H4, acetylene C2H2, carbon monoxide CO, carbon dioxide CO2, etc.), their respective concentrations can be determined. The types and proportions of these gases are closely related to specific types of transformer faults, forming the so-called "fault characteristic gas ratios", such as the three-ratio method or the five-ratio method. However, the potential characteristics of the fault are often limited to the actual environment and application scenarios because they are only explained based on intuitive thresholds and concentration ratios. It should be noted that in multiple tests of local overheating, arc discharge and other faults, it was found that the existing methods would have delayed alarms in actual applications.

[0053] The multivariate photoacoustic signal reflecting the gas concentration is reconstructed into a sensitive field rather than in the form of a concentration threshold or ratio to better reveal the diagnostic features hidden in the signal. In order to solve the problem of weak diagnostic ability of high-dimensional shallow features, an image feature encoding method based on the shortest probability entropy is proposed to form a visual feature table to achieve deep feature extraction and encoding of the image. Finally, we use a data-driven multi-space model to handle complex parameter adjustment problems under different working conditions, which improves the transparency and interpretability of the model. The model parameters are automatically updated by data-driven, without the need to manually adjust hyperparameters, reducing the huge training cost and optimization cost.

[0054] As attached Figure 1 As shown, the transformer fault diagnosis method based on photoacoustic signal reconstruction sensitive field optimization of the present invention may include the following steps:

[0055] Step 1: Obtain a multivariate sequence matrix of signals by monitoring the photoacoustic signals of multiple gases in the transformer oil sample;

[0056] 1.1 Extract a small amount of oil sample from the transformer, separate the dissolved gas in the oil sample through the oil-gas separation module to form a gas sample;

[0057] 1.2 Use modulated laser to irradiate the gas sample at a specific wavelength (or band) to stimulate small changes in local temperature and pressure, thereby generating a sequence of acoustic wave signals.

[0058] 1.3 The sound wave sequences generated by multiple groups of dissolved gases are photoacoustic signal sequences, which in turn form a multivariate sequence matrix V M N , where M is the number of gas types and N is the sequence sample length.

[0059] Step 2: Map the multivariate sequence matrix in the polar coordinate diagram in the form of scattered points by reconstructing the sensitive field;

[0060] 2.1 Define xmax and xmin as V i N , i=1,2,…,the maximum and minimum values ​​of M;

[0061] 2.2 For each time point i, according to its amplitude xi, hysteresis coefficient a, amplitude angle offset θ l , and the amplification factor ζ, through the following specific reconstruction relationship, any point in the multivariate signal matrix is ​​converted into an intuitive representation in polar coordinates to form a reconstructed sensitive field image:

[0062] The polar radius r(i) is expressed as:

[0063]

[0064] The angular offset θ(i) is defined as:

[0065]

[0066] The reflection angle φ(i) is defined as:

[0067]

[0068] Angular offset θ l Defined as:

[0069]

[0070] The value of l ranges from 0 to L-1, where L represents the total number of planes in the sensitive field;

[0071] 2.3 The representation effect of the sensitive field image is optimized by adjusting the amplification factor ζ and the hysteresis coefficient a.

[0072] Step 3: Extract shallow local features and cluster them into multiple mutually exclusive categories. The shortest probability entropy of the center of each category is used as a visual representation factor to form a visual feature vector.

[0073] Step 4: Classify transformer fault diagnosis based on autonomous learning multi-space (ALMMo-0) classifier.

[0074] In step 3, two shallow features are extracted using SURF features and FAST features. It should be noted that in local feature extraction, feature detection and description are separable. First, the location information of the feature is detected, and then it is characterized by a digital description.

[0075] The steps of SURF to extract local features are:

[0076] First, the integral image (Integral Image) and the Gaussian difference integral image (DoG, Difference of Gaussian) of the image are calculated.

[0077] Use DoG images in Gaussian scale space to detect potential key points. This includes comparing DoG images of adjacent scales at different scales to find local extreme points, i.e. key points. Then threshold screening is performed on candidate key points to remove key points with low contrast and edge response to ensure the stability of key points.

[0078] The key points detected initially are precisely located and their scales are fine-tuned. The principal curvature of the Hessian matrix is ​​usually used to optimize the position and scale of the key points.

[0079] The steps of FAST to extract local features are:

[0080] Select an initial pixel point as a candidate corner point, and set a threshold constant T (usually a fixed value of the brightness difference of the sensitive field image).

[0081] For each candidate pixel, check the brightness difference of a circle around the pixel (usually 16 consecutive pixels, forming a ring with a radius of 3, but excluding the central pixel itself). Specifically, check whether there are N consecutive pixels (usually N = 12 consecutive pixels) in this ring that are at least T units brighter (or darker) than the central pixel.

[0082] If such continuous pixels are found in the clockwise or counterclockwise direction, it is considered a corner candidate. If continuous pixels that meet the conditions can be found in both directions, the direction with more continuous pixels is selected.

[0083] In order to avoid repeated detection and improve the quality of corner points, it is necessary to perform non-maximum suppression around the detected corner points to remove those feature points that are not the most significant.

[0084] After extracting local features, Kmeans++ is used to cluster the two shallow features into Kc clusters. The shortest probability entropy of each cluster is calculated by the following formula and used as the characterization factor of the cluster center. Finally, the shallow features are encoded into a feature vector with a dimension of 1*Kc.

[0085]

[0086] Among them, G is the cluster index, g is the feature point index in the Gth cluster, and D min is the shortest distance between the feature point and the cluster center within the cluster, and D(g) is the distance between the gth feature point and the cluster center.

[0087] In step 4, first define {g1,g2,g3,…,g τ} is the feature vector set with a dimension of 1*Kc and is used as the training data set. The number of transformer fault categories is set to q, that is, the number of subspaces, and each subspace corresponds to a set of feature classes.

[0088] Select a single feature vector to form a preliminary set of subspaces. In the training phase, {g1,g2,g3,…,g τ The single feature vectors of the set are input into the autonomous learning multi-space (ALMMo-0) classifier for training. τ The similarity between it and each subspace is calculated according to the following formula.

[0089]

[0090]

[0091]

[0092] in is the average value of all eigenvectors in the i-th subspace, is the average scalar product of the ith subspace, τ is the sample index of the eigenvector set, ‖‖ is the norm calculation, and g ini is a single eigenvector of the preliminary set.

[0093] For the input sample g τ , the classifier will calculate q R(g i τ ) value. τ Distribution and maximum R(g i τ ) and fill it into the corresponding subspace for the next round of training. After the training is completed, the feature vector of the collected samples can be tested and diagnosed in real time. The allocation result can be expressed as:

[0094] Class i = argmax i＝1,2,3,...,q (R i τ )

[0095] At the same time, the present invention designs a transformer fault diagnosis system based on photoacoustic signal reconstruction sensitive field optimization, including:

[0096] Oil-gas separation module, photoacoustic spectroscopy detection sensor, edge detection device, and transformer fault diagnosis service platform.

[0097] The edge detection device adopts a modular design, and the hardware specifically includes a communication unit, a main control unit, a positioning unit, a power supply unit, and a storage unit. The communication unit supports wireless communications of WiFi and 4G, mainly realizing communication with the transformer fault diagnosis service platform, and supports RS232 and RS485 wired communications, mainly realizing data communication with the photoacoustic spectroscopy detection sensor. The main control unit contains the FPGA+D2000-CPU of V7-690T, and the positioning unit mainly realizes the position positioning of the edge detection device, supporting GPS and Beidou positioning. The power supply unit provides power to each module and unit of the device, and realizes functions such as charging and power detection of the backup battery. The storage unit supports SD card or SSD hard disk expansion, which is convenient for storing historical data on the edge side.

[0098] The software design includes: operating system, language environment, data preprocessing, edge computing and edge-service collaborative services. The edge detection device developed an edge computing model based on data preprocessing algorithm and transformer fault diagnosis in the Kylin operating system environment through Python, C, C++ and other languages, and built an edge-service collaborative service suitable for transformer fault diagnosis, which mainly includes the storage of edge computing results, the interaction of device data and service platform data, and the update of edge computing models.

[0099] The oil-gas separation module is connected to the transformer tank to separate the oil and gas in the transformer tank. The sample gas is used as the dissolved gas in the transformer oil and is connected to the photoacoustic spectrum detection sensor through the air inlet valve and the air outlet valve. The edge detection device controls the photoacoustic spectrum detection sensor to detect the photoacoustic signal of the sample gas. The transformer fault diagnosis model running on the edge detection device is used to perform real-time fault diagnosis on the transformer at the edge end, and the calculation results are uploaded to the transformer fault diagnosis service platform. The transformer fault diagnosis service platform can be used to view the transformer status, manage the edge detection device and sensors, and update the edge computing model. The operation and maintenance personnel can view the status of the transformer through the mobile terminal. When the transformer fails, the alarm information can be sent to the operation and maintenance personnel, so that the operation and maintenance personnel can take preventive measures quickly.

[0100] In order to better illustrate the application of the transformer fault diagnosis method based on photoacoustic signal reconstruction sensitive field optimization described in the present invention, a simulation test is carried out for further explanation.

[0101] Table 1 Diagnostic results

[0102] Fault type Training set (feature vector) Test set (feature vector) Accuracy (Kc=10) Normal state 45 8 7 / 8 High Energy Discharge 60 7 7 / 7 Low energy discharge 60 7 7 / 7 Partial Discharge 50 7 7 / 7 High temperature overheating 40 7 6 / 7 total 255 36 94.44％

[0103] It can be seen from Table 1 that the accuracy of the transformer fault diagnosis method based on the optimization of the sensitive field reconstructed by photoacoustic signals is 92.3%. After the edge detection device diagnoses the transformer fault, it sends the diagnosis results to the transformer status monitoring cloud platform, which is convenient for the operation and maintenance personnel to view the status of the transformer in real time in the monitoring center.

[0104] Table 2 Comparison of diagnosis by different algorithms (Kc)

[0105] method Kc=5 Kc=8 Kc=10 Probabilistic Entropy-KNN 77.2％ 80.7％ 82.6％ Probabilistic Entropy-SVM 84.3％ 85.3％ 88.7％ Probabilistic Entropy-LSTM 86.2％ 81.5％ 91.9％ Probability Entropy-ALMMo-0 89.9％ 92.7％ 94.4％

[0106] It can be seen from Table 2 that when Kc=10, each method achieves the best performance and the method of the present invention has the highest accuracy.

[0107] As attached Figure 2 As shown, it can be seen that the sensitive field images reconstructed from the photoacoustic signals collected from different faults are quite different and suitable for subsequent feature recognition.

[0108] As attached Figure 3 As shown, it can be seen that by clustering the feature points, a cluster of Kc=5 is obtained.

[0109] As attached Figure 4 As shown, the transformer fault diagnosis system based on photoacoustic signal reconstruction sensitive field optimization includes:

[0110] Oil-gas separation module, photoacoustic spectroscopy detection sensor, edge detection device, and transformer fault diagnosis service platform.

[0111] The edge detection device adopts a modular design, and the hardware specifically includes a communication unit, a main control unit, a positioning unit, a power supply unit, and a storage unit. The communication unit supports wireless communications of WiFi and 4G, mainly realizing communication with the transformer fault diagnosis service platform, and supports RS232 and RS485 wired communications, mainly realizing data communication with the photoacoustic spectroscopy detection sensor. The main control unit contains the FPGA+D2000-CPU of V7-690T, and the positioning unit mainly realizes the position positioning of the edge detection device, supporting GPS and Beidou positioning. The power supply unit provides power to each module and unit of the device, and realizes functions such as charging and power detection of the backup battery. The storage unit supports SD card or SSD hard disk expansion, which is convenient for storing historical data on the edge side.

[0112] The software design includes: operating system, language environment, data preprocessing, edge computing and edge-service collaborative services. The edge detection device developed an edge computing model based on data preprocessing algorithm and transformer fault diagnosis in the Kylin operating system environment through Python, C, C++ and other languages, and built an edge-service collaborative service suitable for transformer fault diagnosis, which mainly includes the storage of edge computing results, the interaction of device data and service platform data, and the update of edge computing models.

[0113] The oil-gas separation module is connected to the transformer tank to separate the oil and gas in the transformer tank. The sample gas is used as the dissolved gas in the transformer oil and is connected to the photoacoustic spectrum detection sensor through the air inlet valve and the air outlet valve. The edge detection device controls the photoacoustic spectrum detection sensor to detect the photoacoustic signal of the sample gas. The transformer fault diagnosis model running on the edge detection device is used to perform real-time fault diagnosis on the transformer at the edge end, and the calculation results are uploaded to the transformer fault diagnosis service platform. The transformer fault diagnosis service platform can be used to view the transformer status, manage the edge detection device and sensors, and update the edge computing model. The operation and maintenance personnel can view the status of the transformer through the mobile terminal. When the transformer fails, the alarm information can be sent to the operation and maintenance personnel, so that the operation and maintenance personnel can take preventive measures quickly.

Claims

1. A transformer fault diagnosis method based on photoacoustic signal reconstruction sensitive field optimization, characterized in that: The steps include: Step 1: By monitoring the photoacoustic signals of multiple gases in the transformer oil sample, the multivariate sequence matrix V of the signal is obtained M N , where M is the number of gas types and N is the length of the sequence sample; Step 2: By reconstructing the idea of ​​sensitive field, the multivariate sequence matrix V M N Mapped in polar coordinates in the form of scattered points; Step 3: Extract shallow local features, including SURF features and FAST features, and cluster these features into multiple mutually exclusive categories. The shortest probability entropy of the center of each category is used as a visual representation factor to form a visual feature vector. Step 4: Based on the improved autonomous learning multi-space (ALMMo-0) classifier, the formed visual feature vector is trained and classified to achieve the classification of transformer fault diagnosis.

2. The transformer fault diagnosis method based on photoacoustic signal reconstruction sensitive field optimization according to claim 1 is characterized in that: The step 1 specifically includes: The dissolved gas in the oil sample is extracted through the oil-gas separation module to form a gas sample, and the gas sample is irradiated with a modulated laser at a specific wavelength or band to cause a slight change in local temperature and pressure, generating a sound wave signal sequence, and then forming a multivariate sequence matrix V M N .

3. The transformer fault diagnosis method based on photoacoustic signal reconstruction sensitive field optimization according to claim 1 is characterized in that: The idea of ​​reconstructing the sensitive field in step 2 specifically includes: Define x max and x min V i N , i=1,2,…,the maximum and minimum values ​​of M. For each time point i, the corresponding amplitude is x i , hysteresis coefficient a, angular offset θ l , amplification factor ζ, where l ranges from 0 to L-1, and L represents the number of planes in the total sensitive field; The points in the multivariate signal matrix are converted into polar coordinates through a specific reconstruction relationship formula to form a reconstructed sensitive field image. The reconstruction relationship is as follows: The polar radius r(i) is expressed as: The angular offset θ(i) is defined as: The reflection angle φ(i) is defined as: Angular offset θ l Defined as:

4. The transformer fault diagnosis method based on photoacoustic signal reconstruction sensitive field optimization according to claim 1 is characterized in that: The specific method for extracting shallow local features in step 3 is as follows: S3.1 uses SURF features and FAST features to extract two shallow features; S3.2 uses Kmeans++ to cluster the two shallow features into Kc clusters and calculates the shortest probability entropy P(G) of each cluster. The formula is as follows: Among them, G is the cluster index, g is the feature point index in the Gth cluster, and D min is the shortest distance between the feature point and the cluster center within the cluster, and D(g) is the distance between the g-th feature point and the cluster center; S3.3 takes the shortest probability entropy P(G) of each cluster as the characterization factor of the cluster center and encodes the shallow features into a feature vector with a dimension of 1*Kc.

5. The transformer fault diagnosis method based on photoacoustic signal reconstruction sensitive field optimization according to claim 1 is characterized in that: In step 4, the autonomous learning multi-space (ALMMo-0) classifier calculates the similarity between the input feature vector and each subspace, assigns the input sample to the fault category with the greatest similarity, and performs the next round of training until the training is completed.

6. The transformer fault diagnosis method based on photoacoustic signal reconstruction sensitive field optimization according to claim 1 is characterized in that: The specific steps of step 4 are: S4.1 Define {g1,g2,g3,...,g τ } is the feature vector set with a dimension of 1*Kc and is used as the training data set. The number of transformer fault categories is set to q, that is, the number of subspaces, and each subspace corresponds to a set of feature classes. First, we select individual eigenvectors to form a preliminary set of subspaces. In the training phase, {g1,g2,g3,...,g τ The single feature vectors of the set are input into the autonomous learning multi-space (ALMMo-0) classifier for training. τ The similarity between it and each subspace is calculated according to the following formula. in is the average value of all eigenvectors in the i-th subspace, is the average scalar product of the ith subspace, τ is the sample index of the eigenvector set, ‖‖ is the norm calculation, and g ini is a single eigenvector of the preliminary set. S4.2 For input sample g τ , the classifier will calculate q R(g i τ ) is the value of g τ Distribution and maximum R(g i τ ) and fill it into the corresponding subspace for the next round of training. After the training is completed, the feature vector of the collected samples can be tested in real time; the allocation result can be expressed as: Class i =argmax i＝1,2,3,...,q (R i τ )。 7. A transformer fault diagnosis system based on photoacoustic signal reconstruction and sensitive field optimization, characterized in that: include: Oil-gas separation module, used to extract oil samples from transformer tanks and separate dissolved gases; A photoacoustic spectrum detection sensor, used to detect the photoacoustic signal of the sample gas; An edge detection device for controlling the photoacoustic spectroscopy detection sensor, processing data and executing a fault diagnosis model; The transformer fault diagnosis service platform is used to receive the fault diagnosis results uploaded by the edge detection device and provide transformer status viewing, equipment management, and model update functions.

8. The transformer fault diagnosis system based on photoacoustic signal reconstruction and sensitive field optimization according to claim 7 is characterized in that: The hardware system of the edge detection device includes a communication unit, a main control unit, a positioning unit, a power supply unit and a storage unit, wherein the communication unit supports wireless communication of WiFi and 4G, mainly realizing communication with the transformer fault diagnosis service platform, and supports RS232 and RS485 wired communication, mainly realizing data communication with the photoacoustic spectroscopy detection sensor; the main control unit includes a V7-690T FPGA+D2000-CPU, and the positioning unit mainly realizes the position positioning of the edge detection device, supporting GPS and Beidou positioning. The power supply unit provides power to each module and unit of the device, and realizes functions such as charging and power detection of the backup battery. The storage unit supports SD card or SSD hard disk expansion, which is convenient for storing historical data on the edge side. The software design of the edge detection device includes an operating system, a language environment, data preprocessing, edge computing, and edge-server collaborative services, which enable real-time fault diagnosis of the transformer at the edge and upload the results to a transformer fault diagnosis service platform.

9. The transformer fault diagnosis system based on photoacoustic signal reconstruction and sensitive field optimization according to claim 7 is characterized in that: The oil-gas separation module is connected to the transformer oil tank to separate the oil and gas in the transformer oil tank as sample gas of the dissolved gas in the transformer oil, and is connected to the photoacoustic spectrum detection sensor through the air inlet valve and the air outlet valve. The edge detection device controls the photoacoustic spectrum detection sensor to detect the photoacoustic signal of the sample gas. The transformer fault diagnosis model running on the edge detection device is used to perform real-time fault diagnosis on the transformer at the edge end, and the calculation results are uploaded to the transformer fault diagnosis service platform. The transformer fault diagnosis service platform can be used to view the transformer status, manage the edge detection device and sensors, and update the edge computing model. The operation and maintenance personnel can view the status of the transformer through the mobile terminal, and when the transformer fails, the alarm information can be sent to the operation and maintenance personnel, so that the operation and maintenance personnel can quickly take preventive measures.

Images