Transformer winding deformation rapid diagnosis method based on simulation analysis and intelligent classification algorithm and related device

Abstract

The invention provides a transformer winding deformation rapid diagnosis method based on simulation analysis and an intelligent classification algorithm and a related device. The method comprises the following steps: acquiring frequency response data of a winding by using a winding equivalent circuit model of a to-be-researched transformer; comparing the frequency response data of the winding with the frequency response data of the winding in a normal state to obtain a plurality of difference measurement indexes; performing feature combination on the plurality of difference measurement indexes to obtain a plurality of composite feature indexes, each composite feature index being formed by fusing at least two difference measurement indexes; and inputting the plurality of difference measurement indexes and the composite characteristic indexes into a trained diagnosis model to obtain a winding deformation diagnosis result. According to the method, the diagnosis model is trained through the difference measurement indexes and the composite characteristic indexes, so that efficient and accurate transformer winding deformation diagnosis is realized, and reliable technical support is provided for health state evaluation and fault early warning of the transformer winding.

Description

Technical Field

[0001] The present invention belongs to the technical field of transformers, and in particular relates to a method and a related device for quickly diagnosing transformer winding deformation based on simulation analysis and intelligent classification algorithm. Background Art

[0002] As a key device for energy transmission and conversion in the power system, the safety and reliability of the transformer is directly related to the stable operation of the entire power grid. Due to the complex structure and high cost of actual transformers, it is difficult to simulate winding faults and explore the characteristics of frequency response changes under faults. Therefore, it is necessary to establish an equivalent circuit model of transformer windings with the same winding structure to study the law of winding frequency response changes under faults.

[0003] Frequency response analysis (FRA) is a relatively advanced detection method that detects winding deformation by measuring the electrical response of the winding at different frequencies. Although FRA has a great advantage in detection accuracy, traditional FRA data analysis relies on expert experience and lacks automation and intelligence.

[0004] With the increasing complexity and operation requirements of power systems, higher requirements are placed on transformer winding deformation detection methods. The shortcomings of traditional methods, especially the limitations of detection efficiency and accuracy, have promoted the development of intelligent diagnosis technology. Summary of the invention

[0005] In view of this, the present invention aims at the shortcomings of traditional transformer winding deformation detection methods and proposes a transformer winding deformation rapid diagnosis method and related devices based on simulation analysis and intelligent classification algorithm, aiming to improve the detection accuracy and efficiency, provide reliable technical support for transformer winding health status assessment and fault warning, and provide a reference for transformer operation and maintenance.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for rapid diagnosis of transformer winding deformation based on simulation analysis and intelligent classification algorithm, comprising the following steps:

[0008] Using the winding equivalent circuit model of the transformer to be studied, the frequency response data of the winding is obtained;

[0009] Compare the frequency response data of the winding with the frequency response data of the winding in a normal state to obtain several difference measurement indicators;

[0010] Combining several difference metrics to obtain several composite feature metrics, each of which is a fusion of at least two difference metrics;

[0011] Several difference metrics and composite feature metrics are input into the trained diagnostic model to obtain the winding deformation diagnosis result. The diagnostic model is trained based on the difference metrics and composite feature metrics under different fault types and the corresponding fault types as labels.

[0012] Furthermore, the fusion methods include: ratio, difference and product calculation.

[0013] Furthermore, the difference metrics include:

[0014] Correlation coefficient, Euclidean distance, sum-squared error, root mean square error, and squared ratio error.

[0015] Furthermore, the composite characteristic indicators include:

[0016] The ratio of the correlation coefficient to the Euclidean distance, the difference between the sum-squared error and the root mean square error, and the product of the squared ratio error and the correlation coefficient.

[0017] Furthermore, the diagnostic model is trained using the gradient boosting machine algorithm.

[0018] Furthermore, the fault types include:

[0019] Radial deformation, radial displacement and axial displacement.

[0020] Furthermore, the winding equivalent circuit model is determined by calculating the equivalent circuit model parameters using a transformer simulation model.

[0021] In a second aspect, the present invention provides a transformer winding deformation rapid diagnosis device based on simulation analysis and intelligent classification algorithm, comprising:

[0022] A data acquisition module, used for acquiring frequency response data of the winding using an equivalent circuit model of the winding of the transformer to be studied;

[0023] A first index calculation module is used to compare the frequency response data of the winding with the frequency response data of the winding in a normal state to obtain a plurality of difference measurement indicators;

[0024] The second indicator calculation module is used to perform feature combination on a plurality of difference measurement indicators to obtain a plurality of composite feature indicators, each of which is formed by merging at least two difference measurement indicators;

[0025] The diagnosis module is used to input several difference measurement indicators and composite feature indicators into the trained diagnosis model to obtain the winding deformation diagnosis result. The diagnosis model is based on the difference measurement indicators and composite feature indicators under different fault types, and is trained with the corresponding fault types as labels.

[0026] Accordingly, the present invention also provides a computer device, the device comprising a processor and a memory:

[0027] The memory is used to store the computer program and send the instructions of the computer program to the processor;

[0028] The processor executes a transformer winding deformation rapid diagnosis method based on simulation analysis and intelligent classification algorithm as described in the first aspect according to the instructions of the computer program.

[0029] Correspondingly, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, a method for rapid diagnosis of transformer winding deformation based on simulation analysis and intelligent classification algorithm as in the first aspect is implemented.

[0030] In summary, the present invention provides a transformer winding deformation rapid diagnosis method and related devices based on simulation analysis and intelligent classification algorithm, including using the winding equivalent circuit model of the transformer to be studied to obtain the frequency response data of the winding; comparing the frequency response data of the winding with the frequency response data of the winding in a normal state to obtain a number of difference measurement indicators; combining the characteristics of the several difference measurement indicators to obtain a number of composite feature indicators, each composite feature indicator is formed by the fusion of at least two difference measurement indicators; inputting the several difference measurement indicators and the composite feature indicators into the trained diagnosis model to obtain the winding deformation diagnosis result, and the diagnosis model is based on the difference measurement indicators and the composite feature indicators under different fault types, and the corresponding fault types are used as labels for training. The present invention trains the diagnosis model through the difference measurement indicators and the composite feature indicators, thereby realizing efficient and accurate transformer winding deformation diagnosis, and providing reliable technical support for the health status assessment and fault warning of the transformer winding. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 A flowchart of a method for rapid diagnosis of transformer winding deformation based on simulation analysis and intelligent classification algorithm provided by an embodiment of the present invention;

[0033] Figure 2 An equivalent circuit model diagram of a transformer winding of a certain type provided in an embodiment of the present invention;

[0034] Figure 3A frequency response curve diagram of a certain type of transformer before and after a certain fault provided by an embodiment of the present invention;

[0035] Figure 4 A block diagram of a transformer winding deformation rapid diagnosis device based on simulation analysis and intelligent classification algorithm provided by an embodiment of the present invention;

[0036] Figure 5 A block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, 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 embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] See also Figure 1 This embodiment provides a method for rapid diagnosis of transformer winding deformation based on simulation analysis and intelligent classification algorithm, comprising the following steps:

[0039] S1: Use the winding equivalent circuit model of the transformer to be studied to obtain the frequency response data of the winding.

[0040] It should be noted that this step uses the equivalent circuit model of the transformer winding to perform simulation analysis to obtain the response characteristic data of the winding at different frequencies. This usually involves establishing a mathematical model of the transformer winding and using electromagnetic field simulation software or other related tools to calculate its frequency response characteristics.

[0041] S2: Compare the frequency response data of the winding with the frequency response data of the winding in a normal state to obtain several difference measurement indicators.

[0042] It should be noted that the actual measured frequency response data is compared with the data under standard or historical normal conditions to calculate a set of difference metrics. The difference metrics can help identify changes in winding performance, indicating possible deformation or other types of faults.

[0043] S3: Combining several difference metrics to obtain several composite feature metrics, each of which is a fusion of at least two difference metrics.

[0044] It should be noted that this step combines individual difference metrics to generate composite feature metrics. These composite features may be obtained by weighted averaging, multiplication, or other mathematical operations on the original difference metrics. Each composite feature metric is composed of at least two difference metrics. Composite feature metrics can better capture the multi-faceted effects of winding deformation, thereby improving the accuracy and robustness of the diagnostic model.

[0045] S4: Input several difference measurement indicators and composite feature indicators into the trained diagnosis model to obtain the winding deformation diagnosis result. The diagnosis model is trained based on the difference measurement indicators and composite feature indicators under different fault types and the corresponding fault types as labels.

[0046] It should be noted that this step inputs all the difference metrics and composite feature indicators obtained in the previous steps into the pre-trained diagnostic model. The diagnostic model is built based on a machine learning algorithm, which uses a large number of data sets containing different fault types for training, where each set of data is labeled with the corresponding fault type label. The model can predict the health status of the winding or the specific fault type based on the input feature indicators.

[0047] This embodiment provides a transformer winding deformation rapid diagnosis method based on simulation analysis and intelligent classification algorithm, which can efficiently detect whether the transformer winding is deformed and further determine the specific situation of the deformation. The advantage of this method is that it not only relies on a single metric, but also improves the accuracy of diagnosis through multi-dimensional feature analysis.

[0048] In some embodiments, the winding equivalent circuit model is determined by calculating equivalent circuit model parameters using a transformer simulation model.

[0049] In this embodiment, the process of obtaining frequency response data using the winding equivalent circuit model is as follows:

[0050] First, select a specific transformer as the research object and collect detailed information such as its design drawings and technical specifications. Based on these data, use Solidworks or other 3D modeling software to build a detailed simulation model according to the actual structure. This model includes not only the core and windings, but also the insulation paper, insulation pads, pressure end plates and pressure paper, and oil tank.

[0051] Next, the constructed transformer model is imported into the commercial simulation software. A 1V voltage or 1A current excitation is applied to the winding, and the corresponding boundary conditions are set. The longitudinal capacitance, ground capacitance and inductance parameters in the transformer winding equivalent circuit model are calculated by the software, and the transformer winding equivalent circuit model in a healthy state is established based on this.

[0052] In order to further study the influence of winding deformation on the equivalent circuit, it is also necessary to use Solidworks software to draw simulation models representing various common deformation conditions. For each type of deformation, different deformation parameters need to be set to simulate various situations that may actually occur, such as simulating radial deformation by changing the shape of the winding cross section, simulating radial displacement by adjusting the winding position, and simulating the movement of the winding along the length direction, that is, axial displacement.

[0053] For each deformation state, multiple deformation models of different degrees are created and imported into commercial software to calculate the winding equivalent circuit model in each deformation state. Subsequently, a series of frequency excitation signals are applied to the winding equivalent circuit models in the healthy state and various deformation states to obtain the frequency response curves in each state. These curves reflect the changes in the electrical characteristics of the transformer winding at different frequencies and are an important basis for evaluating the winding state. Figure 2 is the equivalent circuit model of a certain type of transformer winding. Figure 3 It is the frequency response curve of a certain type of transformer before and after a certain fault.

[0054] In some embodiments, the fault types include:

[0055] Radial deformation: changes the shape of the winding cross section, simulating the winding being stretched.

[0056] Radial displacement: Adjust the position of the winding within the cross section to simulate the overall inward or outward movement of the winding.

[0057] Axial displacement: simulates the movement of the winding along the length direction, such as the up and down displacement of the winding due to external force.

[0058] In some embodiments, by comparing the frequency response curves in the healthy state and the fault state, numerical indicators that can quantify the changes in winding characteristics in different states are extracted. The selected indicators include:

[0059] Correlation coefficient (CC): Evaluates the similarity of two curves.

[0060] Euclidean distance (ED): Calculates the distance between curves.

[0061] Sum Squared Error (SSE): quantifies the total error between the predicted and actual curves.

[0062] Root Mean Square Error (RMSE): Measures the average error size.

[0063] Squared ratio error (SSRE): compares the difference ratio between two curves.

[0064] The calculation formulas of various parameters are shown in Table 1.

[0065] Table 1 Numerical indicators

[0066]

[0067] In some embodiments, the fusion method includes: ratio, difference and product calculation.

[0068] In this embodiment, “ratio, difference and product calculation” refers to the use of different mathematical operations to integrate or compare two or more related quantities when processing data or signals. These fusion methods can help engineers understand and analyze the state of transformer windings more accurately. Through ratio, difference or product calculation, useful information can be extracted from complex signals, thereby making more accurate diagnosis.

[0069] In some embodiments, the composite feature index includes: a ratio of a correlation coefficient to an Euclidean distance, a difference between a sum-square error and a root mean square error, and a product of a square ratio error and a correlation coefficient.

[0070] Specifically, each pair of indicators is interactively operated to generate new composite features. These features can reveal the interaction between different indicators and may reflect more complex deformation patterns. The specific operations include: Ratio calculation: Calculate the ratio (CC / ED) of the correlation coefficient (CC) and the Euclidean distance (ED) to capture the relationship between the similarity and distance of the frequency response curves.

[0071] Difference calculation: Calculate the difference (SSE-RMSE) between the sum square error (SSE) and the root mean square error (RMSE) to quantify the difference between the predicted error and the actual error. Product calculation: Calculate the product (SSRE*CC) of the squared ratio error (SSRE) and the correlation coefficient (CC) to combine the information of the curve difference ratio and similarity.

[0072] The meaning of feature combinations is as follows:

[0073] Ratio (CC / ED): The ratio calculation provides a new feature that measures the impact of the actual distance between the frequency response curves (low ED) on the transformer condition when the frequency response curves are highly similar (high CC). A high ratio may indicate that a small distance difference may lead to a major failure when the similarity is high.

[0074] Difference (SSE-RMSE): This feature is used to quantify the difference between the overall prediction error and the average error. Large differences may indicate large error fluctuations in the deformed state, which may be a sign of severe deformation of the transformer winding.

[0075] Product (SSRE*CC): This feature combines two indicators and reflects the interaction between the difference ratio (SSRE) and similarity (CC) of the frequency response curve. This feature can reveal the impact of similarity on the diagnosis results when the difference is large, and help identify complex fault types.

[0076] In some embodiments, the diagnostic model uses a gradient boosting machine (GBM) algorithm to classify and diagnose the extracted numerical indicators. GBM is a powerful machine learning algorithm that can handle complex classification tasks. By learning from the training set data, the GBM model can identify deformations of different types and degrees and has good generalization capabilities. The hyperparameters of the GBM model are tuned using the grid search method to optimize the classification performance. By tuning the hyperparameters, the accuracy and stability of the model can be improved, thereby achieving higher diagnostic accuracy. The training process of the diagnostic model is as follows;

[0077] (1) A fault sample library is constructed based on the changing characteristics of the winding frequency response under different deformation states (including difference measurement indicators and composite characteristic indicators). Each group of samples includes the fault type and numerical indicators (such as the above five numerical indicators and the generated composite features (such as CC / ED, SSE-RMSE, SSRE*CC)).

[0078] (2) Model training and tuning: During the model training phase, the original features and the newly generated composite features are used together in the training set and trained using the GBM (gradient boosting machine) algorithm. The new features will help the model capture complex relationships that the original features cannot fully express, and enhance the model's ability to identify different fault types.

[0079] (3) Hyperparameter tuning: Use the grid search method to adjust the model's hyperparameters, such as the learning rate, the number of trees, the depth of the trees, etc., to optimize the model performance and ensure that the model has better classification accuracy and generalization ability after introducing new features.

[0080] (4) Model evaluation: Evaluate the performance of the model on the test set, focusing on analyzing the accuracy, precision, and recall indicators after the introduction of new features. Evaluate the performance of the model under various deformation states to verify the effect of the new features on improving model performance.

[0081] (5) Iterative optimization: Based on the model evaluation results, if the new features fail to significantly improve the model performance, the feature interaction and combination process can be re-analyzed to further optimize the model.

[0082] (6) Set up an actual prototype to conduct actual testing and verification of the GBM model and algorithm. Verify the model's predictive ability and diagnostic accuracy through actual running data. If the results do not meet the expected standards, the algorithm parameters need to be readjusted and the model needs to be retrained and verified until the required diagnostic accuracy requirements are met.

[0083] Based on the same inventive concept, the embodiment of the present application also provides a device for rapid diagnosis of transformer winding deformation based on simulation analysis and intelligent classification algorithm for realizing the method for rapid diagnosis of transformer winding deformation based on simulation analysis and intelligent classification algorithm mentioned above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiment of the device for rapid diagnosis of transformer winding deformation based on simulation analysis and intelligent classification algorithm provided below can be referred to the limitations of the method for rapid diagnosis of transformer winding deformation based on simulation analysis and intelligent classification algorithm above, and will not be repeated here.

[0084] See also Figure 4 This embodiment provides a transformer winding deformation rapid diagnosis device based on simulation analysis and intelligent classification algorithm, including:

[0085] A data acquisition module, used for acquiring frequency response data of the winding using an equivalent circuit model of the winding of the transformer to be studied;

[0086] A first index calculation module is used to compare the frequency response data of the winding with the frequency response data of the winding in a normal state to obtain a plurality of difference measurement indicators;

[0087] The second indicator calculation module is used to perform feature combination on a plurality of difference measurement indicators to obtain a plurality of composite feature indicators, each of which is formed by merging at least two difference measurement indicators;

[0088] The diagnosis module is used to input several difference measurement indicators and composite feature indicators into the trained diagnosis model to obtain the winding deformation diagnosis result. The diagnosis model is based on the difference measurement indicators and composite feature indicators under different fault types, and is trained with the corresponding fault types as labels.

[0089] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0090] Reference Figure 5 An embodiment of the present invention further provides a computer device, comprising: a memory and a processor and a computer program stored in the memory. When the computer program is executed on the processor, a rapid diagnosis method for transformer winding deformation based on simulation analysis and intelligent classification algorithm as described in any one of the above methods is implemented.

[0091] The computer device may be a desktop computer, a notebook, a PDA, a cloud server or other computing device. The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 5 It is only an example of a computer device and does not constitute a limitation of the computer device. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0092] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0093] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Further, the memory may include both an internal storage unit and an external storage device of the computer device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or is to be output.

[0094] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for rapid diagnosis of transformer winding deformation based on simulation analysis and intelligent classification algorithm as described in any one of the above methods is implemented.

[0095] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0096] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0097] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0098] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0099] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A rapid diagnosis method for transformer winding deformation based on simulation analysis and intelligent classification algorithm, characterized in that: The steps include: Using the winding equivalent circuit model of the transformer to be studied, the frequency response data of the winding is obtained; Comparing the frequency response data of the winding with the frequency response data of the winding in a normal state to obtain a plurality of difference measurement indicators; Combining the plurality of difference measurement indicators to obtain a plurality of composite feature indicators, each of which is formed by merging at least two of the difference measurement indicators; Several of the difference measurement indicators and the composite feature indicators are input into a trained diagnostic model to obtain a winding deformation diagnosis result. The diagnostic model is trained based on the difference measurement indicators and the composite feature indicators under different fault types and the corresponding fault types are used as labels.

2. The transformer winding deformation rapid diagnosis method based on simulation analysis and intelligent classification algorithm according to claim 1 is characterized in that: The fusion methods include: ratio, difference and product calculation.

3. The transformer winding deformation rapid diagnosis method based on simulation analysis and intelligent classification algorithm according to claim 1 or 2 is characterized in that: The difference measurement indicators include: Correlation coefficient, Euclidean distance, sum-squared error, root mean square error, and squared ratio error.

4. The transformer winding deformation rapid diagnosis method based on simulation analysis and intelligent classification algorithm according to claim 3 is characterized in that: The composite characteristic index includes: The ratio of the correlation coefficient to the Euclidean distance, the difference between the sum square error and the root mean square error, and the product of the square ratio error and the correlation coefficient.

5. The transformer winding deformation rapid diagnosis method based on simulation analysis and intelligent classification algorithm according to claim 1 is characterized in that: The diagnostic model is trained using a gradient boosting machine algorithm.

6. The transformer winding deformation rapid diagnosis method based on simulation analysis and intelligent classification algorithm according to claim 1 is characterized in that: The fault types include: Radial deformation, radial displacement and axial displacement.

7. The transformer winding deformation rapid diagnosis method based on simulation analysis and intelligent classification algorithm according to claim 1 is characterized in that: The winding equivalent circuit model is determined by calculating the equivalent circuit model parameters using a transformer simulation model.

8. A rapid diagnosis device for transformer winding deformation based on simulation analysis and intelligent classification algorithm, characterized in that: include: A data acquisition module, used for acquiring frequency response data of the winding using an equivalent circuit model of the winding of the transformer to be studied; A first index calculation module, used for comparing the frequency response data of the winding with the frequency response data of the winding in a normal state to obtain a plurality of difference measurement indicators; A second indicator calculation module is used to perform feature combination on a plurality of the difference measurement indicators to obtain a plurality of composite feature indicators, each of which is formed by merging at least two of the difference measurement indicators; The diagnostic module is used to input several of the difference measurement indicators and the composite feature indicators into a trained diagnostic model to obtain a winding deformation diagnosis result. The diagnostic model is based on the difference measurement indicators and the composite feature indicators under different fault types and is trained with the corresponding fault types as labels.

9. A computer device, characterized in that: The device comprises a processor and a memory: The memory is used to store a computer program and send instructions of the computer program to the processor; The processor executes a transformer winding deformation rapid diagnosis method based on simulation analysis and intelligent classification algorithm as described in any one of claims 1 to 7 according to the instructions of the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method for quickly diagnosing transformer winding deformation based on simulation analysis and intelligent classification algorithm as described in any one of claims 1 to 7 is implemented.

Images