Transformer winding wire cake radial displacement detection method, medium and system

Abstract

The invention discloses a method, a medium and a system for detecting radial displacement of a transformer winding wire cake. The method comprises the following steps of: establishing a relational expression between radial deformation quantity of a support strip and a support strip gear interval; assuming that at least one hypothetical supporting strip is arranged between two adjacent actual supporting strips, and establishing a calculation formula of the elastic coefficient of the hypothetical supporting strip; establishing a spring mass model; and simultaneously solving the relational expression of the radial deformation quantity of the stay and the spacing of the stay bars, the calculation formula of the elastic coefficient of the imaginary stay and the spring mass model to obtain the radial displacement quantity of the imaginary stay, and taking the radial displacement quantity of the imaginary stay as the radial displacement quantity of the winding wire cake. According to the method, the radial displacement of the winding wire cake can be accurately determined, the states of the winding wire and the supporting strip can be better evaluated, early warning is carried out in advance, and potential fault risks are avoided, so that the stability and safety of the winding wire and the supporting strip are maintained, safe and stable operation of transformer equipment is ensured, and the reliability and stability of the equipment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of transformers, and in particular to a method, a medium and a system for detecting radial displacement of transformer winding coils. Background Art

[0002] Power transformers are important electrical equipment in power systems, and conductors and stays, as key components inside transformers, have a significant impact on the performance and life of transformers. The design, material selection, installation and operating conditions of conductors and stays will directly affect the reliability and service life of transformers.

[0003] The materials and manufacturing process of the wires and stays have an important impact on the life of the transformer. Traditional wire materials usually use copper or aluminum, which have good electrical conductivity and mechanical strength, but are also susceptible to oxidation and corrosion due to environmental factors. In recent years, with the application of new materials, such as high-temperature superconducting materials, the current transmission capacity of the wire can be improved, and it has better corrosion resistance, thereby extending the life of the wire. The material of the stay is usually insulating plastic or glass fiber reinforced plastic, which has good insulation and mechanical strength, can effectively protect the wire and keep it in a good position, thereby extending the service life of the wire. The installation and maintenance of the wires and stays also have an important impact on the life of the transformer. Good installation can ensure the stability and safety of the wires and stays, and avoid damage or short circuits caused by vibration, collision, etc. Regular maintenance and inspection can timely detect the aging and wear of the wires and stays, and take corresponding repair and replacement measures, thereby extending the service life of the wires and stays. The design of the wires and stays also has an important impact on the life of the transformer. Reasonable design of wires and stays can reduce the power loss of wires, improve the current capacity and thermal conductivity of wires, thereby reducing the temperature rise and aging rate of wires and extending their service life. At the same time, good design can also reduce the electric field concentration and partial discharge between wires and stays, slow down their aging process and extend their service life.

[0004] In summary, as important components of the transformer, the wires and stays have a significant impact on the performance and life of the transformer. Through reasonable material selection, good installation and maintenance, and optimized design, the service life of the wires and stays can be effectively extended, and the reliability and safety of the transformer can be improved. With the continuous application of new materials and new technologies, the performance and life of the wires and stays will be further improved.

[0005] However, a major factor that affects the life of the transformer is that when the transformer is powered on, as the current changes, the winding will produce different degrees of electromagnetic response, which in turn causes the winding to produce different degrees of axial and radial response. Among them, when the radial response is too large, the winding will be distorted, reducing the service life of the transformer. The radial response generated by the winding will also squeeze the transformer stays, causing different degrees of squeezing and bending of the stays. If the bending amplitude is too large, the stays will be radially twisted and broken, which will also affect the service life of the transformer.

[0006] The existing technology for calculating the radial response of transformer windings has poor accuracy and low efficiency, which results in failure to timely detect excessive bending of the stays, resulting in a reduction in the service life of the transformer. Summary of the invention

[0007] The embodiments of the present invention provide a method, medium and system for detecting the radial displacement of a transformer winding coil, so as to solve the problem that the existing technology for calculating the radial response of the transformer winding has poor accuracy and low efficiency, resulting in failure to timely detect excessive bending of the support bar, resulting in a reduced service life of the transformer.

[0008] In a first aspect, a method for detecting radial displacement of a transformer winding coil is provided, comprising:

[0009] Establish the relationship between the radial deformation of the strut and the spacing between the struts;

[0010] Assuming that at least one imaginary strut is provided between two adjacent actual struts, a calculation formula for the elastic coefficient of the imaginary strut is established;

[0011] Establish spring mass model;

[0012] The relationship between the radial deformation of the strut and the strut spacing, the calculation formula of the elastic coefficient of the imaginary strut and the spring mass model are solved simultaneously to obtain the imaginary strut radial displacement, and the imaginary strut radial displacement is used as the radial displacement of the winding coil.

[0013] In a second aspect, a computer-readable storage medium is provided, on which computer program instructions are stored; when the computer program instructions are executed by a processor, the method for detecting radial displacement of a transformer winding coil as described in the embodiment of the first aspect is implemented.

[0014] In a third aspect, a system for detecting radial displacement of a transformer winding coil is provided, comprising: a computer-readable storage medium as described in the embodiment of the second aspect.

[0015] In this way, the embodiment of the present invention can accurately determine the radial displacement of the winding coil, better evaluate the status of the winding wire and the strut, give early warning and avoid potential failure risks, so as to maintain the stability and safety of the winding wire and the strut, ensure the safe and stable operation of the transformer equipment, and improve the reliability and stability of the equipment; it not only has a theoretical basis, but also can provide effective guidance for engineering practice, and also provides reference and reference for the safe operation of the transformer. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0017] Figure 1 It is a flow chart of a method for detecting radial displacement of transformer winding coils according to a preferred embodiment of the present invention;

[0018] Figure 2 is a schematic diagram of an imaginary stay according to an embodiment of the present invention;

[0019] Figure 3 is a schematic diagram of a fitting curve of a hypothetical strut radial response according to an embodiment of the present invention;

[0020] Figure 4 It is a flow chart of a method for detecting radial displacement of transformer winding coils according to another preferred embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0022] The embodiment of the present invention discloses a method for detecting radial displacement of transformer winding coils. Figure 1 As shown, the method of the embodiment of the present invention includes the following steps:

[0023] Step S101: establishing a relationship between the radial deformation of the struts and the strut spacing.

[0024] Specifically, Figure 2As shown, a measuring point can be set at the outer end of the transformer strut. The outer end of the strut can be connected to form a circle, and the strut spacing refers to the length of the arc between the outermost ends of the two struts. The measured strut radial deformation and strut spacing are used to draw the curve of the strut radial deformation and strut spacing. The fifth-order Gaussian function is fitted to the drawn curve of the strut radial deformation and strut spacing to obtain the relationship between the strut radial deformation and the strut spacing.

[0025] Specifically, this step includes the following process:

[0026] 1. Use the Bayesian network and the preset relationship index threshold to determine whether the radial deformation of the struts and the strut spacing contain one or more of the preset functional relationship groups, and record the one or more functional relationships as candidate functional relationships.

[0027] Specifically, the conditional probability distribution function of the Bayesian network is as follows:

[0028]

[0029] Among them, X is the node variable set, Pa(X) is the parent node variable set, and n is the number of nodes.

[0030] Specifically, the preset functional relationship group includes exponential relationship, power relationship, linear relationship, reciprocal relationship and logarithmic relationship. The relationship index calculation formula for each functional relationship is as follows:

[0031] (1) Exponential relationship:

[0032]

[0033] (2) Power relationship:

[0034]

[0035] (3) Linear relationship:

[0036]

[0037] (4) Reciprocal relationship:

[0038]

[0039] (5) Logarithmic relationship:

[0040]

[0041] Among them, x i is the sample value of the i-th support bar spacing, y i is the sample value of the radial deformation of the i-th brace, is the mean spacing between the struts, is the mean value of the radial deformation of the strut, k is the power coefficient, and n is the number of samples.

[0042] 2. For each candidate functional relationship, the least squares algorithm is used for fitting to obtain a linear regression model for each candidate functional relationship.

[0043] Specifically, the objective function of the least squares algorithm is as follows:

[0044]

[0045] Among them, θ is the model parameter vector, m is the number of training samples, and h θ (x) is the prediction function, x (i) is the i-th input sample, y (i) is the ith output sample.

[0046] The parameter update formula is as follows:

[0047]

[0048] Among them, α is the learning rate, the value range is (0,1), and j is the parameter index.

[0049] 3. For each linear regression model, a regression fitting model of multiple compression states of the cushion block is established, and the compression states include maximum compression, no compression, and at least one compression state between maximum compression and no compression.

[0050] Specifically, the regression model of the pad compression state is as follows:

[0051] y=β0+β1x+β2x 2 +β3σ+β4∈+β5δ.

[0052] Among them, β0 is the intercept term, β1 and β2 are the coefficients of the first and second terms, β3, β4, and β5 are the compression state coefficients, σ ​​is the stress term, ∈ is the strain term, and δ is the deformation.

[0053] 4. Solve the regression fitting models of multiple pads and multiple compression states corresponding to each linear regression model simultaneously to obtain the correlation index of each candidate function relationship.

[0054] Specifically, the calculation formula of the correlation index is as follows:

[0055] (1) Matrix expression of the simultaneous equations:

[0056]

[0057] Among them, β ij is the coefficient of the jth parameter in the i-th compression state, x jis the jth unknown parameter, y i is the observed value of the i-th compression state, m is the number of compression states, and n is the number of parameters.

[0058] 2. Correlation index calculation formula:

[0059]

[0060] Among them, CI k is the correlation index of the kth candidate function relationship, is the determination coefficient, ω1, ω2, ω3 are weight coefficients, and satisfy is the predicted value.

[0061] 5. According to the correlation index of each candidate function relationship, a fifth-order Gaussian function is fitted to the curves of the radial deformation of the struts and the strut spacing to obtain the relationship between the radial deformation of the struts and the strut spacing.

[0062] (1) The general form of the fifth-order Gaussian function is as follows:

[0063]

[0064] Among them, a i is the amplitude coefficient, b i is the center position, c i is the standard deviation.

[0065] (2) Parameter optimization objective function:

[0066]

[0067] Among them, θ is the set of parameters to be optimized, λ is the regularization coefficient, and n is the number of samples.

[0068] (3) Partial derivative calculation:

[0069]

[0070] (4) Parameter update rules:

[0071]

[0072] (5) Iteration stop condition:

[0073] max{|Δa i |,|Δb i |,|Δc i |}<∈ort>T max .

[0074] (6) Final goodness of fit evaluation:

[0075]

[0076] Below is an explanation of the above variables and parameters:

[0077] 1) Basic variables:

[0078] ①x i -Sample value of the i-th strut spacing; source: experimental measurement; unit: mm; range: [10,500].

[0079] ②y i - Sample value of radial deformation of the i-th strut; source: experimental measurement; unit: mm; range: [0,10].

[0080] ③n-sample number; source: determined by experimental design; range: [30,100]; recommended value: 50.

[0081] 2) Gaussian function parameters:

[0082] ①a i (i=1,2,3,4,5)-amplitude coefficient of the i-th Gaussian function; initial value: estimated by least squares; range: [-10,10]; calculation steps:

[0083] ②b i (i=1,2,3,4,5)-the center position of the i-th Gaussian function; initial value: evenly distributed within the data range; calculation method:

[0084] ③c i (i=1,2,3,4,5)-standard deviation of the i-th Gaussian function; initial value: 1 / 5 of the data range; calculation method:

[0085] 3) Optimization parameters:

[0086] ①η-learning rate; range: (0,1); recommended value: 0.01; adaptive adjustment rules:

[0087]

[0088] ②λ-regularization coefficient; range: [0.001,0.1]; recommended value: 0.01; determination method: cross validation.

[0089] ③∈-convergence threshold; range: [1e-6, 1e-4]; recommended value: 1e-5.

[0090] ④T max - Maximum number of iterations; range: [1000,10000]; recommended value: 5000.

[0091] 4) Other calculated variables:

[0092] ①Δa i ,Δb i ,Δc i -Parameter update amount; calculation method:

[0093] ②f(x i )-fitting function value; calculation method:

[0094] ③ -Sample mean; calculation method:

[0095] ④R 2 -Goodness of fit; range: [0,1]; minimum acceptance value: 0.9.

[0096] The relationship between the radial deformation of the strut and the strut spacing obtained by fitting is as follows:

[0097]

[0098] Among them, a1~a5, b1~b5, c1~c5 are constants, d is the spacing between the struts, y(d) is the radial deformation of the struts. d∈(0,160) is the spacing between the struts that satisfies the interval.

[0099] The step S101 is further described below with reference to a specific embodiment.

[0100] The Bayesian network is used to determine the candidate functional relationships. First, the experimental data of the radial deformation of the struts (y) and the strut spacing (d) are collected. The 50 sets of data obtained from the experiment are substituted into the calculation formulas of each relationship index.

[0101] The relationship indexes are calculated as follows:

[0102] Exponential relationship: R exp =0.915.

[0103] Power relationship: R pow =0.887.

[0104] Linear relationship: R lin =0.743.

[0105] Reciprocal relationship: R rec =0.812.

[0106] Logarithmic relationship: R log =0.836.

[0107] The relationship index threshold is set to 0.85, and the exponential relationship and power relationship are selected as candidate function relationships.

[0108] Perform a least squares fit on the relationship between two candidate functions. Use the objective function:

[0109]

[0110] The fitting equation is obtained:

[0111] Exponential relationship: y = 0.0245e 0.0428d .

[0112] Power relationship: y = 0.00178d 1.312 .

[0113] Establish the cushion compression state model and select three compression state points:

[0114] Maximum compression (100% compression): d max .

[0115] Intermediate compression (50% compression): d mid .

[0116] No compression (0% compression): d min .

[0117] Establish a regression fitting model for each state: y = β0 + β1d + β2d 2 +β3σ+β4∈+β5δ.

[0118] Solve the compression state equations together to obtain the correlation index:

[0119] Exponential relationship: CI exp =0.934.

[0120] Power relationship: CI pow =0.892.

[0121] Since the exponential relationship has a higher correlation index, a fifth-order Gaussian function fitting is performed based on it.

[0122] Set optimization parameters:

[0123] Learning rate η = 0.01, regularization coefficient λ = 0.01, convergence threshold ∈ = 1e-5, maximum number of iterations T max =5000.

[0124] Through iterative optimization, the coefficients of the final fifth-order Gaussian function are obtained, as shown in Table 1.

[0125] Table 1 Relationship between radial deformation of brace and spacing of brace

[0126]

[0127]

[0128] Finally, the relationship between the radial deformation of the strut and the strut spacing is obtained:

[0129]

[0130] By calculating the goodness of fit: R 2 =0.967, which is greater than the minimum acceptance value of 0.9, indicating that the fitting equation has good accuracy and can effectively describe the relationship between the radial deformation of the strut and the strut spacing.

[0131] Step S102: Assuming that at least one imaginary strut is disposed between two adjacent actual struts, a calculation formula for the elastic coefficient of the imaginary strut is established.

[0132] Specifically, Figure 2 As shown, at least one imaginary strut can be assumed between the actual strut 1 and the actual strut 2. The measuring point is set at the outer end of the strut. The position of the imaginary strut is actually the winding, so the elastic coefficient of the imaginary strut is the radial elastic coefficient k of the winding between the struts. f(x) , x∈(0,160).

[0133] The calculation formula for the elastic coefficient of the imaginary stay includes:

[0134]

[0135] Where k1 is the elastic coefficient of the actual brace, k n is the elastic coefficient of the imaginary strut, y(d1) is the actual radial deformation of the strut, y(d n ) is the assumed radial deformation of the brace, d1 is the actual brace spacing, d n It is the distance between the imaginary support bars.

[0136] The calculation process of the elastic coefficient of the above-mentioned imaginary stay is as follows:

[0137] Known Then there is Deformation can be obtained

[0138] Step S103: Establish a spring mass model.

[0139] Specifically, the spring mass model is as follows:

[0140]

[0141]

[0142]

[0143] …

[0144]

[0145] Among them, x1 is the actual radial displacement of the strut, x n is the radial displacement of the imaginary strut, k1 is the elastic coefficient of the actual strut, k n is the elastic coefficient of the imaginary stay, μ is the friction coefficient of the imaginary stay, m is the mass of the winding coil, and F is the radial static electromagnetic force on the winding between the stays. The friction coefficient of the imaginary stay is the friction coefficient between the winding stays and the transformer oil, which can be preset through experience, or the friction coefficients of multiple measuring points on the winding are obtained by testing and then calculating the average value of these friction coefficients.

[0146] Step S104: Solve the relationship between the radial deformation of the strut and the strut spacing, the calculation formula of the elastic coefficient of the imaginary strut and the spring mass model to obtain the imaginary strut radial displacement, and use the imaginary strut radial displacement as the winding coil radial displacement.

[0147] Specifically, the above equations can be analyzed using an analytical method to obtain the final result.

[0148] Through the above process, the embodiment of the present invention proposes a new concept of imaginary struts, which makes the calculation steps more concise, the derived mathematical model has a higher integration degree, the calculation efficiency is higher, and the calculation precision and accuracy are guaranteed at the same time.

[0149] Preferably, after calculating the radial displacement of the winding coil, the steps of the embodiment of the present invention further include:

[0150] Step S105: Compare the winding coil radial displacement with the winding coil radial displacement warning value to determine whether the transformer winding is faulty.

[0151] Step S106: If the radial displacement of the winding coil reaches the radial displacement warning value of the winding coil, it is determined that the transformer winding is faulty; otherwise, it is determined that the transformer winding is normal.

[0152] If the radial displacement of the winding coil reaches the radial displacement warning value of the winding coil, it indicates that the winding wire may be twisted, broken or have other problems, and timely repair or replacement measures need to be taken.

[0153] Preferably, after judging whether the transformer winding is normal by the radial displacement of the winding coil, the steps of the embodiment of the present invention further include:

[0154] Step S107: Compare the actual radial displacement of the strut with the radial displacement warning value of the strut to determine whether a transformer winding fault occurs.

[0155] The actual radial displacement of the strut can also be obtained by simultaneously solving the relationship between the radial deformation of the strut and the strut spacing, the calculation formula of the elastic coefficient of the imaginary strut and the spring mass model.

[0156] Step S108: If the actual radial displacement of the strut reaches the radial displacement warning value of the strut, it is determined that the transformer winding is faulty; otherwise, it is determined that the transformer winding is normal.

[0157] If the actual radial displacement of the strut reaches the radial displacement warning value of the strut, it indicates that the strut may be twisted, broken or have other problems, and timely repair or replacement measures need to be taken.

[0158] It should be understood that the radial displacement warning value of the winding coil and the radial displacement warning value of the stay are determined in advance by the winding wire bending test and the stay bending test, respectively. Through the winding wire bending test and the stay bending test, the bending degree and bearing capacity of the winding wire and the stay during the force process can be examined, and the radial bending value of the winding wire corresponding to the bending deformation of the winding wire is used as the radial displacement warning value of the winding coil, and the radial bending value of the stay corresponding to the bending deformation of the stay is used as the radial displacement warning value of the winding coil.

[0159] In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which computer program instructions are stored; when the computer program instructions are executed by a processor, the method for detecting radial displacement of a transformer winding coil as described in the above embodiment is implemented.

[0160] In addition, an embodiment of the present invention further provides a system for detecting radial displacement of a transformer winding coil, comprising: a computer-readable storage medium as described in the above embodiment.

[0161] In summary, the embodiments of the present invention can accurately determine the radial displacement of the winding coil, better evaluate the status of the winding wires and the struts, give early warning and avoid potential failure risks, so as to maintain the stability and safety of the winding wires and the struts, ensure the safe and stable operation of the transformer equipment, and improve the reliability and stability of the equipment; it not only has a theoretical basis, but also can provide effective guidance for engineering practice, and also provides reference and reference for the safe operation of the transformer.

[0162] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for detecting radial displacement of transformer winding coils, characterized in that: include: Establish the relationship between the radial deformation of the strut and the spacing between the struts; Assuming that at least one imaginary strut is provided between two adjacent actual struts, a calculation formula for the elastic coefficient of the imaginary strut is established; Establish spring mass model; The relationship between the radial deformation of the strut and the strut spacing, the calculation formula of the elastic coefficient of the imaginary strut and the spring mass model are solved simultaneously to obtain the imaginary strut radial displacement, and the imaginary strut radial displacement is used as the radial displacement of the winding coil.

2. The method for detecting radial displacement of transformer winding coils according to claim 1, characterized in that: The step of establishing a relationship between the radial deformation of the struts and the strut spacing comprises: A Bayesian network and a preset relationship index threshold are used to determine whether the radial deformation of the strut and the strut spacing include one or more of a preset functional relationship group, and the one or more functional relationships included are recorded as candidate functional relationships, wherein the preset functional relationship group includes an exponential relationship, a power relationship, a linear relationship, a reciprocal relationship, and a logarithmic relationship; For each candidate functional relationship, the least squares algorithm is used for fitting to obtain a linear regression model of each candidate functional relationship; For each linear regression model, a regression fitting model of multiple compression states of the cushion block is established, wherein the compression state includes maximum compression, no compression, and at least one compression state between the maximum compression and no compression; The regression fitting models of multiple cushion blocks and multiple compression states corresponding to each linear regression model are solved simultaneously to obtain the correlation index of each candidate functional relationship; According to the correlation index of each candidate function relationship, the fifth-order Gaussian function is fitted to the curves of the radial deformation of the struts and the strut spacing, and the relationship between the radial deformation of the struts and the strut spacing is obtained.

3. The method for detecting radial displacement of transformer winding coils according to claim 1, characterized in that: The relationship between the radial deformation of the strut and the strut spacing includes: Among them, a1~a5, b1~b5, c1~c5 are constants, d is the strut spacing, and y(d) is the radial deformation of the strut.

4. The method for detecting radial displacement of transformer winding coils according to claim 1, characterized in that: The calculation formula of the elastic coefficient of the imaginary stay includes: Where k1 is the elastic coefficient of the actual brace, k n is the elastic coefficient of the imaginary strut, y(d1) is the actual radial deformation of the strut, y(d n ) is the assumed radial deformation of the brace, d1 is the actual brace spacing, d n It is the distance between the imaginary support bars.

5. The method for detecting radial displacement of transformer winding coils according to claim 1, characterized in that: The spring mass model includes: Among them, x1 is the actual radial displacement of the strut, x n is the radial displacement of the imaginary strut, k1 is the elastic coefficient of the actual strut, k n is the elastic coefficient of the imaginary stay, μ is the friction coefficient of the imaginary stay, m is the mass of the winding coil, and F is the radial static electromagnetic force on the winding between the stays.

6. The method for detecting radial displacement of transformer winding coils according to claim 1, characterized in that: After the step of obtaining the imaginary strut radial displacement, the method further comprises: Compare the radial displacement of the winding coil with the radial displacement warning value of the winding coil to determine whether the transformer winding is faulty; If the radial displacement of the winding coil reaches the radial displacement warning value of the winding coil, it is determined that the transformer winding is faulty; otherwise, it is determined that the transformer winding is normal.

7. The method for detecting radial displacement of transformer winding coils according to claim 6, characterized in that: After the step of determining whether the transformer winding is normal, the method further includes: Compare the actual radial displacement of the strut with the radial displacement warning value of the strut to determine whether the transformer winding has a fault; If the actual strut radial displacement reaches the strut radial displacement warning value, it is determined that the transformer winding is faulty; otherwise, it is determined that the transformer winding is normal.

8. The method for detecting radial displacement of transformer winding coils according to claim 6, characterized in that: The winding coil radial displacement warning value and the stay radial displacement warning value are respectively determined in advance through a winding wire bending test and a stay bending test.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, the method for detecting radial displacement of a transformer winding coil according to any one of claims 1 to 8 is implemented.

10. A transformer winding coil radial displacement detection system, characterized in that: include: The computer readable storage medium of claim 9.

Images