Intelligent transformer winding deformation detection method

Abstract

The invention discloses an intelligent transformer winding deformation detection method. The method comprises the steps of data acquisition, data amplification, transformer winding deformation detection model establishment, winding deformation detection and model calibration. The invention relates to the technical field of transformer detection, in particular to an intelligent transformer winding deformation detection method, which innovatively introduces optimization strategies of probability correction, geometric deviation detection and information entropy evaluation, improves the stability and distribution rationality of amplified data, optimizes the data quality, and improves the detection accuracy. By constructing an innovative decision boundary, introducing an adaptive dynamic kernel function, designing a nonlinear boundary relaxation function and optimizing regular term control of a Lagrange function, the adaptability of the model to a complex deformation mode is improved, and the intelligent level of transformer state monitoring is improved; by introducing a feedback data calibration mechanism and utilizing comparative learning, feature alignment is realized, the aggregability of the same category of data is enhanced, different categories of data are distinguished, and the misjudgment rate is effectively reduced.

Description

Technical Field

[0001] The invention relates to the technical field of transformer detection, and in particular to an intelligent transformer winding deformation detection method. Background Art

[0002] Transformers are core equipment in power systems. During long-term operation, their windings may be deformed due to short-circuit current shock, mechanical vibration, thermal expansion and contraction, and other factors. Winding deformation can lead to a decline in electrical performance and even cause serious power accidents. Therefore, it is of great significance to accurately and reliably detect winding deformation.

[0003] Traditional data augmentation methods have problems such as distorted data distribution, single disturbance method, insufficient quality control and difficulty in screening high-quality data; traditional transformer winding deformation detection methods have problems such as rigid decision boundaries, fixed kernel functions, single relaxation strategies and poor adaptability to local data structures; traditional transformer winding deformation detection models have problems such as model drift, unstable features and poor adaptability to new data in long-term operation. Summary of the invention

[0004] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an intelligent transformer winding deformation detection method. In view of the problems of data distribution distortion, single disturbance mode, insufficient quality control and difficulty in screening high-quality data in traditional data augmentation methods, this scheme innovatively introduces nonlinear disturbance conversion, probability correction based on Markov chain, geometric deviation test and information entropy evaluation Multi-level optimization strategy, effectively improves the diversity, stability and distribution rationality of augmented data, ensures that the new data can not only enrich the data set, but also maintain consistency with the core features of the original data, thereby optimizing data quality, improving model generalization ability, and enhancing the robustness and accuracy of transformer winding deformation detection; in view of the problems of rigid decision boundaries, fixed kernel functions, single relaxation strategies and poor adaptability to local data structures in traditional transformer winding deformation detection methods, this scheme constructs a dynamic The segmented hypersurface decision boundary, the introduction of adaptive dynamic kernel function, the design of nonlinear boundary relaxation function and the optimization of regularization term control of Lagrangian function can improve the adaptability of the model to complex deformation patterns, enhance the nonlinear expression ability of data classification, improve the detection accuracy and robustness, enable the model to more accurately identify the slight deformation of transformer windings, and improve the intelligence level of transformer condition monitoring; in view of the problems of model offset, feature instability and poor adaptability to new data in the long-term operation of traditional transformer winding deformation detection model, this scheme introduces feedback data calibration mechanism, uses contrastive learning to realize feature alignment, enhances the aggregation of data of the same category and distinguishes data of different categories, and calculates data distribution deviation through distribution offset detection mechanism, and adjusts model parameters, so as to improve the stability and generalization ability of the model, enhance its adaptability under actual working conditions, and effectively reduce the misjudgment rate.

[0005] The technical solution adopted by the present invention is as follows: an intelligent transformer winding deformation detection method, the method comprising the following steps:

[0006] Step S1: data collection;

[0007] Step S2: data amplification;

[0008] Step S3: creating a transformer winding deformation detection model;

[0009] Step S4: winding deformation detection;

[0010] Step S5: Model calibration.

[0011] Furthermore, in step S1, the data collection is to collect electrical parameter data, mechanical vibration data, temperature data and deformation data of the historical transformer; the electrical parameter data refers to the voltage, current, frequency, three-phase voltage imbalance rate, transformer load rate, harmonic content and impedance parameters of the transformer; the mechanical vibration data refers to the vibration signal of the winding; the temperature data includes the temperature of the winding and the temperature of the environment; the deformation data refers to whether the transformer winding is deformed; and the original data set is created at the same time.

[0012] Furthermore, in step S2, the data amplification specifically includes the following steps:

[0013] Step S21: perturbation conversion, constructing a nonlinear mapping function to perturb the original data in a high-dimensional space and generate new data points, which are expressed as follows:

[0014] ;

[0015] in, represents the data after disturbance conversion, Represents the original data, and represents the conversion weight, represents the linear rectification function, represents the hyperbolic tangent function, Dt represents the noise factor, represents the noise variance, represents the unit rectangle, It means that the noise factor has a mean of 0 and a variance of Normal distribution of

[0016] Step S22: Probability correction, constructing new data points based on the Markov chain so that the generated data conforms to the original distribution while introducing perturbations, as shown below:

[0017] ;

[0018] in, represents the data after probability correction, The transition factor indicating that the element follows the Beta distribution, represents a data sample randomly selected from the original data set, represents the synergy coefficient;

[0019] Step S23: creating a seed data set, and adding the new data generated after the disturbance conversion and probability correction to the created seed data set;

[0020] Step S24: Geometric check, calculate the geometric deviation between the data of the seed data set and the original data in the high-dimensional space to ensure that the new data point does not deviate from the distribution core, as shown below:

[0021] ;

[0022] in, represents the geometric deviation between the data of the seed data set and the original data, i represents the index of the data point, and N represents the total number of data points. represents an exponential function with a natural constant as base, represents the i-th data point in the seed dataset, represents the i-th original data point, Indicates modulus;

[0023] Step S25: Information entropy test, calculating the information entropy change of the data in the seed data set, expressed as follows:

[0024] ;

[0025] in, Represents the information entropy deviation between the data of the seed data set and the original data, and Represent the probability density of the data of the seed data set and the original data respectively, Indicates taking the absolute value, It means taking logarithm;

[0026] Step S26: Data augmentation, calculate the geometric deviation and information entropy deviation between all data in the seed data set and the original data, remove the data in the seed data set with the maximum geometric deviation and information entropy deviation at 50%, and add the remaining data in the seed data set to the original data.

[0027] Further, in step S3, the creation of the transformer winding deformation detection model specifically includes the following steps:

[0028] Step S31: Create a transformation matrix group, the matrix group includes two matrices, one is an upper triangular matrix, and the other is a diagonal matrix;

[0029] Step S32: define the objective function, set whether the transformer winding is deformed as the label of the model, introduce a dynamic segmented hypersurface as the decision boundary, and the shape of the hypersurface is determined by the transformation matrix group;

[0030] Step S33: introducing a dynamic kernel function, and adjusting the shape and parameters of the kernel function according to the local structure of the input data;

[0031] Step S34: generating a decision function;

[0032] Step S35: define constraint conditions, introduce dynamic boundary relaxation function, and determine the relaxation degree of each sample point through nonlinear function;

[0033] Step S36: Generate a Lagrangian function, introduce a regularization term to control the range of change of the dual variable, introduce constraints into the objective function, and construct a Lagrangian function.

[0034] Furthermore, in step S4, the winding deformation detection is to collect the electrical parameter data, mechanical vibration data and temperature data of the transformer in real time, input the data into the transformer winding deformation detection model, and the model determines whether the transformer winding is deformed.

[0035] Furthermore, in step S5, the model calibration specifically includes the following steps:

[0036] Step S51: obtaining feedback data, obtaining electrical parameter data, mechanical vibration data and temperature data of the transformer input into the model, and recording the model's judgment result on whether the transformer winding is deformed, and combining the data into a feedback data set;

[0037] Step S52: feature alignment, for the transformer data of the feedback data set, using a contrastive learning method to make the distance between data of the same category closer in the high-dimensional space and data of different categories farther apart;

[0038] Step S53: Feedback calibration, introducing a distribution offset detection mechanism, calculating the deviation between the initial data distribution of the model and the feedback data distribution, and performing model calibration.

[0039] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0040] (1) In view of the problems of data distribution distortion, single disturbance mode, insufficient quality control and difficulty in screening high-quality data in traditional data augmentation methods, this scheme innovatively introduces a multi-level optimization strategy of nonlinear disturbance conversion, probability correction based on Markov chain, geometric deviation test and information entropy evaluation to effectively improve the diversity, stability and distribution rationality of augmented data, ensuring that the new data can not only enrich the data set but also maintain consistency with the core features of the original data, thereby optimizing data quality, improving model generalization ability, and enhancing the robustness and accuracy of transformer winding deformation detection.

[0041] (2) In view of the problems of rigid decision boundary, fixed kernel function, single relaxation strategy and poor adaptability to local data structure in traditional transformer winding deformation detection methods, this scheme improves the adaptability of the model to complex deformation patterns, enhances the nonlinear expression ability of data classification, improves detection accuracy and robustness, and enables the model to more accurately identify the slight deformation of transformer windings, thereby improving the intelligence level of transformer condition monitoring.

[0042] (3) In view of the problems of model offset, feature instability and poor adaptability to new data in the long-term operation of the traditional transformer winding deformation detection model, this scheme introduces a feedback data calibration mechanism and uses contrastive learning to achieve feature alignment, enhance the aggregation of data of the same category and distinguish data of different categories. At the same time, the data distribution deviation is calculated through the distribution offset detection mechanism, and the model parameters are adjusted, thereby improving the stability and generalization ability of the model, enhancing its adaptability under actual working conditions, and effectively reducing the misjudgment rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of an intelligent transformer winding deformation detection method provided by the present invention;

[0044] Figure 2 A schematic diagram of data amplification provided by the present invention;

[0045] Figure 3 A schematic diagram for creating a transformer winding deformation detection model;

[0046] Figure 4 Schematic diagram of model calibration.

[0047] 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

[0048] 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.

[0049] 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.

[0050] Example 1, see Figure 1 The present invention provides an intelligent transformer winding deformation detection method, which comprises the following steps:

[0051] Step S1: data collection, collecting historical transformer electrical parameter data, mechanical vibration data, temperature data and deformation data;

[0052] Step S2: Data augmentation, data augmentation is performed through perturbation conversion, probability correction, creation of seed data set, geometric test and information entropy test;

[0053] Step S3: creating a transformer winding deformation detection model by creating a transformation matrix group, defining an objective function, introducing a dynamic kernel function, generating a decision function, defining constraint conditions, and generating a Lagrangian function;

[0054] Step S4: winding deformation detection, real-time collection of transformer electrical parameter data, mechanical vibration data and temperature data, input of the data into the transformer winding deformation detection model, the model determines whether the transformer winding is deformed;

[0055] Step S5: Model calibration, which is achieved by obtaining feedback data, feature alignment and feedback calibration.

[0056] Example 2, see Figure 1 This embodiment is based on the above embodiment. In step S1, the data collection specifically collects electrical parameter data, mechanical vibration data, temperature data and deformation data of the historical transformer; the electrical parameter data refers to the voltage, current, frequency, three-phase voltage imbalance rate, transformer load rate, harmonic content and impedance parameters of the transformer; the mechanical vibration data refers to the vibration signal of the winding; the temperature data includes the temperature of the winding and the temperature of the environment; the deformation data refers to whether the transformer winding is deformed; at the same time, an original data set is created, each item of collected data is set as a feature, each group of data features constitutes a data vector, and all data vectors composed of the collected data are added to the original data set to form a complete original data set.

[0057] Example 3, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S2, the data amplification specifically includes the following steps:

[0058] Step S21: perturbation conversion, constructing a nonlinear mapping function to perturb the original data in a high-dimensional space and generate new data points, which are expressed as follows:

[0059] ;

[0060] in, represents the data after disturbance conversion, Represents the original data, and represents the conversion weight, represents the linear rectification function, represents the hyperbolic tangent function, Dt represents the noise factor, represents the noise variance, represents the unit rectangle, It means that the noise factor has a mean of 0 and a variance of Normal distribution of

[0061] Step S22: Probability correction, constructing new data points based on the Markov chain so that the generated data conforms to the original distribution while introducing perturbations, as shown below:

[0062] ;

[0063] in, represents the data after probability correction, The transition factor indicating that the element follows the Beta distribution, represents a data sample randomly selected from the original data set, represents the synergy coefficient;

[0064] Step S23: creating a seed data set, and adding the new data generated after the disturbance conversion and probability correction to the created seed data set;

[0065] Step S24: Geometric check, calculate the geometric deviation between the data of the seed data set and the original data in the high-dimensional space to ensure that the new data point does not deviate from the distribution core, as shown below:

[0066] ;

[0067] in, represents the geometric deviation between the data of the seed data set and the original data, i represents the index of the data point, and N represents the total number of data points. represents an exponential function with a natural constant as base, represents the i-th data point in the seed dataset, represents the i-th original data point, Indicates modulus;

[0068] Step S25: Information entropy test, calculating the information entropy change of the data in the seed data set, expressed as follows:

[0069] ;

[0070] in, Represents the information entropy deviation between the data of the seed data set and the original data, and Represent the probability density of the data of the seed data set and the original data respectively, Indicates taking the absolute value, It means taking logarithm;

[0071] Step S26: Data augmentation, calculate the geometric deviation and information entropy deviation between all data in the seed data set and the original data, remove the data in the seed data set with the maximum geometric deviation and information entropy deviation at 50%, and add the remaining data in the seed data set to the original data.

[0072] By performing the above operations, this scheme innovatively introduces a multi-level optimization strategy of nonlinear perturbation conversion, probability correction based on Markov chain, geometric deviation test and information entropy evaluation to address the problems of traditional data augmentation methods, such as distorted data distribution, single perturbation method, insufficient quality control and difficulty in screening high-quality data. It effectively improves the diversity, stability and distribution rationality of augmented data, and ensures that the new data can not only enrich the data set but also maintain consistency with the core features of the original data, thereby optimizing data quality, improving model generalization ability, and enhancing the robustness and accuracy of transformer winding deformation detection.

[0073] Example 4, see Figure 1 and Figure 3 This embodiment is based on the above embodiment. In step S3, the transformer winding deformation detection model is created, specifically including the following steps:

[0074] Step S31: Create a transformation matrix group, the matrix group includes two matrices, one is an upper triangular matrix, and the other is a diagonal matrix;

[0075] Step S32: define the objective function, set whether the transformer winding is deformed as the label of the model, introduce a dynamic segmented hypersurface as the decision boundary, and the shape of the hypersurface is determined by the transformation matrix group, which is expressed as follows:

[0076] ;

[0077] in, and Represent the weight vector and bias vector of the model respectively, represents the transformation matrix group, Indicates the parameter used to find the minimum value of the target expression , and , , and represents the importance weight, represents the loss function, represents the category label of the i-th data point, represents the i-th data point, represents the output of the decision function, k represents the index of the matrix in the transformation matrix group, represents the kth matrix in the transformation matrix group, means taking the square of the Frobenius norm;

[0078] Step S33: Introduce a dynamic kernel function, and adjust the shape and parameters of the kernel function according to the local structure of the input data, as shown below:

[0079] ;

[0080] Where j represents the index of the data point, represents the jth data point, represents the dynamic kernel function between the i-th and j-th data points, represents the bandwidth function, represents the bandwidth function value between the i-th and j-th data points, represents the cosine function, T represents the transposed symbol, represents a randomly selected matrix from the transformation matrix group, and represents the bandwidth weight, Represents the median of the Euclidean distance between the i-th data point and all other data points;

[0081] Step S34: Generate a decision function, which is expressed as follows:

[0082] ;

[0083] in, represents the symbolic function, represents the Lagrange multiplier of the ith data point, represents decision bias;

[0084] Step S35: Define constraint conditions, introduce dynamic boundary relaxation function, and determine the relaxation degree of each sample point through nonlinear function, which is expressed as follows:

[0085] ;

[0086] in, represents the slack variable, represents the relaxation coefficient, represents the relaxation degree control factor;

[0087] Step S36: Generate a Lagrangian function, introduce a regularization term to control the range of change of the dual variable, introduce constraints into the objective function, and construct a Lagrangian function, which is expressed as follows:

[0088] ;

[0089] in, represents the set of Lagrange multipliers, represents the importance weight set, represents the Lagrangian function, Indicates that the parameter is , , and The value of the Lagrangian function under the condition of .

[0090] By performing the above operations, in order to address the problems of rigid decision boundary, fixed kernel function, single relaxation strategy and poor adaptability to local data structure in traditional transformer winding deformation detection methods, this scheme improves the adaptability of the model to complex deformation patterns, enhances the nonlinear expression ability of data classification, improves detection accuracy and robustness, and enables the model to more accurately identify small deformations of transformer windings, thereby improving the intelligence level of transformer condition monitoring.

[0091] Example 5, see Figure 1 and Figure 4 This embodiment is based on the above embodiment. In step S5, the model calibration specifically includes the following steps:

[0092] Step S51: obtaining feedback data, obtaining electrical parameter data, mechanical vibration data and temperature data of the transformer input into the model, and recording the model's judgment result on whether the transformer winding is deformed, and combining the data into a feedback data set;

[0093] Step S52: feature alignment. For the transformer data of the feedback data set, a contrastive learning method is used to make the distance between the data of the same category closer in the high-dimensional space and the data of different categories farther apart, as shown below:

[0094] ;

[0095] in, represents the feature alignment loss, Represents the model initial data in the dataset used for model training, represents the feedback data in the feedback dataset, Indicates whether the model initial data and feedback data belong to the same category. If they belong to the same category, Equal to 1, belonging to different categories is equal to 0, m represents the interval factor, Indicates taking the maximum value;

[0096] Step S53: Feedback calibration, introducing a distribution offset detection mechanism, calculating the deviation between the initial data distribution of the model and the feedback data distribution, and performing model calibration, as shown below:

[0097] ;

[0098] in, represents the distribution deviation, Indicates the overall deviation distance. Represents the overall deviation distance between the model's initial data distribution and the feedback data distribution, represents the model parameters after feedback calibration, represents the initial parameters of the model, represents the calibration coefficient, represents the gradient of the distribution deviation with respect to the model parameters.

[0099] By performing the above operations, in order to address the problems of model offset, feature instability and poor adaptability to new data in the long-term operation of the traditional transformer winding deformation detection model, this solution introduces a feedback data calibration mechanism and uses contrastive learning to achieve feature alignment, enhance the aggregation of data of the same category and distinguish data of different categories. At the same time, the data distribution deviation is calculated through the distribution offset detection mechanism, and the model parameters are adjusted, thereby improving the stability and generalization ability of the model, enhancing its adaptability under actual working conditions, and effectively reducing the misjudgment rate.

[0100] 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.

[0101] 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.

[0102] 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. An intelligent transformer winding deformation detection method, characterized in that: The method comprises the following steps: Step S1: data collection, collecting historical transformer electrical parameter data, mechanical vibration data, temperature data and deformation data; Step S2: Data augmentation, data augmentation is performed through perturbation conversion, probability correction, creation of seed data set, geometric test and information entropy test; Step S21: perturbation conversion, constructing a nonlinear mapping function to perturb the original data in a high-dimensional space and generate new data points, which are expressed as follows: ； in, represents the data after disturbance conversion, Represents the original data, and represents the conversion weight, represents the linear rectification function, represents the hyperbolic tangent function, Dt represents the noise factor, represents the noise variance, represents the unit rectangle, It means that the noise factor has a mean of 0 and a variance of Normal distribution of Step S3: creating a transformer winding deformation detection model by creating a transformation matrix group, defining an objective function, introducing a dynamic kernel function, generating a decision function, defining constraint conditions, and generating a Lagrangian function; Step S4: winding deformation detection, using a transformer winding deformation detection model to detect the deformation of the transformer winding; Step S5: Model calibration, which is achieved by obtaining feedback data, feature alignment and feedback calibration.

2. The intelligent transformer winding deformation detection method according to claim 1 is characterized in that: In step S2, the data amplification specifically includes the following steps: Step S21: disturbance conversion; Step S22: Probability correction, constructing new data points based on the Markov chain so that the generated data conforms to the original distribution while introducing perturbations, as shown below: ； in, represents the data after probability correction, The transition factor indicating that the element follows the Beta distribution, represents a data sample randomly selected from the original data set, represents the synergy coefficient; Step S23: creating a seed data set, and adding the new data generated after the disturbance conversion and probability correction to the created seed data set; Step S24: Geometric check, calculate the geometric deviation between the data of the seed data set and the original data in the high-dimensional space to ensure that the new data point does not deviate from the distribution core, as shown below: ； in, represents the geometric deviation between the data of the seed data set and the original data, i represents the index of the data point, and N represents the total number of data points. represents an exponential function with a natural constant as base, represents the i-th data point in the seed dataset, represents the i-th original data point, Indicates modulus; Step S25: Information entropy test, calculating the information entropy change of the data in the seed data set, expressed as follows: ； in, Represents the information entropy deviation between the data of the seed data set and the original data, and Represent the probability density of the data of the seed data set and the original data respectively, Indicates taking the absolute value, It means taking logarithm; Step S26: Data augmentation, calculate the geometric deviation and information entropy deviation between all data in the seed data set and the original data, remove the data in the seed data set with the maximum geometric deviation and information entropy deviation at 50%, and add the remaining data in the seed data set to the original data.

3. The intelligent transformer winding deformation detection method according to claim 1 is characterized in that: In step S3, the transformer winding deformation detection model is created, specifically comprising the following steps: Step S31: Create a transformation matrix group, the matrix group includes two matrices, one is an upper triangular matrix, and the other is a diagonal matrix; Step S32: define the objective function, set whether the transformer winding is deformed as the label of the model, introduce a dynamic segmented hypersurface as the decision boundary, and the shape of the hypersurface is determined by the transformation matrix group; Step S33: introducing a dynamic kernel function, and adjusting the shape and parameters of the kernel function according to the local structure of the input data; Step S34: generating a decision function; Step S35: define constraint conditions, introduce dynamic boundary relaxation function, and determine the relaxation degree of each sample point through nonlinear function; Step S36: Generate a Lagrangian function, introduce a regularization term to control the range of change of the dual variable, introduce constraints into the objective function, and construct a Lagrangian function.

4. The intelligent transformer winding deformation detection method according to claim 1 is characterized in that: In step S5, the model calibration specifically includes the following steps: Step S51: obtaining feedback data, obtaining electrical parameter data, mechanical vibration data and temperature data of the transformer input into the model, and recording the model's judgment result on whether the transformer winding is deformed, and combining the data into a feedback data set; Step S52: feature alignment, for the transformer data of the feedback data set, using a contrastive learning method to make the distance between data of the same category closer in the high-dimensional space and data of different categories farther apart; Step S53: Feedback calibration, introducing a distribution offset detection mechanism, calculating the deviation between the initial data distribution of the model and the feedback data distribution, and performing model calibration.

5. The intelligent transformer winding deformation detection method according to claim 1 is characterized in that: In step S1, the data collection is to collect electrical parameter data, mechanical vibration data, temperature data and deformation data of the historical transformer; the electrical parameter data refers to the voltage, current, frequency, three-phase voltage imbalance rate, transformer load rate, harmonic content and impedance parameters of the transformer; the mechanical vibration data refers to the vibration signal of the winding; the temperature data includes the temperature of the winding and the temperature of the environment; the deformation data refers to whether the transformer winding is deformed; and the original data set is created at the same time.

6. The intelligent transformer winding deformation detection method according to claim 1 is characterized in that: In step S4, the winding deformation detection collects the electrical parameter data, mechanical vibration data and temperature data of the transformer in real time, inputs the data into the transformer winding deformation detection model, and the model determines whether the transformer winding is deformed.

Images