Method for evaluating anti-short-circuit checking capability of transformer winding

Abstract

The invention provides a transformer winding anti-short circuit checking capability evaluation method, which belongs to the technical field of transformer winding anti-short circuit, and comprises the following steps: firstly, establishing an electromagnetic force thermal calculation model, inputting related material characteristic data, and obtaining stress and temperature distribution data through electromagnetic force thermal coupling calculation; establishing an anti-short-circuit capability key factor influence database; then short-circuit working condition data are collected in real time, and weights and correlation coefficients of all factors are obtained through analysis in combination with a database; and verifying the accuracy of the calculation model through a short-circuit stress test of the transformer winding, finally establishing an anti-short-circuit capability evaluation model, and calculating to obtain an evaluation vector containing various evaluation coefficients as an evaluation result of the anti-short-circuit checking capability of the transformer winding. According to the transformer winding anti-short-circuit checking capability evaluation method provided by the invention, the problems that key physical factors influencing the winding strength are not comprehensively considered and the evaluation precision needs to be improved in the existing transformer winding anti-short-circuit checking capability evaluation method are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of transformer winding short - circuit resistance, and specifically relates to a method for evaluating the short - circuit resistance checking ability of a transformer winding. Background Art

[0002] Transformer windings are most severely affected by short - circuit faults. Short - circuit faults will bring huge electromagnetic forces and heat shocks to the windings, which will further lead to serious consequences such as mechanical damage and insulation failure of the windings. Therefore, how to accurately evaluate the short - circuit resistance ability of transformer windings is crucial for improving the reliability and extending the service life of transformers.

[0003] Currently, the evaluation of the short - circuit resistance ability of transformer windings mainly relies on empirical formulas or simple analysis methods. For example, based on factors such as winding structure parameters and current magnitude, semi - empirical formulas are used to calculate the electromagnetic force of the winding during short - circuit, and then whether the winding can withstand is judged according to the mechanical properties and insulation withstand voltage characteristics of the materials. Although this method is simple and easy to implement, due to ignoring some key factors such as temperature distribution and stress - strain effects on the winding strength, the evaluation results often have certain deviations. Other methods use numerical calculation means such as finite element analysis to couple and simulate the electromagnetic field, thermal field and stress distribution of the winding, and compare and verify with test results. This method is more comprehensive, but at the same time more complex, requiring a large number of input parameters and complex model establishment, and is difficult to promote in engineering applications.

[0004] Generally speaking, the existing methods for evaluating the short - circuit resistance ability of transformer windings have the problem that they fail to comprehensively consider the key physical factors affecting the winding strength, and the evaluation accuracy needs to be improved, which restricts the further development and application of the evaluation methods for transformer short - circuit resistance ability. Summary of the Invention

[0005] In view of this, the present invention provides a method for evaluating the short - circuit resistance checking ability of a transformer winding, which can solve the problem that the existing methods for evaluating the short - circuit resistance ability of transformer windings fail to comprehensively consider the key physical factors affecting the winding strength and the evaluation accuracy needs to be improved.

[0006] The present invention is implemented as follows:

[0007] The present invention provides a method for evaluating the short - circuit resistance checking ability of a transformer winding, including the following steps:

[0008] S10. Establish a calculation model of electromagnetic force and heat for the short - circuit resistance ability of the transformer winding, and input the stress - strain curve data of the wire and spacer under different temperature conditions into the calculation model;

[0009] S20. Perform electromagnetic-force-thermal coupling calculations using the calculation model to obtain stress distribution data and temperature distribution data of the transformer winding under short-circuit conditions;

[0010] S30. Establish a database of the influencing factors of the short-circuit resistance ability of the transformer winding based on the stress distribution data and temperature distribution data;

[0011] S40. Real-time collect data on the number of short-circuit impacts, the magnitude of the short-circuit current, and the duration of the short circuit of the transformer;

[0012] S50. Analyze and process the data on the number of short-circuit impacts, the magnitude of the short-circuit current, and the duration of the short circuit using the database of the influencing factors of the short-circuit resistance ability of the transformer winding to obtain the weight coefficients and correlation coefficients of the influence of each key factor on the short-circuit resistance ability;

[0013] S60. Conduct a short-circuit force test on the transformer winding to obtain test data, and use the test data to verify the calculation results of the calculation model;

[0014] S70. Establish an evaluation model for the short-circuit resistance ability of the transformer, and input the data on the number of short-circuit impacts, the magnitude of the short-circuit current, and the duration of the short circuit into the evaluation model for the short-circuit resistance ability of the transformer;

[0015] S80. Calculate an evaluation vector for the short-circuit resistance ability of the transformer winding based on the evaluation model for the short-circuit resistance ability of the transformer, and use it as the evaluation result of the short-circuit resistance checking ability of the transformer winding.

[0016] Based on the above technical solution, an evaluation method for the short-circuit resistance checking ability of a transformer winding according to the present invention can be further improved as follows:

[0017] Among them, the calculation model includes an electromagnetic force calculation equation, a temperature distribution equation, a stress distribution equation, a strain distribution equation, a material property equation, a heat conduction equation, and a displacement calculation equation.

[0018] Further, the electromagnetic force calculation equation is used to calculate the radial force and axial force when the transformer winding is short-circuited;

[0019] The temperature distribution equation is used to calculate the temperature field distribution when the transformer winding is short-circuited;

[0020] The stress distribution equation is used to calculate the stress distribution of the transformer winding under the action of electromagnetic force;

[0021] The strain distribution equation is used to calculate the strain distribution of the transformer winding under the action of stress;

[0022] The material property equation is used to describe the mechanical properties of the wire and spacer materials at different temperatures;

[0023] The heat conduction equation is used to calculate the heat transfer between different parts of the transformer winding;

[0024] The displacement calculation equation is used to calculate the deformation displacement of the transformer winding under the action of electromagnetic force.

[0025] Furthermore, the test data specifically includes the radial deformation amount of the winding, the axial displacement amount, the winding temperature rise value, the short-circuit current waveform data, and the short-circuit duration data.

[0026] Furthermore, the short-circuit withstand capacity evaluation model includes a stress evaluation equation, a deformation evaluation equation, and a temperature evaluation equation.

[0027] Furthermore, the stress evaluation equation is used to evaluate the deviation degree between the actual stress of the winding and the allowable stress;

[0028] The deformation evaluation equation is used to evaluate the deviation degree between the actual deformation of the winding and the critical deformation;

[0029] The temperature evaluation equation is used to evaluate the deviation degree between the actual temperature rise of the winding and the allowable temperature rise.

[0030] Furthermore, the evaluation vector specifically includes a radial resistance coefficient, an axial stability coefficient, an insulation thermal stability coefficient, and a life prediction coefficient.

[0031] Furthermore, the short-circuit force test of the transformer winding is carried out by using the following transformer winding short-circuit force test device.

[0032] Furthermore, the transformer winding short-circuit force test device includes:

[0033] Test cylinder system: It is composed of a test cylinder with a vertical cylindrical structure. The bottom of the test cylinder is fixed on the base, and a simplified upper cover plate is arranged at the top to enclose the test space;

[0034] Mechanical loading system: It includes two core components, a hydraulic cylinder and a loading disc. The hydraulic cylinder is fixed on the base, its piston rod extends upward and is fixedly connected to the loading disc. An annular groove is designed on the loading disc for placing the winding to be tested;

[0035] Displacement measurement system: Two radial displacement sensors and two axial displacement sensors are installed. The radial displacement sensors are fixed on both sides of the test cylinder through mounting seats, and the sensor probes are in contact with the winding to be tested; the axial displacement sensors are fixed at the upper and lower ends of the test cylinder.

[0036] Furthermore, the electromagnetic force calculation equation is specifically expressed as follows:

[0037]

[0038] In the formula, Fr is the radial electromagnetic force (N); F z is the axial electromagnetic force (N); μ0 is the vacuum permeability, with a value of 4π×10 - 7 H / m; I is the short-circuit current (A); N is the number of winding turns; h is the winding height (m); r1 and r2 are the inner and outer winding radii (m) respectively; r is the radial position of the calculation point (m); h1 and h2 are the upper and lower boundary positions of the calculation point (m); α1, α2, β1, and β2 are correction factors related to the winding structure, obtained through experimental calibration.

[0039] Furthermore, the temperature distribution equation is specifically expressed as follows:

[0040]

[0041] In the formula, ρ is the material density (kg / m 3 ); c p is the specific heat capacity (J / (kg·K)); T is the temperature (K); t is the time (s); λ is the thermal conductivity (W / (m·K)); q v is the heat generation rate per unit volume (W / m 3 ); σ is the Stefan-Boltzmann constant, with a value of 5.67×10 -8 W / (m 2 ·K 4 ); T0 is the ambient temperature (K).

[0042] Furthermore, the stress distribution equation is specifically expressed as follows:

[0043]

[0044] In the formula, σ r , σ θ , σ z are the radial, circumferential, and axial stresses (Pa) respectively; E is the elastic modulus (Pa); v is the Poisson's ratio; ε r , ε θ , ε z are the radial, circumferential, and axial strains respectively; γ1, γ2, γ3, η1, η2, and η3 are temperature influence coefficients, obtained through material tests.

[0045] Furthermore, the strain distribution equation is specifically expressed as follows:

[0046]

[0047]

[0048] In the formula, α is the linear expansion coefficient (1 / K); ΔT is the temperature change (K); ur , u θ , u z are the radial, circumferential, and axial displacements (m), respectively; κ1, κ2, and κ3 are displacement correction coefficients.

[0049] Furthermore, the material property equation is specifically expressed as follows:

[0050] E(T) = E0[1 - δ1(T - T0) - δ2(T - T0) 2 ;

[0051] σ y (T) = σ y0 [1 - ξ1(T - T0) - ξ2(T - T0) 2 ;

[0052] α(T) = α0[1 + χ1(T - T0) + χ2(T - T0) 2 ;

[0053] In the formula, E0 is the elastic modulus at the reference temperature (Pa); σ y0 is the yield strength at the reference temperature (Pa); α0 is the linear expansion coefficient at the reference temperature (1 / K); δ1, δ2, ξ1, ξ2, χ1, and χ2 are temperature-related coefficients obtained through material property tests.

[0054] Furthermore, the heat conduction equation is specifically expressed as follows:

[0055]

[0056] In the formula, h c is the convective heat transfer coefficient (W / (m 2 ·K)); T f is the temperature of the cooling medium (K); ε is the emissivity; T ∞ is the ambient temperature (K); q v can be expressed as:

[0057]

[0058] where R is the winding resistance (Ω); V is the volume of the calculation unit (m 3 ); φ1 and φ2 are temperature correction coefficients.

[0059] Furthermore, the displacement calculation equation is specifically expressed as follows:

[0060]

[0061] In the formula, the left side term is the acceleration term, the first right side term is the displacement caused by elastic deformation, and the second right side term is the displacement caused by electromagnetic force.

[0062] Furthermore, the stress evaluation equation is specifically expressed as follows:

[0063]

[0064] In the formula, η σ is the stress evaluation index; σ i is the actual stress (Pa); σ i,allow is the allowable stress (Pa); w i is the weight coefficient; p i is the power term, reflecting the penalty degree of stress overrun; Δt is the duration (s); τ i is the characteristic time constant (s); i = 1, 2, 3 correspond to the radial, circumferential, and axial directions respectively.

[0065] Furthermore, the deformation evaluation equation is specifically expressed as follows:

[0066]

[0067] In the formula, η d is the deformation evaluation index; d j is the actual deformation (m); d j,crit is the critical deformation (m); v j is the weight coefficient; q j is the power term; μ j is the deformation rate influence coefficient; j = 1, 2 correspond to the radial and axial directions respectively.

[0068] Furthermore, the temperature evaluation equation is specifically expressed as follows:

[0069]

[0070] In the formula, η T is the temperature evaluation index; T max is the highest temperature (K); T allow is the allowable temperature (K); t c is the short - circuit duration (s); ω1, ω2 are the weight coefficients; m, n are the power terms.

[0071] Furthermore, it further includes step S90: performing feature analysis on the evaluation vector using a preset neural network classifier, and issuing a warning when any evaluation coefficient is lower than the preset threshold.

[0072] The process of establishing a training data set for a preset neural network classifier used to evaluate the short - circuit resistance ability of transformer windings needs to comprehensively consider historical operation data and test data from multiple dimensions. It mainly includes basic data such as the magnitude of short - circuit current, short - circuit duration, and number of impacts in historical short - circuit accident records, as well as the corresponding evaluation results of winding damage degree. At the same time, it is also necessary to collect basic parameters such as winding deformation, temperature rise value, and insulation condition under normal operation of the transformer, and classify and label these data in combination with expert experience to establish a standard training sample set containing input feature vectors and corresponding grade labels. In the data pre - processing stage, it is necessary to normalize all the collected data to eliminate the influence of different feature dimensions, and use the principal component analysis method to reduce the dimensionality of features and extract the most representative feature combinations. At the same time, through data augmentation technology, the quantity and type coverage of the training sample set are expanded to improve the generalization ability of the model.

[0073] The neural network classifier adopts a multi - layer perceptron structure. The number of nodes in the input layer corresponds to the dimension of the feature vector and includes key evaluation indicators such as radial resistance coefficient, axial stability coefficient, insulation thermal stability coefficient, and life prediction coefficient. The hidden layer adopts a three - layer structure, and the number of nodes in each layer decreases sequentially. The ReLU activation function is used to enhance the non - linear expression ability of the network, and a Dropout layer is added between the hidden layers to prevent overfitting. The number of nodes in the output layer corresponds to the preset number of grade divisions, and the Softmax function is used for multi - classification probability output. During the training process, cross - entropy is used as the loss function, the Adam optimizer is used for parameter optimization, and the batch training method is adopted to gradually adjust the network weights. At the same time, the model performance is evaluated through the cross - validation method, and the learning rate and number of training epochs are dynamically adjusted according to the validation results until the model converges to an ideal state. Finally, an independent test data set is used to evaluate the performance of the trained model to ensure that the model has good classification accuracy and generalization ability.

[0074] Compared with the prior art, a method for evaluating the short - circuit checking ability of transformer windings provided by the present invention establishes a calculation model covering key physical quantities such as electromagnetic force, temperature field, stress and strain, and verifies the model through material performance tests and winding short - circuit force tests to ensure the accuracy of the calculation results. On this basis, the present invention constructs an evaluation model for the short - circuit resistance ability of transformers that comprehensively considers stress, deformation, and temperature rise, and proposes a feature analysis method based on neural networks, which can more accurately diagnose the key factors affecting the short - circuit resistance ability of windings and provide strong support for the design optimization and operation and maintenance of transformers. The beneficial effects of the present invention are:

[0075] 1. A coupled calculation model covering multiple physical fields such as electromagnetic force, temperature field, stress and strain is established, which is more comprehensive than the existing empirical formulas or simple analysis methods, and the calculation results are more accurate and reliable.

[0076] 2. The calculation model was verified by material property tests and short-circuit force tests on windings, ensuring the rationality and reliability of the model and making up for the lack of experimental verification in existing methods.

[0077] 3. A comprehensive evaluation model based on stress, deformation and temperature rise was constructed, which can more comprehensively diagnose the key factors affecting the short-circuit resistance of windings and provide a basis for the design optimization of transformers.

[0078] 4. Neural networks were used to analyze the characteristics of the evaluation results, which can timely detect potential hazards of reduced short-circuit resistance of windings and provide support for preventive maintenance.

[0079] In summary, the method for evaluating the short-circuit resistance of transformer windings proposed in the present invention has great innovations in aspects such as calculation model establishment, experimental verification, comprehensive evaluation and automatic diagnosis. It can greatly improve the evaluation accuracy and reliability of the short-circuit resistance of transformer windings, and solve the problem that the existing methods for evaluating the short-circuit resistance of transformer windings fail to comprehensively consider the key physical factors affecting the winding strength and the evaluation accuracy needs to be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Figure 1 is a flowchart of the method provided by the present invention;

[0081] Figure 2 is a schematic diagram of a short-circuit force test device for transformer windings;

[0082] Figure 3 is a curve graph of the temperature change of three windings during the short-circuit process in the embodiment;

[0083] Figure 4 is a graph showing the changes of radial stress, circumferential stress and axial stress with time during the short-circuit process in the embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0084] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0085] As Figure 1 shown, it is a flowchart of a method for evaluating the short-circuit checking ability of transformer windings provided by the present invention. This method includes the following steps:

[0086] S10. Establish an electromagnetic force-thermal calculation model for the short-circuit resistance of transformer windings, and input the stress-strain curve data of wires and spacers under different temperature conditions into the calculation model;

[0087] S20. Perform electromagnetic-force and thermal coupling calculations using a computational model to obtain stress distribution data and temperature distribution data of the transformer winding under short-circuit conditions;

[0088] S30. Establish a database of the influencing key factors for the short-circuit withstand ability of the transformer winding based on the stress distribution data and temperature distribution data;

[0089] S40. Collect in real-time data on the number of short-circuit impulses, the magnitude of the short-circuit current, and the short-circuit duration of the transformer;

[0090] S50. Use the database of the influencing key factors for the short-circuit withstand ability of the transformer winding to analyze and process the data on the number of short-circuit impulses, the magnitude of the short-circuit current, and the short-circuit duration, and obtain the weight coefficients and correlation coefficients of the influence of each key factor on the short-circuit withstand ability;

[0091] S60. Conduct a short-circuit force test on the transformer winding to obtain test data, and use the test data to verify the calculation results of the computational model;

[0092] S70. Establish an evaluation model for the short-circuit withstand ability of the transformer, and input the data on the number of short-circuit impulses, the magnitude of the short-circuit current, and the short-circuit duration into the evaluation model for the short-circuit withstand ability of the transformer;

[0093] S80. Calculate an evaluation vector for the short-circuit withstand ability of the transformer winding based on the evaluation model for the short-circuit withstand ability of the transformer, and use it as the evaluation result of the short-circuit withstand checking ability of the transformer winding.

[0094] As Figure 2 shown, the short-circuit force test on the transformer winding is carried out using the following short-circuit force test device for the transformer winding. The short-circuit force test device for the transformer winding includes:

[0095] Test cylinder system: It consists of a test cylinder with a vertical cylindrical structure. The bottom of the test cylinder is fixed on the base, and a simplified upper cover plate is provided at the top to enclose the test space;

[0096] Mechanical loading system: It includes two core components, a hydraulic cylinder and a loading plate. The hydraulic cylinder is fixed on the base, and its piston rod extends upward and is fixedly connected to the loading plate. An annular groove is designed on the loading plate for placing the winding to be tested;

[0097] Displacement measurement system: Two radial displacement sensors and two axial displacement sensors are installed. The radial displacement sensors are fixed on both sides of the test cylinder through mounting seats, and the sensor probes are in contact with the winding to be tested; the axial displacement sensors are fixed at the upper and lower ends of the test cylinder.

[0098] The acquisition of test data on the short-circuit force of transformer windings is a crucial step in evaluating the short-circuit resistance of transformer windings. Through systematic test procedures, important parameters such as the radial deformation of the winding, axial displacement, winding temperature rise, short-circuit current waveform data, and short-circuit duration data can be comprehensively and accurately collected. Before officially conducting the test, a comprehensive inspection and calibration of the test equipment are required to ensure that all measuring devices and sensors are in normal working condition, and the test environmental conditions are recorded, including factors such as environmental temperature and humidity that may affect the test results.

[0099] First, a detailed visual inspection and dimensional measurement of the transformer winding to be tested are needed. Record the initial state parameters of the winding, including key dimensions such as the outer diameter, inner diameter, and height of the winding, and conduct a comprehensive inspection of the winding surface condition and the integrity of the insulating material to ensure the integrity and reliability of the reference data before the test. After completing the initial inspection, carefully install the winding to be tested on the loading plate of the test equipment, adjust the position of the winding to accurately correspond to the measurement points of the radial displacement sensor, and ensure that the axial displacement sensor can accurately capture the axial movement of the winding. To ensure measurement accuracy, the installation position and initial readings of the displacement sensors need to be repeatedly verified to ensure that all sensors are in the best working condition.

[0100] Before entering the formal test stage, appropriate test conditions need to be set according to the design parameters of the winding to be tested, including parameters such as the magnitude of the mechanical load applied, the load application rate, and the duration. In the test process, a step-by-step loading method is adopted, gradually increasing from a lower load level to the design load value. Each load level needs to be maintained for a sufficient stable time to obtain steady-state data. During the load application process, the output data of the radial displacement sensor and the axial displacement sensor are recorded in real-time through a high-precision data acquisition system, and the temperature change of the winding is monitored simultaneously. To ensure the reliability of the data, multiple repeated measurements are required at each load level, and the measurement results are statistically analyzed to eliminate abnormal data points.

[0101] The measurement of the short-circuit current is another important part of the test. A current sensor with high-frequency sampling is needed to accurately capture the current waveform during the short-circuit transient process. By analyzing the current waveform data, characteristic parameters such as the peak value, effective value, and waveform distortion of the short-circuit current can be obtained. At the same time, the duration of each short-circuit impact needs to be accurately recorded, which is of great significance for evaluating the thermal effect during the short-circuit process. During the short-circuit test, the temperature distribution of each part of the winding also needs to be monitored in real-time through equipment such as an infrared thermal imager, and the temperature rise data is recorded. These data have important reference value for evaluating the thermal stability of the winding.

[0102] After completing the preset test conditions, it is necessary to unload the winding and observe and record the rebound characteristics and residual deformation of the winding. By comparing the dimensional data before and after the test, the degree of plastic deformation of the winding under short-circuit impact can be evaluated. At the same time, a detailed visual inspection of the winding is required to record any possible damage or deformation marks. To ensure the integrity of the test data, it is also necessary to test the insulation performance of the winding to evaluate the impact of short-circuit impact on the insulation system.

[0103] The post-processing of test data is an important part of the entire test process, and the collected raw data needs to be systematically sorted and analyzed. First, the validity of the data needs to be verified, and abnormal data caused by equipment failures or external interferences should be excluded. Then, statistical analysis is performed on the valid data to calculate statistical characteristics such as the mean and standard deviation of various parameters, and to evaluate the degree of data dispersion. For short-circuit current waveform data, Fourier analysis needs to be performed to extract spectral characteristics and evaluate the degree of waveform distortion. At the same time, it is necessary to establish a relationship curve between the radial deformation amount, axial displacement amount, and applied load to analyze the mechanical response characteristics of the winding.

[0104] Finally, all test data is systematically sorted and archived, including test condition records, original measurement data, processed analysis results, and records of special phenomena during the test process, etc.

[0105] The specific implementation methods of the above steps are described in detail below:

[0106] The specific implementation method of step S10 is as follows: First, an electromagnetic-force-thermal calculation model for the short-circuit withstand ability of the transformer winding is established, and the stress-strain curve data of the conductor and spacer under different temperature conditions are input into this calculation model. This calculation model includes electromagnetic force calculation equations, temperature distribution equations, stress distribution equations, strain distribution equations, material property equations, heat conduction equations, and displacement calculation equations.

[0107] The electromagnetic force calculation equation is used to calculate the radial force and axial force when the transformer winding is short-circuited. Among them, the radial electromagnetic force F r can be expressed as The axial electromagnetic force F z can be expressed as where μ0 is the vacuum permeability, I is the short-circuit current, N is the number of winding turns, h is the winding height, r1 and r2 are the inner and outer winding radii respectively, r is the radial position of the calculation point, h1 and h2 are the upper and lower boundary positions of the calculation point, and α1, α2, β1, β2 are correction coefficients related to the winding structure, which are obtained through experimental calibration.

[0108] The temperature distribution equation is used to calculate the temperature field distribution when the transformer winding is short-circuited, and its specific expression is where ρ is the material density, cp where \(c_p\) is the specific heat capacity, \(T\) is the temperature, \(t\) is the time, \(\lambda\) is the thermal conductivity, and \(q\) v is the heat generation rate per unit volume, \(\sigma\) is the Stefan–Boltzmann constant, and \(T_0\) is the ambient temperature.

[0109] The stress distribution equation is used to calculate the stress distribution in the transformer winding under the action of electromagnetic force, and is specifically expressed as where \(\sigma\) r , \(\sigma\) θ , \(\sigma\) z are the radial, circumferential, and axial stresses respectively, \(E\) is the elastic modulus, \(v\) is the Poisson's ratio, and \(\varepsilon\) r , \(\varepsilon\) θ , \(\varepsilon\) z are the radial, circumferential, and axial strains respectively, and \(\gamma_1\), \(\gamma_2\), \(\gamma_3\), \(\eta_1\), \(\eta_2\), \(\eta_3\) are the temperature influence coefficients, which are obtained through material tests.

[0110] The strain distribution equation is used to calculate the strain distribution in the transformer winding under the action of stress, and is specifically expressed as where \(\alpha\) is the coefficient of linear expansion, \(\Delta T\) is the temperature change, and \(u\) r , \(u\) θ , \(u\) z are the radial, circumferential, and axial displacements respectively, and \(\kappa_1\), \(\kappa_2\), \(\kappa_3\) are the displacement correction coefficients.

[0111] The material property equation is used to describe the mechanical properties of the conductor and spacer materials at different temperatures, and is specifically expressed as \(E(T)=E_0[1 - \delta_1(T - T_0)-\delta_2(T - T_0) 2 , \(\sigma\) y (T)=\sigma y0 [1 - \xi_1(T - T_0)-\xi_2(T - T_0) 2 , \(\alpha(T)=\alpha_0[1+\chi_1(T - t_0)+\chi_2(T - T_0) 2 . Here, \(E_0\) is the elastic modulus at the reference temperature, \(\sigma\) y0 is the yield strength at the reference temperature, \(\alpha_0\) is the coefficient of linear expansion at the reference temperature, and \(\delta_1\), \(\delta_2\), \(\xi_1\), \(\xi_2\), \(\chi_1\), \(\chi_2\) are the temperature-related coefficients, which are obtained through material property tests.

[0112] The heat conduction equation is used to calculate the heat transfer between different parts of the transformer winding, and is specifically expressed as where h c is the convective heat transfer coefficient, \(T\) f is the temperature of the cooling medium, \(\varepsilon\) is the emissivity, \(T\) ∞ is the ambient temperature, and \(q\) v can be expressed as Wherein, R is the winding resistance, V is the volume of the calculation unit, and φ1, φ2 are temperature correction coefficients.

[0113] The displacement calculation equation is used to calculate the deformation displacement of the transformer winding under the action of electromagnetic force, and is specifically expressed as Wherein, the left term is the acceleration term, the first right term is the displacement caused by elastic deformation, and the second right term is the displacement caused by electromagnetic force.

[0114] By establishing the above electromagnetic force-thermal coupling calculation model, the stress distribution and temperature distribution data of the transformer winding under short-circuit conditions can be obtained. This calculation model covers various key physical processes of the transformer winding under short-circuit conditions, providing important basic data for the subsequent evaluation of the short-circuit resistance ability of the winding.

[0115] The specific implementation manner of step S20 is: performing electromagnetic force-thermal coupling calculation using the above calculation model to obtain the stress distribution data and temperature distribution data of the transformer winding under short-circuit conditions. The purpose of this step is to obtain the key physical quantity data of the transformer winding during short-circuit, laying a foundation for the subsequent analysis of the short-circuit resistance ability of the winding.

[0116] The specific implementation manner of step S30 is: based on the stress distribution data and temperature distribution data obtained in step S20, establish a database of the influencing factors of the key factors of the short-circuit resistance ability of the transformer winding. This database records the influence degree of each key factor on the short-circuit resistance ability of the winding, providing a reference for the subsequent evaluation of the short-circuit resistance ability of the winding. Specifically, this database includes but is not limited to the following key factors and their influence degrees:

[0117] 1) Magnitude of short-circuit current: The larger the short-circuit current, the greater the electromagnetic force on the winding, and the more serious the influence on the stress and temperature rise of the winding.

[0118] 2) Short-circuit duration: The longer the short-circuit duration, the longer the heating time of the winding, the greater the temperature rise, and the greater the influence on the mechanical properties of the winding material.

[0119] 3) Number of short-circuit impacts: The more the number of short-circuit impacts, the more serious the fatigue damage of the winding, and the weaker the short-circuit resistance ability.

[0120] 4) Winding structure parameters: Such as winding height, inner and outer diameters, etc. These parameters will affect the force and heat conduction characteristics of the winding, thereby affecting the short-circuit resistance ability.

[0121] 5) Material property parameters: Such as elastic modulus, yield strength, thermal expansion coefficient of wires and spacers, etc. The temperature-dependent characteristics of these parameters will directly affect the stress and deformation of the winding during short-circuit.

[0122] By establishing a database that affects key factors in this way, it can provide important references for subsequent short-circuit resistance evaluation.

[0123] The specific implementation of step S40 is as follows: Real-time collect data on the number of short-circuit impacts, the magnitude of short-circuit current, and the duration of short-circuit during the operation of the transformer. These data reflect the short-circuit load conditions faced by the transformer during actual operation and are important bases for evaluating the short-circuit resistance of the winding. It should be noted that these data should be collected in real time using reliable sensors and measurement systems and stored in the database for future use.

[0124] The specific implementation of step S50 is as follows: Use the database of key factor impacts on the short-circuit resistance of the transformer winding established in step S30 to analyze and process the data on the number of short-circuit impacts, the magnitude of short-circuit current, and the duration of short-circuit collected in step S40. Specifically, through statistical analysis and data mining methods, obtain the weight coefficients and correlation coefficients of each key factor on the short-circuit resistance.

[0125] The weight coefficient reflects the relative importance of a certain factor to the short-circuit resistance of the winding. For example, the weight coefficient of the magnitude of short-circuit current may be higher than that of the duration of short-circuit, indicating that the current magnitude has a more critical impact on the short-circuit resistance of the winding.

[0126] The correlation coefficient represents the degree of association between a certain factor and the short-circuit resistance of the winding. For example, there may be a strong positive correlation between the number of short-circuit impacts and the fatigue damage of the winding, that is, the more the number of impacts, the weaker the short-circuit resistance of the winding.

[0127] Through the weight and correlation analysis of these key factors, the key factors affecting the short-circuit resistance of the transformer winding can be diagnosed more accurately, providing an important basis for subsequent short-circuit resistance evaluation.

[0128] The specific implementation of step S60 is as follows: Conduct a short-circuit force test on the transformer winding to obtain test data and use these test data to verify the calculation results of the above calculation model. The specific test device includes:

[0129] 1) Test cylinder: An upright cylindrical structure made of transparent organic glass, with the bottom of the cylinder fixed on the base, and a feed inlet and an upper cover assembly provided at the top.

[0130] 2) Mechanical loading mechanism: It includes a hydraulic cylinder and a loading plate. The hydraulic cylinder is fixed on the base, the top of the piston rod is connected to the loading plate, and an annular groove for placing the winding to be tested is provided on the loading plate.

[0131] 3) Displacement measurement mechanism: It includes 4 radial displacement sensors evenly distributed along the circumference of the test cylinder and 2 axial displacement sensors located at the upper and lower ends of the cylinder, which are used to measure the radial and axial deformations of the winding under short-circuit conditions.

[0132] 4) Other configurations: The upper cover assembly has an oil injection port and an exhaust port, and is provided with an observation window; an oil medium can be injected into the test cylinder to simulate the cooling conditions of an actual transformer.

[0133] Through this test device, key test data such as the radial deformation amount of the winding, the axial displacement amount, the winding temperature rise value, the short-circuit current waveform data, and the short-circuit duration data can be obtained. These test data will be used to verify the accuracy and reliability of the aforementioned calculation model to ensure that the calculation results can accurately reflect the physical behavior of the actual transformer winding under short-circuit conditions.

[0134] The specific implementation of step S70 is: Establish an evaluation model for the short-circuit resistance ability of the transformer. This model includes three parts: a stress evaluation equation, a deformation evaluation equation, and a temperature evaluation equation.

[0135] The stress evaluation equation is used to evaluate the deviation degree between the actual stress of the winding and the allowable stress, and its expression is where, η σ is the stress evaluation index, σ i is the actual stress, σ i,allow is the allowable stress, w i is the weight coefficient, p i is the power term, Δt is the duration, τ i is the characteristic time constant, and i = 1, 2, 3 correspond to the radial, circumferential, and axial directions respectively.

[0136] The deformation evaluation equation is used to evaluate the deviation degree between the actual deformation of the winding and the critical deformation, and its expression is where, η d is the deformation evaluation index, d j is the actual deformation amount, d j,crit is the critical deformation amount, v j is the weight coefficient, q j is the power term, μ j is the deformation rate influence coefficient, and j = 1, 2 correspond to the radial and axial directions respectively.

[0137] The temperature evaluation equation is used to evaluate the deviation degree between the actual temperature rise of the winding and the allowable temperature rise, and its expression is where, η T is the temperature evaluation index, T max is the highest temperature, T allow is the allowable temperature, t c is the short-circuit duration, ω1, ω2 are the weight coefficients, and m, n are the power terms.

[0138] These three evaluation equations take the data of the number of short - circuit shocks, the magnitude of short - circuit current, and the short - circuit duration collected in step S40 as inputs, comprehensively consider the effects of stress, deformation, and temperature rise on the short - circuit resistance ability of the winding, and give a comprehensive short - circuit resistance ability evaluation vector.

[0139] The specific implementation of step S80 is: Based on the transformer short - circuit resistance ability evaluation model established in step S70, calculate the short - circuit resistance ability evaluation vector of the transformer winding. This evaluation vector specifically includes:

[0140] 1) Radial resistance coefficient: Reflects the radial short - circuit resistance ability of the winding, and is affected by the comprehensive influence of electromagnetic force, stress, and temperature rise.

[0141] 2) Axial stability coefficient: Reflects the axial short - circuit resistance ability of the winding, and is affected by the comprehensive influence of axial electromagnetic force, stress, and deformation.

[0142] 3) Insulation thermal stability coefficient: Reflects the thermal stability of the insulation material of the winding, and is affected by temperature rise.

[0143] 4) Life prediction coefficient: Reflects the degree of fatigue damage of the winding under the action of short - circuit cycles, and is affected by the number of short - circuit shocks.

[0144] These four evaluation coefficients comprehensively consider the key physical quantities of the transformer winding under short - circuit conditions and can comprehensively evaluate its short - circuit resistance ability. When any one of the evaluation coefficients is lower than the preset threshold, the system will issue a warning signal to remind the user to perform necessary maintenance and repair.

[0145] Specifically, the principle of the present invention is:

[0146] 1. Establish an electromagnetic - force - thermal coupling calculation model: The transformer winding will be subjected to severe electromagnetic - force shocks and temperature rises under short - circuit faults, resulting in a reduction in mechanical strength and insulation failure. Therefore, accurately calculating the electromagnetic - force distribution, temperature - field distribution, and stress - strain state of the winding under short - circuit conditions is the key to evaluating its short - circuit resistance ability. The present invention uses numerical calculation methods such as finite - element analysis to establish a coupling model covering electromagnetic - force calculation equations, temperature - distribution equations, stress - distribution equations, material - property equations, etc., which can comprehensively simulate the physical behavior of the winding in the short - circuit state. It should be noted that some correction coefficients related to the winding structure and material properties are included in these equations and need to be calibrated through experimental data to ensure the accuracy of the calculation results.

[0147] 2. Conduct winding short - circuit force test verification: To verify the reliability of the above - mentioned calculation model, the present invention designs a special transformer winding short - circuit force test device. This device includes a test cylinder, a mechanical loading mechanism, and a displacement measurement mechanism, which can measure the deformation behavior of the transformer winding under simulated short - circuit conditions. By comparing the calculation results with the test data, the model parameters can be calibrated and verified to ensure that the calculation model can accurately reflect the physical behavior of the actual winding.

[0148] 3. Establish a comprehensive evaluation model: On the basis of the foregoing calculation model and test verification, the present invention further constructs a set of comprehensive evaluation models for the short - circuit resistance ability of transformer windings. This model includes a stress evaluation equation, a deformation evaluation equation, and a temperature evaluation equation, which can comprehensively consider the stress state, deformation degree, and temperature rise of the winding under short - circuit conditions, and give a comprehensive short - circuit resistance ability evaluation vector. These evaluation indicators reflect the key performance indicators of the transformer winding under short - circuit faults, providing an important basis for transformer design and operation and maintenance.

[0149] 4. Use neural network for feature analysis: To further improve the diagnostic level of the short - circuit resistance ability of transformer windings, the present invention adopts a feature analysis method based on neural networks. Specifically, taking the above - mentioned comprehensive evaluation vector as the input, a pre - trained neural network model is used to extract features and classify it, so as to obtain the short - circuit resistance ability level of the transformer winding. When any evaluation index is lower than the preset threshold, the system will issue a warning signal, indicating that corresponding measures need to be taken. This automatic diagnosis method based on machine learning can timely detect potential hazards of the winding's short - circuit resistance ability, providing support for the preventive maintenance of transformers.

[0150] To better understand and implement the present invention, an embodiment of a specific application scenario of the present invention is provided below: A certain power enterprise is responsible for operating and maintaining a three - phase three - winding transformer with a capacity of 500 MVA. This transformer was put into operation in 2020 and has been running for 5 years. To ensure the safe and reliable operation of the transformer, the power enterprise decides to comprehensively evaluate the short - circuit resistance ability of the transformer winding.

[0151] In the first step, establish an electromagnetic - force - heat coupling calculation model for the short - circuit resistance ability of the transformer winding. According to the specific parameters of the transformer, this calculation model includes the following key equations:

[0152] Electromagnetic force calculation equation:

[0153] Radial electromagnetic force

[0154] Axial electromagnetic force

[0155] Among them, μ0 = 4π×10 -7H / m is the magnetic permeability of vacuum, I is the short-circuit current, N is the number of turns of the winding, h is the height of the winding, r1 and r2 are the inner and outer radii of the winding respectively, r is the radial position of the calculation point, h1 and h2 are the upper and lower boundary positions of the calculation point, and α1, α2, β1, and β2 are correction factors related to the winding structure.

[0156] Temperature distribution equation:

[0157]

[0158] Among them, ρ is the material density, c p is the specific heat capacity, T is the temperature, t is the time, λ is the thermal conductivity, q v is the heat generation rate per unit volume, σ = 5.67×10 -8 W / (m 2 ·K 4 ) is the Stefan-Boltzmann constant, and T0 is the ambient temperature. As Figure 3 shown, the temperature change curves of the inner, middle, and outer windings during the short-circuit process are displayed.

[0159] Stress distribution equation:

[0160] Radial stress

[0161] Circumferential stress

[0162] Axial stress

[0163] Among them, E is the elastic modulus, v is the Poisson's ratio, ε r , ε θ , ε z are the radial, circumferential, and axial strains respectively, and γ1, γ2, γ3, η1, η2, η3 are the temperature influence coefficients. As Figure 4 shown, the variation of the radial stress, circumferential stress, and axial stress with time during the short-circuit process is presented. It can be seen that each stress component shows a periodic decay characteristic during the short-circuit process.

[0164] Material property equation:

[0165] Elastic modulus E(T) = E0[1 - δ1(T - T0) - δ2(T - T0) 2 ;

[0166] Yield strength δ y (T) = σ y0 [1 - ξ1(T - T0) - ξ2(T - T0) 2 ;

[0167] Coefficient of linear expansion α(T) = α0[1 + χ1(T - T0) + χ2(T - T0)2 ;

[0168] Among them, E0, σ y0 , and α0 are the elastic modulus, yield strength, and linear expansion coefficient at the reference temperature respectively, and δ1, δ2, ξ1, ξ2, χ1, χ2 are temperature-related coefficients.

[0169] By establishing the above electromagnetic-force-thermal coupling calculation model, the physical behavior of the transformer winding under short-circuit conditions can be simulated. To verify the accuracy of the model, the power enterprise organized a winding short-circuit force test.

[0170] Specifically, a specially designed transformer winding short-circuit force test device was adopted in the test, including a test cylinder made of transparent plexiglass, a hydraulic loading mechanism, and a displacement measurement system. During the test, the winding to be measured was placed on the loading plate, a short-circuit current was applied through the hydraulic cylinder, and at the same time, radial and axial displacement sensors were used to measure the deformation of the winding under the short-circuit effect in real time. During the test process, the temperature distribution inside the winding was also monitored in real time through the observation window.

[0171] Through this test, the power enterprise obtained key parameters such as the radial deformation amount, axial displacement amount, winding temperature rise value, short-circuit current waveform data, and short-circuit duration data of the winding. Comparing these test data with the prediction results of the calculation model, it was found that the two were in good agreement, verifying the accuracy and reliability of the calculation model.

[0172] With a reliable calculation model, the power enterprise then established a database on the influencing key factors of the short-circuit resistance ability of the transformer winding. Through the analysis of a large amount of short-circuit accident data and test results, this database records the influence degrees of factors such as the magnitude of the short-circuit current, short-circuit duration, and number of short-circuit impacts on the winding stress, deformation, and temperature rise. For example, Table 1 gives some key factors and their corresponding influence weights:

[0173] Table 1 Key factors and influence weights of the short-circuit resistance ability of the transformer winding

[0174] Factor Stress influence weight Deformation influence weight Temperature rise influence weight Short-circuit current magnitude 0.45 0.35 0.30 Short-circuit duration 0.35 0.25 0.40 Short-circuit impact times 0.20 0.40 0.30 Winding structure parameters 0.30 0.25 0.15 Material property parameters 0.40 0.15 0.25

[0175] It can be seen from Table 1 that the magnitude of the short-circuit current has the greatest influence on the winding stress, while the short-circuit duration is the most critical for the temperature rise. In addition, the winding structure parameters and material property parameters will also have different degrees of influence on the short-circuit resistance ability.

[0176] With the influence data of the key factors, the power enterprise then collected the data of the number of short-circuit impacts, the magnitude of the short-circuit current, and the short-circuit duration of this transformer during operation. By analyzing these data and combining with the key factor influence database, the relative importance of each factor on the short-circuit resistance ability of this transformer winding can be obtained.

[0177] Table 2 Analysis Results of Transformer Operation Data and Key Factors

[0178] Parameter Value Key factor influence Short-circuit impact times 15 times Larger Short-circuit current magnitude 25 kA Larger Short-circuit duration 0.2s Larger Winding structure parameters - Medium Material property parameters - Medium

[0179] As can be seen from Table 2, the transformer has experienced 15 short - circuit impacts during operation, with a short - circuit current as high as 25 kA and a duration of 0.2 s. These factors have a greater impact on the short - circuit resistance ability of the winding. The impacts of winding structure parameters and material property parameters are relatively small.

[0180] Based on the aforementioned calculation models, experimental verifications, key factor analyses, etc., power enterprises have established a set of models for comprehensively evaluating the short - circuit resistance ability of transformer windings, including:

[0181] Stress evaluation equation:

[0182]

[0183] Among them, η σ is the stress evaluation index, σ i is the actual stress, σ i,allow is the allowable stress, w i is the weight coefficient, p i is the power term, Δt is the duration, τ i is the characteristic time constant, and i = 1, 2, 3 correspond to the radial, circumferential, and axial directions respectively.

[0184] Deformation evaluation equation:

[0185]

[0186] Among them, η d is the deformation evaluation index, d j is the actual deformation, d j,crit is the critical deformation, v j is the weight coefficient, q j is the power term, μ j is the deformation rate influence coefficient, and j = 1, 2 correspond to the radial and axial directions respectively.

[0187] Temperature evaluation equation:

[0188]

[0189] Among them, η T is the temperature evaluation index, T max is the highest temperature, T allow is the allowable temperature, t c is the short - circuit duration, ω1, ω2 are the weight coefficients, and m, n are the power terms.

[0190] Substituting the above transformer operation data into the above evaluation model, the short-circuit resistance evaluation vector of the transformer winding can be obtained:

[0191] Radial resistance coefficient

[0192] Axial stability factor

[0193] Insulation thermal stability coefficient η T =0.75;

[0194] Life prediction coefficient η L =0.72;

[0195] It can be seen that the stress, deformation and temperature rise of the transformer winding under short-circuit conditions have not reached the ideal level, especially the life prediction coefficient is low, indicating that the fatigue damage of the winding is serious. This may be due to the transformer experiencing more short-circuit shocks.

[0196] In order to further diagnose the key factors affecting the short-circuit resistance of the transformer winding, the power company used a pre-trained neural network model to perform feature analysis on the above evaluation vector. The analysis results show that the number of short-circuit impacts has the most significant impact on the life prediction coefficient of the winding, reaching a weight coefficient of 0.75. The short-circuit current and short-circuit duration have the second largest impact on stress and deformation, with weight coefficients of 0.55 and 0.48 respectively.

[0197] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for evaluating the short-circuit withstand checking ability of a transformer winding, characterized in that It includes the following steps: S10. Establish an electromagnetic force - heat calculation model for the short - circuit withstand ability of the transformer winding, and input the stress - strain curve data of the wire and spacer under different temperature conditions into the calculation model; S20. Use the calculation model to perform electromagnetic force - heat coupling calculation to obtain the stress distribution data and temperature distribution data of the transformer winding under short - circuit conditions; S30. Establish a database of the influence of key factors on the short - circuit withstand ability of the transformer winding based on the stress distribution data and temperature distribution data; S40. Real - time collect the data of the number of short - circuit impacts, the magnitude of short - circuit current, and the short - circuit duration of the transformer; S50. Use the database of the influence of key factors on the short - circuit withstand ability of the transformer winding to analyze and process the data of the number of short - circuit impacts, the magnitude of short - circuit current, and the short - circuit duration, and obtain the weight coefficients and correlation coefficients of the influence of each key factor on the short - circuit withstand ability; S60. Conduct a short - circuit force test on the transformer winding to obtain test data, and use the test data to verify the calculation results of the calculation model; S70. Establish an evaluation model for the short - circuit withstand ability of the transformer, and input the data of the number of short - circuit impacts, the magnitude of short - circuit current, and the short - circuit duration into the evaluation model for the short - circuit withstand ability of the transformer; S80. Calculate the evaluation vector of the short - circuit withstand ability of the transformer winding based on the evaluation model for the short - circuit withstand ability of the transformer, and use it as the evaluation result of the short - circuit withstand checking ability of the transformer winding.

2. The evaluation method for the short-circuit withstand checking ability of a transformer winding according to claim 1, characterized in that The calculation model includes an electromagnetic force calculation equation, a temperature distribution equation, a stress distribution equation, a strain distribution equation, a material property equation, a heat conduction equation, and a displacement calculation equation.

3. The method for evaluating the short-circuit withstand checking ability of a transformer winding according to claim 2, wherein The electromagnetic force calculation equation is used to calculate the radial force and axial force when the transformer winding is short - circuited; The temperature distribution equation is used to calculate the temperature field distribution when the transformer winding is short - circuited; The stress distribution equation is used to calculate the stress distribution of the transformer winding under the action of electromagnetic force; The strain distribution equation is used to calculate the strain distribution of the transformer winding under the action of stress; The material property equation is used to describe the mechanical properties of the wire and spacer materials at different temperatures; The heat conduction equation is used to calculate the heat transfer between different parts of the transformer winding; The displacement calculation equation is used to calculate the deformation displacement of the transformer winding under the action of electromagnetic force.

4. The evaluation method for the short-circuit withstand checking ability of a transformer winding according to claim 3, wherein The test data specifically includes the radial deformation amount of the winding, the axial displacement amount, the winding temperature rise value, the short - circuit current waveform data, and the short - circuit duration data.

5. A method for evaluating the short-circuit withstand checking ability of a transformer winding according to claim 4, characterized in that The evaluation model for the short - circuit withstand ability includes a stress evaluation equation, a deformation evaluation equation, and a temperature evaluation equation.

6. The evaluation method for the short-circuit withstand checking ability of a transformer winding according to claim 5, characterized in that, The stress evaluation equation is used to evaluate the deviation degree between the actual stress of the winding and the allowable stress; The deformation evaluation equation is used to evaluate the deviation degree between the actual deformation of the winding and the critical deformation; The temperature evaluation equation is used to evaluate the deviation degree between the actual temperature rise of the winding and the allowable temperature rise.

7. The evaluation method for the short-circuit withstand checking ability of a transformer winding according to claim 6, wherein, The evaluation vector specifically includes a radial resistance coefficient, an axial stability coefficient, an insulation thermal stability coefficient, and a life prediction coefficient.

8. A method for evaluating the short-circuit withstand checking ability of a transformer winding according to claim 7, characterized in that, The short - circuit force test of the transformer winding is carried out by using the following short - circuit force test device for the transformer winding.

9. The method for evaluating the short-circuit withstand checking ability of a transformer winding according to claim 8, wherein, The short - circuit force test device for the transformer winding includes: Test cylinder system: It is composed of a test cylinder with a vertical cylindrical structure. The bottom of the test cylinder is fixed on the base, and a simplified upper cover plate is provided at the top to enclose the test space; Mechanical loading system: It includes two core components, a hydraulic cylinder and a loading plate. The hydraulic cylinder is fixed on the base, its piston rod extends upward and is fixedly connected to the loading plate. An annular groove is designed on the loading plate for placing the winding to be tested; Displacement measurement system: Two radial displacement sensors and two axial displacement sensors are installed. The radial displacement sensors are fixed on both sides of the test cylinder through mounting seats, and the sensor probes are in contact with the winding to be tested; the axial displacement sensors are fixed at the upper and lower ends of the test cylinder.

10. The method for evaluating the short-circuit withstand checking ability of a transformer winding according to claim 9, characterized in that, It further includes step S90: performing feature analysis on the evaluation vector by using a preset neural network classifier, and issuing a warning when any evaluation coefficient is lower than the preset threshold.

Images