Transformer winding deformation monitoring method and system based on artificial intelligence

Abstract

The invention discloses a transformer winding deformation monitoring method and system based on artificial intelligence, and belongs to the technical field of deformation monitoring, and the method comprises the steps: data collection, signal data processing, building of a transformer winding deformation monitoring model, and real-time deformation monitoring. According to the scheme, an IMF component is selected based on the contribution degree to carry out wavelet transformation, a guide value and an updating strategy are designed to search threshold values, the optimal threshold value of each wavelet coefficient is found, an adjustment coefficient is introduced to design a threshold value processing function, and threshold value processing is carried out on each wavelet coefficient based on the optimal threshold value; the method comprises the following steps: screening and deleting majority class nodes based on reference nodes, generating new nodes for minority class nodes based on auxiliary nodes and balance factors and calculating embedding, setting weights of new node edges according to correlation degrees, and performing multi-layer updating on node embedding based on a node embedding matrix and a new adjacent matrix, thereby improving the quality of transformer winding signals. And the timeliness and reliability of winding deformation monitoring are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of deformation monitoring, and specifically refers to a transformer winding deformation monitoring method and system based on artificial intelligence. Background Art

[0002] The transformer winding deformation monitoring method uses advanced artificial intelligence technology to analyze and process the transformer winding signal data in real time, realize accurate monitoring of the transformer winding deformation state, ensure the safe and stable operation of the transformer, and reduce the risk of failure. However, the existing transformer winding deformation monitoring method has the problem that the transformer operation will be interfered by various electromagnetic signals, the collected transformer winding signal data has a lot of noise, and the winding signal itself is relatively complex and contains multiple components, which makes it difficult to accurately analyze and timely and accurately detect the problem of winding deformation; the existing transformer winding deformation monitoring method has the problem that the transformer winding deformation is complex and diverse, the data has a complex nonlinear relationship, and there is an imbalance in the various data types, making it difficult to comprehensively and accurately analyze the characteristics of the transformer winding signal data, resulting in misjudgment of transformer winding deformation and the inability to timely detect hidden deformation. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a transformer winding deformation monitoring method and system based on artificial intelligence. In view of the existing transformer winding deformation monitoring method, the transformer operation will be interfered by various electromagnetic signals, the collected transformer winding signal data contains a lot of noise, and the winding signal itself is relatively complex and contains multiple components, which makes it difficult to accurately analyze and cannot timely and accurately detect the problem of winding deformation. This scheme decomposes the transformer winding signal data, selects IMF components based on contribution to perform wavelet transform, and accurately selects low-contribution IMF components with high noise content; designs guiding values ​​and update strategies to search for thresholds, finds the optimal threshold for each wavelet coefficient, introduces adjustment coefficients to design threshold processing functions, performs threshold processing on each wavelet coefficient based on the optimal threshold, finds the optimal threshold to effectively remove the noise in the wavelet coefficient, better adapts to the noise removal needs of different situations, and improves the transformer winding. The quality of the signal is improved to enhance the reliability of winding deformation monitoring; the existing transformer winding deformation monitoring methods have complex and diverse transformer winding deformation conditions, complex nonlinear relationships in the data, and imbalances in various data types, making it difficult to conduct a comprehensive and accurate analysis of the characteristics of the transformer winding signal data, resulting in misjudgment of transformer winding deformation and failure to timely discover hidden deformation conditions. This scheme calculates embedding based on node attribute data, and screens and deletes majority class nodes based on reference nodes to avoid missing important deformations due to majority class masking; generates new nodes for minority class nodes based on auxiliary nodes and balance factors and calculates embedding to enhance the expression of minority class deformations; sets the weight of the new node edge according to the correlation to more reasonably reflect the actual connection between the winding deformation data; performs multi-layer updates on the node embedding based on the node embedding matrix and the new adjacency matrix to ensure that hidden deformation conditions can be discovered in a timely manner, thereby improving the timeliness and reliability of monitoring.

[0004] The technical solution adopted by the present invention is as follows: The present invention provides a transformer winding deformation monitoring method based on artificial intelligence, the method comprising the following steps:

[0005] Step S1: data collection;

[0006] Step S2: signal data processing;

[0007] Step S3: constructing a transformer winding deformation monitoring model;

[0008] Step S4: Real-time deformation monitoring.

[0009] Furthermore, in step S1, the data collection is to collect historical transformer winding signal data; the historical transformer winding signal data includes current signal data, voltage signal data, vibration signal data, temperature signal data, acoustic wave signal data, timestamp and winding status; the winding status is used as a data label.

[0010] Furthermore, in step S2, the signal data processing specifically includes the following steps:

[0011] Step S21: Decomposition: using an improved adaptive noise complete set empirical mode decomposition method ICEEMDAN to perform empirical mode decomposition on the collected transformer winding signal data to obtain N IMF components and residual components;

[0012] Step S22: Calculate the contribution. Calculate the contribution of the IMF component based on the energy of each component. Preset the contribution threshold. The formula used is as follows:

[0013] ;

[0014] ;

[0015] In the formula, E i is the energy of the ith component, c i is the ith component, is the energy of the jth IMF component, is the contribution of the jth IMF component;

[0016] Step S23: Component processing: performing wavelet transform on the IMF components whose contribution is less than the contribution threshold, using the wavelet basis of db6 and the wavelet layer number of 5 to obtain wavelet coefficients;

[0017] Step S24: searching for the best threshold, applying the threshold function to the wavelet coefficients for denoising, searching for the threshold, and finding the best threshold for each wavelet coefficient, including the following:

[0018] Step S241: Initial position, establish a search space based on the threshold of each wavelet coefficient, randomly initialize individual positions in the search space, use the individual positions as representatives of the threshold, and use the signal-to-noise ratio of the wavelet coefficients after threshold processing as the fitness value of the corresponding individual position;

[0019] Step S242: Design the guide value, and calculate the guide value based on the best fitness value in each iteration. The formula used is as follows:

[0020] ;

[0021] Where D t is the bootstrap value at the tth iteration, and are the best fitness values ​​at the t-1th and t-2th iterations, respectively. is rounded down, θ t is a dynamically adjusted benchmark. , exp(·) is the exponential function;

[0022] Step S243: Design an update strategy, sort the individual positions in descending order according to the size of the fitness value, select the top 10% of the individual positions as the elite individual positions, and randomly generate a random number in the range of (0, 1) for each individual position, compare the size of the random number and the guide value, select the update strategy of the individual position, and complete the update of the individual position. The formula used is as follows:

[0023] ;

[0024] In the formula, and are the positions of the bth individual at the t+1th and tth iterations, β1 and β2 are the first and second guidance factors, γ is the dynamic factor, is the Euclidean distance between the global best position and the bth individual position at the tth iteration, is the global optimal position at the tth iteration, is the Euclidean distance between a random elite individual position and the bth individual position at the tth iteration, is the position of the random elite individual at the tth iteration, is the random number of the bth individual position at the tth iteration, is the Euclidean distance between a random individual position and the bth individual position at the tth iteration, is the random individual position at the tth iteration, is the Hadamard product, o is a constant, I is a d-dimensional uniform random vector, and d is the dimension of the individual position;

[0025] Step S244: Determine the optimal threshold, pre-set the fitness threshold and the maximum number of iterations, update the fitness value of the individual position, and when the optimal fitness value is higher than the fitness threshold, use the threshold represented by the global optimal position as the optimal threshold; otherwise, if the maximum number of iterations is reached, set the number of iterations to 0 and return to step S241; otherwise, add 1 to the number of iterations and return to step S242 to continue iterating;

[0026] Step S25: Denoising, introducing the adjustment coefficient to design the threshold processing function, performing threshold processing on each wavelet coefficient based on the optimal threshold to remove noise, the formula used is as follows:

[0027] ;

[0028] In the formula, x a and are the ath original wavelet coefficient and the wavelet coefficient after threshold processing, δ and μ are the first adjustment coefficient and the second adjustment coefficient, respectively. ais the optimal threshold of the ath wavelet coefficient;

[0029] Step S26: feature extraction, performing inverse wavelet transform on the denoised wavelet coefficients to obtain processed IMF components, combining and superimposing the processed IMF components, unprocessed IMF components and residual components to obtain denoised transformer winding signal data, extracting time domain features and frequency domain features from the denoised transformer winding signal data, and constructing a monitoring data set in combination with data labels; and dividing the feature data in the monitoring data set into majority class data and minority class data.

[0030] Furthermore, in step S3, the construction of the transformer winding deformation monitoring model specifically includes the following steps:

[0031] Step S31: Initialize the graph structure, generate a node for each feature data in the monitoring data set, and use each feature data as the attribute data of the corresponding node to obtain a node set and a node attribute matrix; pre-set a connection threshold, if the Euclidean distance between the attribute data of two nodes is less than the connection threshold, there is an edge between the two nodes, and the weight of the edge is 1; otherwise, there is no edge between the corresponding two nodes, and the weight of the edge is 0; construct an adjacency matrix G based on the weight of the edge; if the feature data corresponding to the node is majority class data, the node is a majority class node, otherwise it is a minority class node;

[0032] Step S32: Calculate the embedding of the node, using the following formula:

[0033] ;

[0034] In the formula, is the embedding of the vth node, W 1 is the first weight matrix, σ(·) is the activation function, CONCAT(·) is the connection function, M is the node attribute matrix, is the attribute data of the vth node, is the vth column of the adjacency matrix G;

[0035] Step S33: Node processing, including the following steps:

[0036] Step S331: majority class node processing, calculate the Euclidean distance between each majority class node and the attribute data of the remaining nodes, and select the first k nodes with the smallest Euclidean distance as reference nodes; if Among the k reference nodes, The number of nodes belonging to the same data label is greater than or equal to , then the majority class nodes Delete from the node set and delete the corresponding edge; where, is the nth majority class node;

[0037] Step S332: Minority node processing: find the node with the shortest Euclidean distance to each minority node and belonging to the same data label, use it as an auxiliary node, generate a new node for each minority node based on the auxiliary node, add the new node to the node set, and obtain the node embedding matrix F. The formula used is as follows:

[0038] ;

[0039] In the formula, is the embedding of the new node generated by the u-th minority class node, is the embedding of the u-th minority class node, is the embedding of the auxiliary node corresponding to the u-th minority class node, and α is the balancing factor;

[0040] Step S34: Edge processing, calculating each new node B r With the rest of the Node B p The correlation between them is pre-set with a correlation threshold. If the correlation is greater than the correlation threshold, the new node B r With the rest of the Node B p There is an edge between the two nodes, and the weight of the edge is 1; otherwise, there is no edge between the two nodes, and the weight of the edge is 0; and a new adjacency matrix is ​​obtained , the formula used is as follows:

[0041] ;

[0042] In the formula, It is B r and B p The correlation between r and B p are the rth new node and the pth node in the node set, respectively. and B r and B p The embedding of W 2 is the second weight matrix;

[0043] Step S35: Embedding update based on the node embedding matrix F and the new adjacency matrix , perform Z1 layer update on the node embedding, the formula used is as follows:

[0044] ;

[0045] In the formula, and are the embeddings of the p-th node in the node set at the z+1th layer and the z-th layer, respectively. is the new adjacency matrix The pth column, W z+1 is the weight matrix of the z+1th layer;

[0046] Step S36: Monitoring, normalizing the embedding of the Z1th layer nodes based on the softmax function to obtain the probability distribution corresponding to each data label, and selecting the data label with the largest probability as the monitoring output of the transformer winding deformation monitoring model for the node.

[0047] Furthermore, in step S4, the real-time deformation monitoring is to collect real-time transformer winding signal data; the real-time transformer winding signal data includes current signal data, voltage signal data, vibration signal data, temperature signal data, sound wave signal data and timestamp, and after signal data processing, it is input into the transformer winding deformation monitoring model for analysis, and the real-time status of the transformer winding is obtained based on the output data label.

[0048] The present invention provides a transformer winding deformation monitoring system based on artificial intelligence, comprising a data acquisition module, a signal data processing module, a transformer winding deformation monitoring model building module and a real-time deformation monitoring module;

[0049] The data acquisition module collects historical transformer winding signal data and sends the data to the signal data processing module;

[0050] The signal data processing module decomposes the transformer winding signal data, selects the IMF component based on the contribution to perform wavelet transform, obtains the wavelet coefficient, designs the guide value and the update strategy to search the threshold, finds the optimal threshold of each wavelet coefficient, introduces the adjustment coefficient to design the threshold processing function, performs threshold processing on each wavelet coefficient based on the optimal threshold, extracts features and constructs a monitoring data set, and sends the data to the module for constructing the transformer winding deformation monitoring model;

[0051] The transformer winding deformation monitoring model building module calculates embedding according to node attribute data, screens and deletes majority class nodes based on reference nodes, generates new nodes for minority class nodes based on auxiliary nodes and balance factors and calculates embedding, sets weights of new node edges according to association, performs multi-layer update of node embedding based on node embedding matrix and new adjacency matrix, outputs data labels, and sends data to the real-time deformation monitoring module;

[0052] The real-time deformation monitoring module collects real-time transformer winding signal data, processes the signal data, and then inputs the data into the transformer winding deformation monitoring model for analysis to obtain the real-time status of the transformer winding.

[0053] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0054] (1) In view of the existing transformer winding deformation monitoring methods, the transformer operation will be disturbed by various electromagnetic signals, the collected transformer winding signal data contains a lot of noise, and the winding signal itself is relatively complex and contains multiple components, which makes it difficult to accurately analyze and timely and accurately detect the problem of winding deformation. This scheme decomposes the transformer winding signal data and can effectively separate the IMF components and residual components with different characteristics; selects the IMF components based on the contribution to perform wavelet transform to obtain the wavelet coefficients, and accurately selects the low-contribution IMF components with high noise content; designs the guide value and update strategy to search the threshold to find the optimal threshold for each wavelet coefficient, introduces the adjustment coefficient to design the threshold processing function, performs threshold processing on each wavelet coefficient based on the optimal threshold, extracts features and constructs the monitoring data set, and finds the optimal threshold to effectively remove the noise in the wavelet coefficients, thereby improving the purity of the data and reducing noise interference. At the same time, it makes the threshold processing more flexible and accurate, better adapts to the noise removal needs of different situations, improves the quality of the transformer winding signal, and enhances the reliability of winding deformation monitoring.

[0055] (2) In view of the existing transformer winding deformation monitoring methods, the transformer winding deformation is complex and diverse, the data has complex nonlinear relationships, and there is an imbalance in the data types. It is difficult to comprehensively and accurately analyze the characteristics of the transformer winding signal data, which leads to misjudgment of the transformer winding deformation and failure to timely discover hidden deformation conditions. This scheme calculates embedding based on node attribute data, converts complex winding deformation features into processable embedding vectors, and can better capture various deformation features; based on the reference node, the majority class nodes are screened and deleted, and the relationship between nodes is more accurately identified to avoid missing important deformations due to majority class masking. shape; based on the auxiliary nodes and balance factors, new nodes are generated for the minority class nodes and the embedding is calculated to enhance the expression ability of the minority class deformation, so that the model can effectively monitor the less common but critical deformation conditions, and improve the sensitivity and comprehensiveness of the monitoring; the weights of the new node edges are set according to the correlation degree, which can more reasonably reflect the actual connection between the winding deformation data and improve the understanding of complex deformation relationships and the monitoring effect; based on the node embedding matrix and the new adjacency matrix, the node embedding is updated in multiple layers, and the data labels are output, so as to continuously improve the analysis ability and accuracy of the winding deformation, ensure that the hidden deformation conditions can be discovered in time, and improve the timeliness and reliability of the monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A schematic flow chart of a transformer winding deformation monitoring method based on artificial intelligence provided by the present invention;

[0057] Figure 2 A schematic diagram of a transformer winding deformation monitoring system based on artificial intelligence provided by the present invention;

[0058] Figure 3 is a schematic flow chart of step S2;

[0059] Figure 4 It is a schematic diagram of the process of step S3.

[0060] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0062] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0063] Example 1, see Figure 1 The present invention provides a transformer winding deformation monitoring method based on artificial intelligence, the method comprising the following steps:

[0064] Step S1: data collection, collecting historical transformer winding signal data;

[0065] Step S2: Signal data processing, decomposing transformer winding signal data, selecting IMF components based on contribution for wavelet transform, obtaining wavelet coefficients, designing guide values ​​and update strategies to search thresholds, finding the best threshold for each wavelet coefficient, introducing adjustment coefficients to design threshold processing functions, performing threshold processing on each wavelet coefficient based on the best threshold, extracting features and constructing a monitoring data set;

[0066] Step S3: construct a transformer winding deformation monitoring model, calculate embedding according to node attribute data, filter and delete majority class nodes based on reference nodes, generate new nodes for minority class nodes based on auxiliary nodes and balance factors and calculate embedding, set the weight of the new node edge according to the association degree, perform multi-layer update on node embedding based on node embedding matrix and new adjacency matrix, and output data labels;

[0067] Step S4: real-time deformation monitoring, collecting real-time transformer winding signal data, processing the signal data, and inputting it into the transformer winding deformation monitoring model for analysis to obtain the real-time status of the transformer winding.

[0068] Example 2, see Figure 1 This embodiment is based on the above embodiment. In step S1, the historical transformer winding signal data includes current signal data, voltage signal data, vibration signal data, temperature signal data, acoustic signal data, timestamp and winding status; the winding status includes normal, slight deformation, moderate deformation and severe deformation, and the winding status is used as a data label.

[0069] Example 3, see Figure 1 and Figure 3 This embodiment is based on the above embodiment. In step S2, the signal data processing specifically includes the following steps:

[0070] Step S21: Decomposition, using the improved adaptive noise complete set empirical mode decomposition method ICEEMDAN to perform empirical mode decomposition on the collected transformer winding signal data to obtain N IMF components and residual components; more finely analyze the different frequency components and characteristics of the signal;

[0071] Step S22: Calculate the contribution. Calculate the contribution of the IMF component based on the energy of each component. Preset the contribution threshold. The formula used is as follows:

[0072] ;

[0073] ;

[0074] In the formula, E i is the energy of the ith component, c i is the ith component, is the energy of the jth IMF component, is the contribution of the jth IMF component;

[0075] Step S23: Component processing: performing wavelet transform on the IMF components whose contribution is less than the contribution threshold, using the wavelet basis of db6 and the wavelet layer number of 5 to obtain wavelet coefficients;

[0076] Step S24: searching for the best threshold, applying the threshold function to the wavelet coefficients for denoising, searching for the threshold, finding the best threshold for each wavelet coefficient, and improving the denoising effect and adaptability; including the following contents:

[0077] Step S241: Initial position, establish a search space based on the threshold of each wavelet coefficient, randomly initialize individual positions in the search space, use the individual positions as representatives of the threshold, and use the signal-to-noise ratio of the wavelet coefficients after threshold processing as the fitness value of the corresponding individual position;

[0078] Step S242: Design the guide value, and calculate the guide value based on the best fitness value in each iteration. The formula used is as follows:

[0079] ;

[0080] Where D t is the bootstrap value at the tth iteration, and are the best fitness values ​​at the t-1th and t-2th iterations respectively. The best fitness value is the maximum fitness value. is rounded down, θ t is a dynamically adjusted benchmark. , exp(·) is the exponential function;

[0081] Step S243: Design an update strategy, sort the individual positions in descending order according to the size of the fitness value, select the top 10% of the individual positions as the elite individual positions, and randomly generate a random number in the range of (0, 1) for each individual position, compare the size of the random number and the guide value, select the update strategy of the individual position, and complete the update of the individual position. The formula used is as follows:

[0082] ;

[0083] In the formula, and are the positions of the bth individual at the t+1th and tth iterations, β1 and β2 are the first and second guidance factors in the range of (0.5, 1], γ is the dynamic factor in the range of (0.8, 1], is the Euclidean distance between the global best position and the bth individual position at the tth iteration, is the global best position at the tth iteration. The global best position is the individual position with the best fitness value. is the Euclidean distance between a random elite individual position and the bth individual position at the tth iteration, is the position of the random elite individual at the tth iteration, is the random number of the bth individual position at the tth iteration, is the Euclidean distance between a random individual position and the bth individual position at the tth iteration, is the random individual position at the tth iteration, is the Hadamard product, o is a constant in the range (0, 1), and I is A d-dimensional uniform random vector in the range, where d is the dimension of the individual position;

[0084] Step S244: Determine the optimal threshold, pre-set the fitness threshold and the maximum number of iterations, update the fitness value of the individual position, and when the optimal fitness value is higher than the fitness threshold, use the threshold represented by the global optimal position as the optimal threshold; otherwise, if the maximum number of iterations is reached, set the number of iterations to 0 and return to step S241; otherwise, add 1 to the number of iterations and return to step S242 to continue iterating;

[0085] Step S25: Denoising, introducing the adjustment coefficient to design the threshold processing function, performing threshold processing on each wavelet coefficient based on the optimal threshold to remove noise, the formula used is as follows:

[0086] ;

[0087] In the formula, x a and are the ath original wavelet coefficient and the wavelet coefficient after threshold processing, δ and μ are the first adjustment coefficient and the second adjustment coefficient, respectively. a is the optimal threshold of the ath wavelet coefficient;

[0088] Step S26: feature extraction, performing inverse wavelet transform on the denoised wavelet coefficients to obtain processed IMF components, combining and superimposing the processed IMF components, unprocessed IMF components and residual components to obtain denoised transformer winding signal data, extracting time domain features and frequency domain features from the denoised transformer winding signal data, and constructing a monitoring data set in combination with data labels; and dividing the feature data in the monitoring data set into majority class data and minority class data.

[0089] By performing the above operations, the existing transformer winding deformation monitoring method has the problem that the transformer operation will be disturbed by various electromagnetic signals, the collected transformer winding signal data has a lot of noise, and the winding signal itself is relatively complex and contains multiple components, which makes it difficult to accurately analyze and timely and accurately detect the problem of winding deformation. This scheme decomposes the transformer winding signal data, which can effectively separate the IMF components and residual components with different characteristics; selects the IMF components based on the contribution to perform wavelet transform, obtains the wavelet coefficients, and accurately selects the low-contribution IMF components with high noise content; designs the guide value and update strategy to search the threshold, finds the best threshold for each wavelet coefficient, introduces the adjustment coefficient to design the threshold processing function, performs threshold processing on each wavelet coefficient based on the best threshold, extracts features and constructs the monitoring data set, finds the optimal threshold to effectively remove the noise in the wavelet coefficient, improves the purity of the data, reduces noise interference, and makes the threshold processing more flexible and accurate, better adapts to the noise removal needs of different situations, improves the quality of the transformer winding signal, and enhances the reliability of winding deformation monitoring.

[0090] Example 4, see Figure 1 and Figure 4 Based on the above embodiment, in step S3, building a transformer winding deformation monitoring model specifically includes the following steps:

[0091] Step S31: Initialize the graph structure, generate a node for each feature data in the monitoring data set, and use each feature data as the attribute data of the corresponding node to obtain a node set and a node attribute matrix; pre-set a connection threshold, if the Euclidean distance between the attribute data of two nodes is less than the connection threshold, there is an edge between the two nodes, and the weight of the edge is 1; otherwise, there is no edge between the corresponding two nodes, and the weight of the edge is 0; construct an adjacency matrix G based on the weight of the edge; if the feature data corresponding to the node is majority class data, the node is a majority class node, otherwise it is a minority class node;

[0092] Step S32: Calculate the embedding of the node. Calculate the node embedding using node attributes and adjacency relationships to capture node features more comprehensively. The formula used is as follows:

[0093] ;

[0094] In the formula, is the embedding of the vth node, W 1 is the first weight matrix, σ(·) is the ReLU activation function, CONCAT(·) is the connection function, M is the node attribute matrix, is the attribute data of the vth node, is the vth column of the adjacency matrix G;

[0095] Step S33: Node processing, including the following steps:

[0096] Step S331: majority class node processing, calculate the Euclidean distance between each majority class node and the attribute data of the remaining nodes, and select the first k nodes with the smallest Euclidean distance as reference nodes; if Among the k reference nodes, The number of nodes belonging to the same data label is greater than or equal to , then the majority class nodes Delete from the node set and delete the corresponding edge; where, It is the nth majority class node; it avoids the excessive influence of majority class nodes on deformation monitoring and improves the efficiency and accuracy of monitoring;

[0097] Step S332: Minority class node processing, find the node with the closest Euclidean distance to each minority class node and belonging to the same data label, use it as an auxiliary node, generate a new node for each minority class node based on the auxiliary node, add the new node to the node set, and obtain the node embedding matrix F, which enhances the attention to minority class information and improves the comprehensiveness of monitoring; the formula used is as follows:

[0098] ;

[0099] In the formula, is the embedding of the new node generated by the u-th minority class node, is the embedding of the u-th minority class node, is the embedding of the auxiliary node corresponding to the u-th minority class node, and α is a balancing factor in the range [0, 1];

[0100] Step S34: Edge processing, calculating each new node B r With the rest of the Node B p The correlation between them is pre-set with a correlation threshold. If the correlation is greater than the correlation threshold, the new node B r With the rest of the Node B p There is an edge between the two nodes, and the weight of the edge is 1; otherwise, there is no edge between the two nodes, and the weight of the edge is 0; and a new adjacency matrix is ​​obtained , which realizes the fine control of the relationship between nodes and improves the flexibility and adaptability of monitoring; the formula used is as follows:

[0101] ;

[0102] In the formula, It is B r and B p The correlation between r and Bp are the rth new node and the pth node in the node set, respectively. and B r and B p The embedding of W 2 is the second weight matrix;

[0103] Step S35: Embedding update based on the node embedding matrix F and the new adjacency matrix , the embedding of the node is updated at the Z1 level, which improves the timeliness and accuracy of monitoring; the formula used is as follows:

[0104] ;

[0105] In the formula, and are the embeddings of the p-th node in the node set at the z+1th layer and the z-th layer, respectively. is the new adjacency matrix The pth column, W z+1 is the weight matrix of the z+1th layer;

[0106] Step S36: Monitoring, normalizing the embedding of the Z1th layer nodes based on the softmax function to obtain the probability distribution corresponding to each data label, and selecting the data label with the largest probability as the monitoring output of the transformer winding deformation monitoring model for the node.

[0107] By performing the above operations, the existing transformer winding deformation monitoring methods have complex and diverse transformer winding deformation conditions, complex nonlinear relationships in the data, and imbalances in the data types, making it difficult to comprehensively and accurately analyze the characteristics of the transformer winding signal data, resulting in misjudgment of transformer winding deformation and failure to timely discover hidden deformation conditions. This solution calculates embedding based on node attribute data, converts complex winding deformation features into processable embedding vectors, and can better capture various deformation features; based on the reference nodes, the majority class nodes are screened and deleted, and the relationship between nodes is more accurately identified to avoid omissions due to majority class masking. Important deformations; based on auxiliary nodes and balance factors, new nodes are generated for minority class nodes and embedding is calculated to enhance the expression ability of minority class deformations, so that the model can effectively monitor less common but critical deformations, and improve the sensitivity and comprehensiveness of monitoring; the weights of new node edges are set according to the correlation degree, which can more reasonably reflect the actual connection between winding deformation data and improve the understanding of complex deformation relationships and monitoring effects; based on the node embedding matrix and the new adjacency matrix, the node embedding is updated in multiple layers, and data labels are output, so as to continuously improve the analysis ability and accuracy of winding deformation, ensure that hidden deformations can be discovered in time, and improve the timeliness and reliability of monitoring.

[0108] Example 5, see Figure 1 This embodiment is based on the above embodiment. In step S4, real-time deformation monitoring is to collect real-time transformer winding signal data; the real-time transformer winding signal data includes current signal data, voltage signal data, vibration signal data, temperature signal data, sound wave signal data and timestamp. After signal data processing, it is input into the transformer winding deformation monitoring model for analysis. Based on the output data label, the real-time state of the transformer winding is obtained to complete the real-time deformation monitoring of the transformer winding.

[0109] Example 6, see Figure 2 , this embodiment is based on the above embodiment, and the present invention provides a transformer winding deformation monitoring system based on artificial intelligence, including a data acquisition module, a signal data processing module, a transformer winding deformation monitoring model construction module and a real-time deformation monitoring module;

[0110] The data acquisition module collects historical transformer winding signal data and sends the data to the signal data processing module;

[0111] The signal data processing module decomposes the transformer winding signal data, selects the IMF component based on the contribution to perform wavelet transform, obtains the wavelet coefficient, designs the guide value and the update strategy to search the threshold, finds the optimal threshold of each wavelet coefficient, introduces the adjustment coefficient to design the threshold processing function, performs threshold processing on each wavelet coefficient based on the optimal threshold, extracts features and constructs a monitoring data set, and sends the data to the module for constructing the transformer winding deformation monitoring model;

[0112] The transformer winding deformation monitoring model building module calculates embedding according to node attribute data, screens and deletes majority class nodes based on reference nodes, generates new nodes for minority class nodes based on auxiliary nodes and balance factors and calculates embedding, sets weights of new node edges according to association, performs multi-layer update of node embedding based on node embedding matrix and new adjacency matrix, outputs data labels, and sends data to the real-time deformation monitoring module;

[0113] The real-time deformation monitoring module collects real-time transformer winding signal data, processes the signal data, and then inputs the data into the transformer winding deformation monitoring model for analysis to obtain the real-time status of the transformer winding.

[0114] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0115] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0116] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A transformer winding deformation monitoring method based on artificial intelligence, characterized in that: The method comprises the following steps: Step S1: data collection, collecting historical transformer winding signal data; Step S2: signal data processing; Step S3: constructing a transformer winding deformation monitoring model; Step S4: real-time deformation monitoring, collecting real-time transformer winding signal data, processing the signal data, and inputting it into the transformer winding deformation monitoring model for analysis to obtain the real-time status of the transformer winding; Step S3 includes step S34: edge processing, calculating each new node B r With the rest of the Node B p The correlation between them is pre-set with a correlation threshold. If the correlation is greater than the correlation threshold, the new node B r With the rest of the Node B p There is an edge between the two nodes, and the weight of the edge is 1; otherwise, there is no edge between the two nodes, and the weight of the edge is 0; and a new adjacency matrix is ​​obtained , the formula used is as follows: ； In the formula, It is B r and B p The correlation between r and B p are the rth new node and the pth node in the node set, respectively. and B r and B p The embedding of W 2 is the second weight matrix and σ(•) is the activation function.

2. The transformer winding deformation monitoring method based on artificial intelligence according to claim 1 is characterized in that: In step S2, the signal data processing specifically includes the following steps: Step S21: Decomposition: using an improved adaptive noise complete set empirical mode decomposition method ICEEMDAN to perform empirical mode decomposition on the collected transformer winding signal data to obtain N IMF components and residual components; Step S22: Calculate the contribution. Calculate the contribution of the IMF component based on the energy of each component. Preset the contribution threshold. The formula used is as follows: ； ； In the formula, E i is the energy of the ith component, c i is the i-th component, is the energy of the jth IMF component, is the contribution of the jth IMF component; Step S23: Component processing: performing wavelet transform on the IMF components whose contribution is less than the contribution threshold, using the wavelet basis of db6 and the wavelet layer number of 5 to obtain wavelet coefficients; Step S24: searching for the best threshold, applying the threshold function to the wavelet coefficients for denoising, searching for the threshold, and finding the best threshold for each wavelet coefficient; Step S25: Denoising, introducing the adjustment coefficient to design the threshold processing function, performing threshold processing on each wavelet coefficient based on the optimal threshold to remove noise, the formula used is as follows: ； In the formula, x a and are the ath original wavelet coefficient and the wavelet coefficient after threshold processing, δ and μ are the first adjustment coefficient and the second adjustment coefficient, respectively. a is the optimal threshold of the ath wavelet coefficient; Step S26: feature extraction, performing inverse wavelet transform on the denoised wavelet coefficients to obtain processed IMF components, combining and superimposing the processed IMF components, unprocessed IMF components and residual components to obtain denoised transformer winding signal data, extracting time domain features and frequency domain features from the denoised transformer winding signal data, and constructing a monitoring data set in combination with data labels; and dividing the feature data in the monitoring data set into majority class data and minority class data.

3. The transformer winding deformation monitoring method based on artificial intelligence according to claim 2 is characterized in that: In step S24, the searching for the optimal threshold value specifically includes the following steps: Step S241: Initial position, establish a search space based on the threshold of each wavelet coefficient, randomly initialize individual positions in the search space, use the individual positions as representatives of the threshold, and use the signal-to-noise ratio of the wavelet coefficients after threshold processing as the fitness value of the corresponding individual position; Step S242: Design the guide value, and calculate the guide value based on the best fitness value in each iteration. The formula used is as follows: ； Where D t is the bootstrap value at the tth iteration, and are the best fitness values ​​at the t-1th and t-2th iterations, respectively. is rounded down, θ t is a dynamically adjusted benchmark. , exp(·) is the exponential function; Step S243: Design an update strategy, sort the individual positions in descending order according to the size of the fitness value, select the top 10% of the individual positions as the elite individual positions, and randomly generate a random number in the range of (0, 1) for each individual position, compare the size of the random number and the guide value, select the update strategy of the individual position, and complete the update of the individual position. The formula used is as follows: ； In the formula, and are the positions of the bth individual at the t+1th and tth iterations, β1 and β2 are the first and second guiding factors, γ is the dynamic factor, is the Euclidean distance between the global best position and the bth individual position at the tth iteration, is the global optimal position at the tth iteration, is the Euclidean distance between a random elite individual position and the bth individual position at the tth iteration, is the position of the random elite individual at the tth iteration, is the random number of the bth individual position at the tth iteration, is the Euclidean distance between a random individual position and the bth individual position at the tth iteration, is the random individual position at the tth iteration, is the Hadamard product, o is a constant, I is a d-dimensional uniform random vector, and d is the dimension of the individual position; Step S244: The optimal threshold is determined, the fitness threshold and the maximum number of iterations are pre-set, and the fitness value of the individual position is updated. When the optimal fitness value is higher than the fitness threshold, the threshold represented by the global optimal position is used as the optimal threshold; otherwise, if the maximum number of iterations is reached, the number of iterations is set to 0 and returns to step S241; otherwise, the number of iterations is increased by 1 and returns to step S242 to continue iterating.

4. The transformer winding deformation monitoring method based on artificial intelligence according to claim 1 is characterized in that: In step S3, the construction of the transformer winding deformation monitoring model specifically includes the following steps: Step S31: Initialize the graph structure, generate a node for each feature data in the monitoring data set, and use each feature data as the attribute data of the corresponding node to obtain a node set and a node attribute matrix; pre-set a connection threshold, if the Euclidean distance between the attribute data of two nodes is less than the connection threshold, there is an edge between the two nodes, and the weight of the edge is 1; otherwise, there is no edge between the corresponding two nodes, and the weight of the edge is 0; construct an adjacency matrix G based on the weight of the edge; if the feature data corresponding to the node is majority class data, the node is a majority class node, otherwise it is a minority class node; Step S32: Calculate the embedding of the node, using the following formula: ； In the formula, is the embedding of the vth node, W 1 is the first weight matrix, σ(·) is the activation function, CONCAT(·) is the connection function, M is the node attribute matrix, is the attribute data of the vth node, is the vth column of the adjacency matrix G; Step S33: node processing; Step S34: edge processing; Step S35: Embedding update based on the node embedding matrix F and the new adjacency matrix , perform Z1 layer update on the node embedding, the formula used is as follows: ； In the formula, and are the embeddings of the p-th node in the node set at the z+1th layer and the z-th layer, respectively. is the new adjacency matrix The pth column, W z+1 is the weight matrix of the z+1th layer; Step S36: Monitoring, normalizing the embedding of the Z1th layer nodes based on the softmax function to obtain the probability distribution corresponding to each data label, and selecting the data label with the largest probability as the monitoring output of the transformer winding deformation monitoring model for the node.

5. The transformer winding deformation monitoring method based on artificial intelligence according to claim 4 is characterized in that: In step S33, the node processing specifically includes the following steps: Step S331: majority class node processing, calculate the Euclidean distance between each majority class node and the attribute data of the remaining nodes, and select the first k nodes with the smallest Euclidean distance as reference nodes; if Among the k reference nodes, The number of nodes belonging to the same data label is greater than or equal to , then the majority class nodes Delete from the node set and delete the corresponding edge; where, is the nth majority class node; Step S332: Minority node processing: find the node with the shortest Euclidean distance to each minority node and belonging to the same data label, use it as an auxiliary node, generate a new node for each minority node based on the auxiliary node, add the new node to the node set, and obtain the node embedding matrix F. The formula used is as follows: ； In the formula, is the embedding of the new node generated by the u-th minority class node, is the embedding of the u-th minority class node, is the embedding of the auxiliary node corresponding to the u-th minority class node, and α is the balancing factor.

6. The transformer winding deformation monitoring method based on artificial intelligence according to claim 1 is characterized in that: In step S1, the data collection is to collect historical transformer winding signal data; the historical transformer winding signal data includes current signal data, voltage signal data, vibration signal data, temperature signal data, sound wave signal data, timestamp and winding status; the winding status is used as a data label.

7. The transformer winding deformation monitoring method based on artificial intelligence according to claim 1 is characterized in that: In step S4, the real-time deformation monitoring is to collect real-time transformer winding signal data; the real-time transformer winding signal data includes current signal data, voltage signal data, vibration signal data, temperature signal data, sound wave signal data and timestamp, and after signal data processing, it is input into the transformer winding deformation monitoring model for analysis, and the real-time status of the transformer winding is obtained based on the output data label.

8. A transformer winding deformation monitoring system based on artificial intelligence, used to implement a transformer winding deformation monitoring method based on artificial intelligence as claimed in any one of claims 1 to 7, characterized in that: It includes a data acquisition module, a signal data processing module, a transformer winding deformation monitoring model building module and a real-time deformation monitoring module; The data acquisition module collects historical transformer winding signal data and sends the data to the signal data processing module; The signal data processing module decomposes the transformer winding signal data, selects the IMF component based on the contribution to perform wavelet transform, obtains the wavelet coefficient, designs the guide value and the update strategy to search the threshold, finds the optimal threshold of each wavelet coefficient, introduces the adjustment coefficient to design the threshold processing function, performs threshold processing on each wavelet coefficient based on the optimal threshold, extracts features and constructs a monitoring data set, and sends the data to the module for constructing the transformer winding deformation monitoring model; The transformer winding deformation monitoring model building module calculates embedding according to node attribute data, screens and deletes majority class nodes based on reference nodes, generates new nodes for minority class nodes based on auxiliary nodes and balance factors and calculates embedding, sets weights of new node edges according to association, performs multi-layer update of node embedding based on node embedding matrix and new adjacency matrix, outputs data labels, and sends data to the real-time deformation monitoring module; The real-time deformation monitoring module collects real-time transformer winding signal data, processes the signal data, and then inputs the data into the transformer winding deformation monitoring model for analysis to obtain the real-time status of the transformer winding.

Images