Transformer insulation cushion block mechanical parameter identification method, system and related device
Through the viscoelastic model and improved parameter identification method, the solution problem of nonlinear viscous damping of transformer insulating pads is solved, the accuracy and reliability of vibration calculation are improved, and more accurate theoretical support is provided for transformer state monitoring.
Patent Information
- Application Number
- CN202510326961.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-19
- Publication Date
- 2025-07-08
AI Technical Summary
The prior art lacks detailed solutions in describing nonlinear viscous damping of transformer insulating pads, resulting in inaccurate vibration calculations and incomplete consideration of viscoelastic characteristics, which affects the accuracy and reliability of transformer state monitoring.
Using the viscoelastic model, mechanical parameters, including mechanical linear parameters, nonlinear parameters and damping parameters are identified by minimizing the error between the strain and the numerical solution of the insulating pad, the parameter identification process is optimized using the improved gradient descent method and weight decay coefficient.
It improves the accuracy and reliability of transformer vibration calculation, provides a more complete theoretical basis, and provides a new way for transformer status monitoring and fault diagnosis research.
Smart Images
Figure CN120277827A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of power equipment condition monitoring, and particularly relates to a method and system for identifying mechanical parameters of transformer insulation pads and related devices. Background Art
[0002] As a core device for electric energy transmission in the power system, the reliability of a transformer's operation is directly related to the safety and stability of the power grid. However, during operation, the internal windings of a transformer are subjected to the combined effects of electrical, thermal, and mechanical stresses, which may cause mechanical structure failures and thus threaten the normal operation of the transformer. Therefore, conducting transformer condition assessment is of great significance for improving the reliability of the power system and maintaining the safe and stable operation of the power grid.
[0003] In recent years, the transformer condition monitoring method based on vibration analysis has received extensive attention from academia and industry because it can achieve online monitoring of transformers. In existing transformer vibration models, the vibration of windings is usually modeled and analyzed through a mass-spring-damping system, where the wire is equivalent to a concentrated mass block, and the insulation pad is equivalent to a spring and a viscous damping element. However, it has been found that during vibration, the insulation pad exhibits significant non-linear mechanical properties in the out-of-plane direction, that is, its elastic modulus increases with the increase of stress. At the same time, the viscous damping of the insulation pad also shows obvious non-linear characteristics. During steady-state vibration, due to the small electromagnetic force received, the compression stress of the winding on the insulation pad is small, and the non-linearity of the insulation pad can be ignored; but during transient vibration, due to the large electromagnetic force generated by the short-circuit current, the insulation pad is subjected to a large compression stress, so the non-linearity during the vibration process cannot be ignored.
[0004] Although existing research has considered the non-linearity of the insulation pad, there are still deficiencies in the non-linear modeling of the insulation pad. Especially in describing the non-linear viscous damping of the insulation pad, the current research has not provided a detailed enough solution method. Solving this problem can not only improve the transformer vibration model but also provide a theoretical basis for improving the accuracy and effectiveness of transformer condition monitoring. This has important theoretical and practical significance for ensuring the long-term safe operation of transformers and the overall stability of the power grid.
[0005] Existing research on the non-linear characteristics of insulation pads is relatively less, and usually, the stiffness of the insulation pad is regarded as a constant value in vibration calculations. However, when it comes to the application of non-linear parameters of the insulation pad in vibration calculations, most research uses the stress-strain curve of the insulation pad obtained through compression experiments and fits it to extract the mechanical parameters of the insulation pad. Although this method can to some extent reflect the non-linear elastic deformation characteristics of the insulation pad, it has obvious limitations and fails to comprehensively consider the viscoelastic characteristics of the insulation pad.
[0006] Under actual working conditions, the stress-strain curves of the insulating pads in a transformer usually do not coincide during the process of increasing and decreasing the load, showing obvious hysteresis phenomena. This means that the existing processing method, which only describes the non-linear elastic deformation of the insulating pads by fitting the average values of the loading and unloading curves, ignores the influence of viscoelasticity on the vibration characteristics and is an inaccurate processing method. In addition, the numerical value of viscous damping is usually simplified to a constant based on empirical values, and this processing method fails to reflect the non-linear change of the viscous damping of the insulating pads, which may affect the accuracy of vibration calculation. Summary of the Invention
[0007] The purpose of the present invention is to provide a method, a system and related devices for identifying the mechanical parameters of insulating pads in a transformer, which can more accurately describe the mechanical behavior of the insulating pads under actual operating conditions, thereby improving the accuracy and reliability of vibration calculation.
[0008] To achieve the above purpose, the present invention adopts the following technical solutions: In the first aspect, the present invention provides a method for identifying the mechanical parameters of insulating pads in a transformer, including: Establish a viscoelastic model of the insulating pad, where the viscoelastic model of the insulating pad characterizes the relationship between the stress and strain of the insulating pad with mechanical parameters, and the mechanical parameters include mechanical linear parameters, mechanical non-linear parameters and damping parameters; Apply stress to the insulating pad and collect the strain of the insulating pad under the stress; By minimizing the error between the strain of the insulating pad under the stress and the numerical solution of the strain, identify the mechanical parameters of the viscoelastic model of the pad, and the numerical solution of the strain is obtained by solving the viscoelastic model of the insulating pad.
[0009] Further, the viscoelastic model of the insulating pad is: ; Wherein, ; Wherein, represents the stress of the insulating pad, represents the elastic stress of the insulating pad, represents the viscous stress of the insulating pad, a is the mechanical linear parameter, b is the mechanical non-linear parameter, is the damping parameter of the insulating pad, represents the strain of the insulating pad under the action of stress, represents the displacement of the insulating pad under the action of stress, represents the initial thickness of the insulating pad.
[0010] Further, the stress applied to the insulating spacer is a sinusoidal alternating periodic stress.
[0011] Further, the mechanical parameters for identifying the viscoelastic model of the spacer by minimizing the error between the strain of the insulating spacer under the stress and the strain calculated based on the viscoelastic model of the insulating spacer include: Define an error function based on the strain under the stress and the strain calculated based on the viscoelastic model of the insulating spacer; Solve the differential equation of the viscoelastic model of the insulating spacer to obtain a numerical solution of the strain: Minimize the error function and iterate on each mechanical parameter until the value of the error function is reduced to meet the threshold.
[0012] Further, the error function is the sum of the squared errors of the strain of the insulating spacer under the stress and the numerical solution of the strain.
[0013] Further, minimizing the error function and iterating on the gradients of each mechanical parameter includes: Obtain an error gradient based on the error function; Update the first moment and second moment of each mechanical parameter based on the error gradient; Perform bias correction on the first moment and second moment of each mechanical parameter to obtain the corrected first moment and second moment of each mechanical parameter; Iterate on the gradients of each mechanical parameter based on the corrected first moment and second moment of each mechanical parameter.
[0014] Further, a weight decay coefficient is introduced when iterating on the gradients of each mechanical parameter based on the corrected first moment and second moment of each mechanical parameter.
[0015] In a second aspect, the present invention provides a system for identifying mechanical parameters of a transformer insulating spacer, including: A modeling module for establishing a viscoelastic model of the insulating spacer, where the viscoelastic model of the insulating spacer includes a non-linear elastic part and a non-linear viscous damping part; A data acquisition module for acquiring the stress applied to the insulating spacer and the strain of the insulating spacer under the stress; A mechanical parameter identification module for identifying the mechanical parameters of the viscoelastic model of the spacer by minimizing the error between the strain of the insulating spacer under the stress and the numerical solution of the strain, where the mechanical parameters include mechanical linear parameters, mechanical non-linear parameters, and damping parameters.
[0016] In a third aspect, the present invention provides an electronic device, characterized by including: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute a method for identifying mechanical parameters of a transformer insulating spacer as described in any one of the first aspects of the present invention.
[0017] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, characterized in that when the computer program is executed by a processor, it implements a method for identifying mechanical parameters of a transformer insulating spacer as described in any one of the first aspects of the present invention.
[0018] Compared with the prior art, the present invention has at least the following beneficial technical effects: The present invention provides a method for identifying mechanical parameters of a transformer insulating spacer. When modeling the viscoelasticity of the insulating spacer, the nonlinearity of the insulating spacer is considered, especially considering that the damping also exhibits nonlinearity, and a specific model is given. In previous studies on the mechanical characteristics of transformers, the identification of damping parameters was ignored, while the present invention fills this gap and provides support for the accurate calculation of transformer transient vibrations. Through this parameter identification algorithm, the mechanical parameters of the insulating spacer, especially the damping parameters of the insulating spacer, can be directly obtained from the stress-strain curve of the insulating spacer obtained during the experiment.
[0019] Further, when conducting the experiment, the electromagnetic force of the transient vibration is used as the test load to highly simulate the force received by the insulating spacer during transformer short circuit, so the parameters used for fitting are relatively accurate.
[0020] Further, the present invention provides an identification algorithm based on an improved gradient descent method. By calculating the moving average of the first and second moments, the update step size of each parameter is automatically adjusted, thereby improving the convergence speed and stability. At the same time, it can also accelerate convergence, and a weight decay coefficient is introduced to improve the performance of overfitting. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Figure 1 It is a flowchart of the method for identifying mechanical parameters of a transformer insulating spacer provided by the present invention; Figure 2 It is a schematic diagram of a cyclic load test of an insulating spacer; Figure 3 It is the waveform of the periodic stress applied to the insulating spacer; Figure 4 It is the stress-strain curve calculated by the model; Figure 5 It is the measured stress-strain curve; Figure 6The structural block diagram of a mechanical parameter identification system for a transformer insulation spacer provided by an embodiment of the present invention; Figure 7 The block diagram of an electronic device according to an embodiment of the present invention.
[0022] In the drawings: 1. Sample; 2. Upper clamping piece; 3. Lower clamping piece; 4. Stainless steel container; 5. Transformer oil. Specific embodiments
[0023] In order to enable those skilled in the art to better understand the solution of the present invention, 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. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.
[0025] The present invention proposes a new theoretical modeling method for the mechanical characteristics of insulation spacers under the action of periodic electromagnetic force, and provides a corresponding mechanical parameter identification method. By introducing the viscoelastic characteristics of insulation spacers including nonlinear elasticity and nonlinear viscous damping characteristics, the mechanical behavior of insulation spacers under actual operating conditions is more accurately described, thereby improving the accuracy and reliability of vibration calculation. In addition, the present invention provides a method for identifying the mechanical parameters of insulation spacers under strong compressive stress. This improvement not only provides a more perfect theoretical basis for transformer vibration analysis, but also opens up a new way for future state monitoring and fault diagnosis research.
[0026] The following further describes the present invention in detail with reference to the accompanying drawings: Embodiment 1 Refer to Figure 1 , this embodiment provides a method for identifying the mechanical parameters of a transformer insulation spacer, including the following steps: Step 1. Viscoelastic modeling of the insulation spacer The equivalent model of the insulating spacer consists of a spring and a viscous damper, both of which exhibit obvious non-linearity.
[0027] The elastic part of the insulating spacer is expressed as: ; ; where a is the mechanical linear parameter and b is the mechanical non-linear parameter. represents the elastic stress of the insulating spacer. represents the displacement of the insulating spacer under the action of stress. represents the strain of the insulating spacer under the action of stress. represents the initial thickness of the insulating spacer.
[0028] The viscous part of the insulating spacer is expressed as:
[0029] represents the viscous stress of the insulating spacer. represents the damping parameter of the insulating spacer. represents the strain of the insulating spacer under the action of stress.
[0030] Based on the non-linearity of the above-mentioned insulating spacer, the viscoelastic model of the insulating spacer is expressed as:
[0031] where represents the stress of the insulating spacer. This model takes into account the asymmetry of the loading and unloading processes. The mechanical linear parameter a, the mechanical non-linear parameter b, and the damping parameter of the insulating spacer are all mechanical parameters.
[0032] Step 2: Conduct a cyclic loading test on the insulating spacer Step 2.1: Place the insulating spacer with a thickness of 1 mm and a length × width of 30 mm × 30 mm between two steel plates and then place it in the clamping plate of a flat vulcanizing machine. Place it in an environment with a pressure of 5 Mpa and a temperature of 100 °C for 48 hours to densify the insulating spacer and reduce the water content of the insulating spacer.
[0033] Step 2.2: Refer to Figure 2 , stack the pre-treated insulating spacers neatly in groups of 5 - 10 pieces and place them in the stainless-steel container 4 filled with transformer oil 5 to simulate the working condition of the insulating spacer in the transformer. Place the stainless-steel container 5 between the upper clamp 2 and the lower clamp 3 of the MTS-880 electro-hydraulic servo universal material testing machine. Before the test, measure the thickness of each group of samples to obtain the initial thickness L0 of the insulating spacer.
[0034] Step 2.3: Apply a cyclic stress of sine wave as shown in Figure 3 to the insulating spacer through a cyclic stress loading experiment, and record the strain under the cyclic force, denoted as .
[0035]
[0036] Wherein, represents the stress applied to the insulating spacer, is the stress amplitude, f is the stress frequency, and t is the time.
[0037] Step 3: Identification of mechanical parameters of the insulating spacer Parameter identification is a method for determining the parameter values in a system model. Its main purpose is to estimate unknown parameters through experimental data so that the model output can approximate the output of the actual system as much as possible. Its principle is: identify the parameters of the viscoelastic model of the insulating spacer by minimizing the error between the strain of the insulating spacer obtained from experimental data and the strain calculated by the model. If the deviation between the two is very small, it is considered that the parameters given for model calculation are the approximate solutions of the true parameters of the measured insulating spacer. If the deviation is very large, new parameters are generated and the above calculation process is repeated until the deviation is less than the preset threshold.
[0038] The identification of mechanical parameters of the insulating spacer includes the following steps: Step 3.1: The mechanical parameters to be identified are: , and . Define the error function as follows: ; Wherein, is the error function between the theoretical model and the measured value, N is the number of time points of experimental data, represents the i-th time point, represents the experimental strain at the i-th time point, represents the strain calculated based on the viscoelastic model.
[0039] Step 3.2: In order to calculate the strain of the viscoelastic model of the insulating spacer, it is necessary to solve the differential equation of the viscoelastic model of the insulating spacer. Substitute the stress applied to the insulating spacer into the viscoelastic model of the insulating spacer to obtain: ; By separating variables, the differential equation of strain is obtained: ; This equation can be solved by numerical methods (such as the Runge-Kutta method) to obtain the numerical solution of the strain in the viscoelastic model of the insulating spacer 。
[0040] Step 3.3: Use the gradient descent method to minimize the error function. The core idea of the gradient descent method is to update the parameters along the negative gradient direction of the error function to gradually approach the optimal solution. Respectively, take the derivatives of the parameters to be identified in the error function 、 and to obtain the expressions of the gradients: ; ; ; In the above formula, represents the small variable of the mechanical linear parameter a, represents the small variable of the mechanical non - linear parameter b, represents the small variable of the damping parameter , 、 、 respectively represent the derivative results of the mechanical linear parameter a, the mechanical non - linear parameter b, and the damping parameter .
[0041] Step 3.4: Improve the gradient descent algorithm. By calculating the moving averages of the first - order moments and second - order moments of each mechanical parameter, automatically adjust the step size of each mechanical parameter, so as to improve the convergence speed and stability. Update the first - order moments and second - order moments through the following formulas: ; ; ; ; ; ; In the above formula, 、 、 are the first - order moments of the parameters a, b, and at the k - th iteration respectively, 、 、 are the first - order moments of the parameters a, b, and at the (k - 1) - th iteration respectively, 、 、 are the second - order moments of the parameters a, b, and at the k - th iteration respectively, 、 、 are the second - order moments of the parameters a, b, and The second moment at the (k - 1)-th iteration and and are the parameters a, b, and the decay rate of the first moment estimate, and and are the parameters and and the decay rate of the second moment estimate, respectively.
[0042] Step 3.5: Bias correction of the first and second moments of each mechanical parameter gives:[ ; ; ; ; ; ; In the above equations, and and are the parameters a, b, and the first moment at the k-th iteration, and and are the parameters a, b, and the second moment at the k-th iteration, and and are the parameters a, b, and the decay rate of the first moment estimate, and and are the parameters a, b, and the decay rate of the second moment estimate, and and are respectively and and the corrected values, and and are respectively and and the corrected values; Step 3.6: Introduce a weight decay coefficient to improve the performance during overfitting. Update the mechanical parameters by iterating according to the gradients of the solved mechanical parameters through the following equation.[
[0043] ; ; ; Among them, , , are the parameters to be identified , and the numerical value of the (k + 1)-th iteration, , , are the parameters to be identified , and the numerical value of the k-th iteration, is the weight decay coefficient, is the initial learning rate of the mechanical linear parameter, is the initial learning rate of the mechanical non-linear parameter, is the initial learning rate of the mechanical damping parameter, , and are all set to 0.01.
[0044] Step 3.7: Recalculate the error function using the updated mechanical parameters . When the value of the error function drops to meet the threshold, the parameters at this time are the actual parameters of the model.
[0045] ; Among them, is the error after the (k + 1)-th iteration.
[0046] Based on the above process identification results as shown in Figure 4 and Figure 5 , the similarity between the measured value and the stress-strain curve obtained by theoretical calculation is relatively high, verifying the accuracy of this method.
[0047] Embodiment 2 Please refer to Figure 6 . In this embodiment, a mechanical parameter identification system for transformer insulating pads is provided, including: A modeling module for establishing a viscoelastic model of the insulating pad; A data acquisition module for collecting the sinusoidal alternating periodic stress applied to the insulating pad and the strain of the insulating pad under the periodic stress; A mechanical parameter identification module for identifying the mechanical parameters of the insulating pad based on the error between the strain under the periodic force and the strain calculated by the viscoelastic model of the insulating pad. The mechanical parameters of the insulating pad include a mechanical linear parameter a, a mechanical non-linear parameter b, and a damping parameter .
[0048] All relevant contents of each step involved in the embodiment of the foregoing method for identifying mechanical parameters of a transformer insulation spacer can be cited in the functional description of the corresponding functional modules of a system for identifying mechanical parameters of a transformer insulation spacer in the embodiments of the present invention, and will not be repeated here.
[0049] Embodiment 3 Referring to Figure 7 , this embodiment provides an electronic device, which includes a processor and a memory, and the processor is connected to the memory through a bus; the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiments of the present invention can be used for the operation of a method for identifying mechanical parameters of a transformer insulation spacer. The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 7 only one line is shown in ,
[0050] Embodiment 4 This embodiment provides a storage medium, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in an electronic device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the electronic device and, of course, the extended storage medium supported by the electronic device. The computer-readable storage medium provides a storage space, and the operating system of the terminal is stored in this storage space. Moreover, one or more instructions suitable for being loaded and executed by the processor are stored in this storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. One or more instructions stored in the computer-readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the method for identifying the mechanical parameters of a transformer insulation spacer in the above embodiment.
[0051] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.
[0052] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.
[0053] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions in Figure 1 one flow or multiple flows and / or blocks Figure 1The functions specified in one or more boxes.
[0054] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for implementing the steps for the functions specified in one Figure 1 one process or more processes and / or boxes Figure 1 the steps for the functions specified in one or more boxes.
[0055] Embodiment 5 This embodiment provides a computer program product, including a non-volatile computer-readable storage medium. The non-volatile computer-readable storage medium stores a computer program product. When the computer program is executed by a processor, it implements the steps of the methods described in various embodiments of the present application.
[0056] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data that have been authorized by the user or fully authorized by all parties. And the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.
[0057] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.
[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: still can modify the specific implementation manners of the present invention or make equivalent replacements, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.
Claims
1. A method for identifying mechanical parameters of a transformer insulation spacer, characterized in that, including: establishing a viscoelastic model of the insulating spacer, where the viscoelastic model of the insulating spacer characterizes the relationship between the stress and strain of the insulating spacer using mechanical parameters, and the mechanical parameters include mechanical linear parameters, mechanical nonlinear parameters, and damping parameters; applying stress to the insulating spacer and collecting the strain of the insulating spacer under the stress; identifying the mechanical parameters of the viscoelastic model of the spacer by minimizing the error between the strain of the insulating spacer under the stress and the numerical solution of the strain, where the numerical solution of the strain is obtained by solving the viscoelastic model of the insulating spacer.
2. The mechanical parameter identification method for a transformer insulation spacer according to claim 1, wherein The viscoelastic model of the insulating spacer is: ； Among them, ; Among them, represents the stress of the insulating spacer, represents the elastic stress of the insulating spacer, represents the viscous stress of the insulating spacer, a is the mechanical linear parameter, b is the mechanical non-linear parameter, is the damping parameter of the insulating spacer, represents the strain of the insulating spacer under the action of stress, represents the displacement of the insulating spacer under the action of stress, represents the initial thickness of the insulating spacer.
3. A method for identifying mechanical parameters of a transformer insulation pad according to claim 1, characterized in that, The stress applied to the insulating spacer is a sinusoidal alternating periodic stress.
4. A method for identifying mechanical parameters of a transformer insulation spacer according to claim 1, characterized in that The identifying the mechanical parameters of the viscoelastic model of the spacer by minimizing the error between the strain of the insulating spacer under the stress and the strain calculated based on the viscoelastic model of the insulating spacer includes: defining an error function based on the strain under the stress and the strain calculated based on the viscoelastic model of the insulating spacer; solving the differential equation of the viscoelastic model of the insulating spacer to obtain the numerical solution of the strain: minimizing the error function and iterating on each mechanical parameter until the value of the error function is reduced to meet the threshold.
5. A method for identifying mechanical parameters of a transformer insulation spacer according to claim 4, characterized in that The error function is the sum of the squared errors between the strain of the insulating spacer under the stress and the numerical solution of the strain.
6. A method for identifying mechanical parameters of a transformer insulation pad according to claim 4, characterized in that, The minimizing the error function and iterating on the gradients of each mechanical parameter includes: obtaining an error gradient based on the error function; updating the first moment and second moment of each mechanical parameter based on the error gradient; performing bias correction on the first moment and second moment of each mechanical parameter to obtain the corrected first moment and second moment of each mechanical parameter; iterating on the gradients of each mechanical parameter based on the corrected first moment and second moment of each mechanical parameter.
7. A method for identifying mechanical parameters of a transformer insulation spacer according to claim 6, characterized in that, When iterating on the gradients of each mechanical parameter based on the corrected first moment and second moment of each mechanical parameter, a weight decay coefficient is introduced.
8. A mechanical parameter identification system for transformer insulation pads, characterized in that including: a modeling module for establishing a viscoelastic model of the insulating spacer, where the viscoelastic model of the insulating spacer includes a nonlinear elastic part and a nonlinear viscous damping part; a data acquisition module for collecting the stress applied to the insulating spacer and the strain of the insulating spacer under the stress; a mechanical parameter identification module for identifying the mechanical parameters of the viscoelastic model of the spacer by minimizing the error between the strain of the insulating spacer under the stress and the numerical solution of the strain, where the mechanical parameters include mechanical linear parameters, mechanical nonlinear parameters, and damping parameters.
9. An electronic device, characterized in that, including: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute a method for identifying mechanical parameters of a transformer insulating spacer as described in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements a method for identifying mechanical parameters of a transformer insulating spacer as described in any one of claims 1 to 7.