A method and system for processing transformer winding copper wire based on tension monitoring

Abstract

The invention relates to the field of information technology, and discloses a transformer winding copper wire processing method and system based on tension monitoring. A transformer winding copper wire mechanical model established by mechanical property parameters of the transformer winding copper wire is combined with finite element analysis technology to determine a critical disassembly tension threshold for permanent deformation of the transformer winding copper wire; a surface roughness feature of the transformer winding copper wire of a historical transformer winding copper wire disassembly image is combined with finite element analysis technology to determine a correlation between surface damage data of the transformer winding copper wire and disassembly tension, and a critical disassembly tension range required for completely stripping off the insulation layer of the transformer winding copper wire; a multi-objective optimization model is constructed and solved based on the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range to obtain an optimal disassembly tension control strategy, and the scheme realizes efficient and intelligent disassembly and recycling of the transformer winding copper wire, and improves the recycling quality and recycling efficiency of the transformer winding copper wire.

Description

Technical Field

[0001] The invention relates to the field of information technology, and in particular to a transformer winding copper wire processing method and system based on tension monitoring. Background Art

[0002] In the process of disassembling and recycling distribution transformers, the disassembly of transformer winding copper wire is a key link. However, the processing of transformer winding copper wire is often based on manual experience and with the help of various tools. It has a low degree of intelligence, is time-consuming and increases labor costs. In addition, due to differences in experience and technical levels in the manual disassembly process, the quality of the recycled parts after processing may be unstable, resulting in low processing efficiency.

[0003] It can be seen that how to solve the problem that the current processing scheme for transformer winding copper wire is time-consuming and inefficient has become a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0004] The present invention provides a transformer winding copper wire processing method and system based on tension monitoring, which solves the problem that the current processing scheme for transformer winding copper wire is time-consuming and inefficient.

[0005] In order to solve the above technical problems, the first aspect of the present invention provides a transformer winding copper wire processing method based on tension monitoring, comprising:

[0006] Obtaining mechanical property parameters of the transformer winding copper wire to establish a mechanical model of the transformer winding copper wire, and based on the mechanical model of the transformer winding copper wire, determining the stress and strain distribution of the transformer winding copper wire under different disassembly tensions through finite element analysis and analyzing, to obtain a critical disassembly tension threshold at which the transformer winding copper wire undergoes permanent deformation;

[0007] Acquire the historical transformer winding copper wire disassembly image, and determine the correlation between the surface damage data of the transformer winding copper wire and the disassembly tension according to the surface roughness characteristics of the transformer winding copper wire extracted from the historical transformer winding copper wire disassembly image;

[0008] The tear strength and thickness uniformity of the insulating layer in the copper wire of the transformer winding are obtained to establish a constitutive model of the insulating layer. Based on the constitutive model of the insulating layer, the stress distribution and deformation of the insulating layer under different disassembly tensions are determined and analyzed by finite element analysis to obtain a critical disassembly tension range required for completely stripping the insulating layer.

[0009] A multi-objective optimization model is constructed and solved according to the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range to obtain an optimal disassembly tension control strategy.

[0010] As one of the preferred solutions, based on the mechanical model of the transformer winding copper wire, the stress and strain distribution of the transformer winding copper wire under different disassembly tensions is determined by finite element analysis and analyzed to obtain the critical disassembly tension threshold at which the transformer winding copper wire undergoes permanent deformation, including:

[0011] Setting boundary conditions and load steps, and calculating stress and strain distribution data of the transformer winding copper wire under different disassembly tensions by a finite element solver;

[0012] Calculating the maximum equivalent stress and equivalent plasticity of the transformer winding copper wire under different disassembly tensions according to the stress and strain distribution data to determine the critical disassembly tension of the transformer winding copper wire when yielding;

[0013] Introducing a plastic strain accumulation rule, and establishing a relationship model between the plastic strain and disassembly tension of the transformer winding copper wire based on the critical disassembly tension;

[0014] The critical plastic strain threshold of the transformer winding copper wire during permanent deformation is obtained, and the relationship model is solved by the critical plastic strain threshold to obtain the critical disassembly tension threshold of the transformer winding copper wire during permanent deformation.

[0015] As one of the preferred solutions, the method of determining the correlation between the surface damage data of the transformer winding copper wire and the disassembly tension according to the surface roughness characteristics of the transformer winding copper wire extracted from the historical transformer winding copper wire disassembly image includes:

[0016] Extracting texture features of the historical transformer winding copper wire disassembly image, and constructing a surface roughness feature vector of the transformer winding copper wire according to the texture features, so as to determine whether the surface of the transformer winding copper wire is damaged;

[0017] When there is damage on the surface of the transformer winding copper wire, calculating the damage area ratio and the maximum damage depth of the transformer winding copper wire as quantitative indicators of the degree of surface damage;

[0018] The functional relationship between the quantitative index and the disassembly tension is fitted by a polynomial regression method to obtain the correlation between the surface damage data of the transformer winding copper wire and the disassembly tension.

[0019] As one of the preferred solutions, the extracting of texture features of the historical transformer winding copper wire disassembly image includes:

[0020] The surface texture features of the disassembled image of the historical transformer winding copper wire are highlighted by local binary pattern transformation to obtain a surface clear texture image;

[0021] Extracting surface features of the surface clear texture image through a gray level co-occurrence matrix, and calculating feature statistics based on the surface features; the feature statistics include energy, contrast, entropy, correlation, average roughness and maximum contour height;

[0022] The texture features of the historical transformer winding copper wire disassembly image are determined according to the feature statistics.

[0023] As one of the preferred solutions, the constitutive model based on the insulating layer is used to determine the stress distribution and deformation of the insulating layer under different disassembly tensions through finite element analysis and analyze, and obtain the critical disassembly tension range required for completely stripping the insulating layer, including:

[0024] Based on the constitutive model of the insulating layer, the bonding strength and fracture energy of the interface between the insulating layer and the transformer winding copper wire are obtained to construct a cohesive force parameter model of the transformer winding copper wire interface;

[0025] Based on the constitutive model of the insulating layer and the cohesive force parameter model of the transformer winding copper wire interface, the disassembly process of the transformer winding copper wire is simulated by finite element analysis to obtain the stress distribution and deformation data of the insulating layer under different disassembly tensions;

[0026] Determining the stress-strain curve and the peeling force-displacement curve of the insulating layer according to the stress distribution and deformation data, so as to generate a peeling behavior evolution model of the insulating layer under different disassembly tensions;

[0027] The peeling force sudden drop point is taken as the curve characteristic point, and the preset peeling area is taken as the critical point. The critical disassembly tension range required for completely peeling off the insulating layer in the peeling behavior evolution model is determined according to the curve characteristic point and the critical point.

[0028] As one of the preferred solutions, a multi-objective optimization model is constructed and solved according to the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range to obtain an optimal disassembly tension control strategy, including:

[0029] constructing a plurality of single-objective models according to the critical disassembly tension threshold, the association relationship and the critical disassembly tension range;

[0030] Taking disassembly tension as a decision variable and maximizing the quality of copper wire recovery of transformer windings as an optimization goal, a plurality of single-objective models are transformed into a multi-objective optimization model;

[0031] The multi-objective optimization model is solved by improving the non-dominated sorting genetic algorithm to obtain the optimal disassembly tension control strategy.

[0032] As one of the preferred solutions, the multi-objective optimization model is solved by improving the non-dominated sorting genetic algorithm to obtain the optimal disassembly tension control strategy, including:

[0033] Initialize a population containing several individuals, and set the initial values ​​of population size, crossover probability, mutation probability and number of iterations;

[0034] The individuals in the initialized population are stratified according to non-dominated relationships, and the crowding degree of each individual is calculated by the multi-objective optimization model;

[0035] The parent individuals are selected according to the non-dominated hierarchical level and crowding degree of each individual through the binary tournament selection strategy;

[0036] Based on the crossover probability after the initial value setting and the mutation probability after the initial value setting, the crossover probability and the mutation probability are adjusted by uniform crossover and uniform mutation according to the crowding degree of each individual, and the individuals are crossovered and mutated respectively by the adjusted crossover probability and mutation probability to obtain offspring individuals;

[0037] The parent individuals and the offspring individuals are merged to obtain a new population, and non-dominated sorting and crowding degree calculation are performed on the new population to obtain new parent individuals and new offspring individuals to iteratively update the new population until the number of iterations is reached, and a final population is output;

[0038] The final population is comprehensively evaluated by the superior and inferior solution distance method to calculate the Euclidean distance of each solution in the final population relative to the ideal solution and the negative ideal solution to obtain a comprehensive performance index, and the solution with the highest comprehensive performance index is selected as the optimal disassembly tension control strategy.

[0039] As one of the preferred solutions, after constructing and solving a multi-objective optimization model according to the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range to obtain the optimal disassembly tension control strategy, the method includes:

[0040] Acquire a real-time disassembly image of the transformer winding copper wire when the optimal disassembly tension control strategy is executed, and extract real-time roughness characteristics of the transformer winding copper wire surface and stripping state characteristics of the insulation layer from the real-time disassembly image of the transformer winding copper wire;

[0041] The real-time roughness characteristics of the transformer winding copper wire surface and the peeling state characteristics are input into a multi-layer feedforward neural network, and the fitness function constructed by the evaluation index of the real-time roughness characteristics of the transformer winding copper wire surface and the evaluation index of the peeling state characteristics is used to guide the standard particle swarm algorithm and the cooperative particle swarm algorithm to search for the optimal weight and the optimal bias of the multi-layer feedforward neural network, so that the multi-layer feedforward neural network with the optimal weight and the optimal bias is set to output the optimal disassembly tension optimization value;

[0042] The optimal disassembly tension optimization value, the deviation of the current disassembly tension and the deviation change rate are input into a fuzzy PID controller to convert the input quantity of the fuzzy PID controller into a language variable, and the language variable is inferred based on a preset fuzzy rule to obtain a PID parameter adjustment quantity;

[0043] The tension applying mechanism is controlled to adjust the disassembly tension according to the tension adjustment amount corresponding to the PID parameter adjustment amount.

[0044] As one of the preferred solutions, after constructing and solving a multi-objective optimization model according to the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range to obtain the optimal disassembly tension control strategy, the method further includes:

[0045] Constructing original quality evaluation data of the transformer winding copper wire according to the real-time roughness characteristics of the transformer winding copper wire surface and the peeling state characteristics;

[0046] Extracting the time domain features and frequency domain features of the original quality evaluation data to obtain quality evaluation features, and quantifying the degree of correlation between the quality evaluation features by a correlation analysis method to obtain feature correlation;

[0047] Based on the relationship between the feature correlation and the preset correlation threshold, a transformer winding copper wire quality assessment model is constructed by a random forest algorithm to determine the quality grade of the disassembled transformer winding copper wire, and the corresponding processing technology is determined according to the quality grade of the disassembled transformer winding copper wire.

[0048] A second aspect of the present invention provides a transformer winding copper wire processing system based on tension monitoring, comprising:

[0049] A tension threshold analysis module is used to obtain the mechanical performance parameters of the transformer winding copper wire to establish a mechanical model of the transformer winding copper wire. Based on the mechanical model of the transformer winding copper wire, the stress and strain distribution of the transformer winding copper wire under different disassembly tensions is determined by finite element analysis and analyzed to obtain a critical disassembly tension threshold at which the transformer winding copper wire undergoes permanent deformation;

[0050] A correlation determination module is used to obtain the historical transformer winding copper wire disassembly image, and determine the correlation between the surface damage data of the transformer winding copper wire and the disassembly tension according to the surface roughness characteristics of the transformer winding copper wire extracted from the historical transformer winding copper wire disassembly image;

[0051] A tension range generation module is used to obtain the tear strength and thickness uniformity of the insulating layer in the copper wire of the transformer winding to establish a constitutive model of the insulating layer. Based on the constitutive model of the insulating layer, the stress distribution and deformation of the insulating layer under different disassembly tensions are determined and analyzed by finite element analysis to obtain a critical disassembly tension range required for completely stripping the insulating layer.

[0052] The optimal strategy solving module is used to construct and solve a multi-objective optimization model according to the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range to obtain an optimal disassembly tension control strategy.

[0053] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0054] (1) Finite element analysis based on physical models provides highly accurate predictions of the behavior of transformer winding copper wires. It can accurately simulate and analyze the stress and strain distribution of transformer winding copper wires and insulation layers under different disassembly tensions, providing accurate data support for the formulation of subsequent strategies.

[0055] (2) By analyzing the critical disassembly tension threshold at which permanent deformation of the transformer winding copper wire occurs, combined with the correlation between the surface roughness characteristics of the transformer winding copper wire and the disassembly tension, the surface damage of the transformer winding copper wire during the processing process can be monitored and evaluated in real time, and the disassembly strategy can be adjusted in time to effectively prevent damage to the transformer winding copper wire;

[0056] (3) The construction of the multi-objective optimization model comprehensively considers multiple key factors such as transformer winding copper wire deformation, surface damage, and insulation peeling. By solving the model, the optimal disassembly tension control strategy can be obtained, which not only ensures the efficiency of the processing process, but also achieves effective cost control by reducing unnecessary damage and waste;

[0057] (4) The present invention combines finite element analysis technology, image processing technology and multi-objective optimization to form a complete and operational disassembly strategy formulation process, which helps to improve the intelligence level of the disassembly process, reduce human intervention and errors, and improve overall processing efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the implementation mode will be briefly introduced below. Obviously, the drawings described below are only some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1 It is a flow chart of a transformer winding copper wire processing method based on tension monitoring provided by a certain embodiment of the present invention;

[0060] Figure 2 It is a structural diagram of a transformer winding copper wire processing system based on tension monitoring provided by a certain embodiment of the present invention. DETAILED DESCRIPTION

[0061] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings and embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. 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.

[0062] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0063] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two components. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are for illustrative purposes only, and do not indicate or imply that the system or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0064] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0065] In one embodiment, if Figure 1 As shown, the first aspect of the present invention provides a transformer winding copper wire processing method based on tension monitoring, comprising:

[0066] S1. Obtaining mechanical property parameters of transformer winding copper wire to establish a mechanical model of transformer winding copper wire. Based on the mechanical model of transformer winding copper wire, determining the stress and strain distribution of the transformer winding copper wire under different disassembly tensions through finite element analysis and analyzing, to obtain a critical disassembly tension threshold at which permanent deformation of the transformer winding copper wire occurs;

[0067] Specifically, the present invention obtains mechanical property parameters including elastic modulus E, yield stress σy and tangent modulus Et by conducting material tests on transformer winding copper wire, and adopts a bilinear hardening model to describe the elastic-plastic behavior of transformer winding copper wire, and establishes a piecewise function expression of the relationship between stress and strain, that is, the mechanical model of transformer winding copper wire is: σ=Eε(ε≤εy), σ=σy+Et(ε-εy)(ε>εy), where εy is the yield strain. The present invention can accurately simulate and analyze the stress and strain distribution of transformer winding copper wire under different disassembly tensions by obtaining the mechanical property parameters of transformer winding copper wire and establishing a mechanical model. This finite element analysis based on the physical model provides a highly accurate prediction of the behavior of transformer winding copper wire, which helps to avoid damage caused by excessive or insufficient disassembly tension.

[0068] In one embodiment, based on the mechanical model of the transformer winding copper wire, the stress and strain distribution of the transformer winding copper wire under different disassembly tensions is determined by finite element analysis and analyzed to obtain a critical disassembly tension threshold at which the transformer winding copper wire undergoes permanent deformation, including:

[0069] Setting boundary conditions and load steps, and calculating stress and strain distribution data of the transformer winding copper wire under different disassembly tensions by a finite element solver;

[0070] Calculating the maximum equivalent stress and equivalent plasticity of the transformer winding copper wire under different disassembly tensions according to the stress and strain distribution data to determine the critical disassembly tension of the transformer winding copper wire when yielding;

[0071] Introducing a plastic strain accumulation rule, and establishing a relationship model between the plastic strain and disassembly tension of the transformer winding copper wire based on the critical disassembly tension;

[0072] The critical plastic strain threshold of the transformer winding copper wire during permanent deformation is obtained, and the relationship model is solved by the critical plastic strain threshold to obtain the critical disassembly tension threshold of the transformer winding copper wire during permanent deformation.

[0073] Specifically, the present invention uses ANSYS finite elements for modeling, adopts SOLID185 units to mesh the constructed transformer winding copper wire mechanical model, selects hexahedral units to mesh the transformer winding copper wire, applies different sizes of disassembly tensions to the ends of the transformer winding copper wire, sets boundary conditions and load steps, runs a finite element solver to calculate the stress and strain distribution of the transformer winding copper wire during the disassembly process, and obtains stress and strain distribution cloud maps of the transformer winding copper wire under different disassembly tensions; extracts the maximum equivalent stress and equivalent plastic strain of each cross section of the transformer winding copper wire under different disassembly tensions from the finite element simulation results, i.e., the stress and strain distribution cloud maps, and draws relationship curves between the disassembly tension and the maximum equivalent stress and the maximum equivalent plastic strain, and the critical disassembly tension Fc at which the transformer winding copper wire yields can be determined by analyzing the yield points of the two relationship curves.

[0074] The concept of plastic strain accumulation is introduced, that is, after the material is subjected to stress, part of the deformation is irreversible, and the plastic strain will not be completely restored due to the disappearance of stress. Based on the critical disassembly tension, the relationship model between the plastic strain εp and the disassembly tension F is established as εp=a(F-Fc)^b, where a and b are unknown coefficients. Based on the yield strength and critical disassembly tension of the transformer winding copper wire, a quantitative relationship model between the cross-sectional deformation variable Δ of the transformer winding copper wire and the disassembly tension F can be established, and the quadratic polynomial function is fitted as Δ=k0+k1F+k2F^2, where k0, k1, and k2 are fitting coefficients; then the fitting coefficient is determined by the least squares method, and the critical plastic strain threshold εpc of the transformer winding copper wire at permanent deformation is set. By solving the equation εp=εpc, the corresponding critical disassembly tension Fpc is obtained as the disassembly tension threshold for permanent deformation of the transformer winding copper wire. The present invention simulates and analyzes the copper wire disassembly process through finite element analysis technology, and can obtain the critical disassembly tension threshold at which the copper wire undergoes permanent deformation, so as to avoid using a disassembly tension exceeding the threshold, thereby effectively preventing permanent damage to the copper wire and extending the service life of the transformer winding.

[0075] S2, obtaining the historical transformer winding copper wire disassembly image, and determining the correlation between the surface damage data of the transformer winding copper wire and the disassembly tension according to the surface roughness characteristics of the transformer winding copper wire extracted from the historical transformer winding copper wire disassembly image;

[0076] Specifically, the present application uses a high-speed industrial camera to perform real-time imaging of the copper wire surface during the disassembly process, sets the image acquisition frequency to 60 frames per second, and the image resolution to 1920×1080 pixels. It is linked with the disassembly equipment through a synchronization trigger to ensure that the image acquisition and disassembly process are carried out simultaneously, and a real-time historical transformer winding copper wire disassembly image is obtained. A ring-shaped LED light source is used in image acquisition to provide uniform lighting, eliminate shadows and reflections, and improve image quality.

[0077] In one embodiment, determining the correlation between the surface damage data of the transformer winding copper wire and the disassembly tension according to the surface roughness feature of the transformer winding copper wire extracted from the historical transformer winding copper wire disassembly image includes:

[0078] Extracting texture features of the historical transformer winding copper wire disassembly image, and constructing a surface roughness feature vector of the transformer winding copper wire according to the texture features, so as to determine whether the surface of the transformer winding copper wire is damaged;

[0079] When there is damage on the surface of the transformer winding copper wire, calculating the damage area ratio and the maximum damage depth of the transformer winding copper wire as quantitative indicators of the degree of surface damage;

[0080] The functional relationship between the quantitative index and the disassembly tension is fitted by a polynomial regression method to obtain the correlation between the surface damage data of the transformer winding copper wire and the disassembly tension.

[0081] Specifically, the present invention constructs a surface roughness feature vector of the transformer winding copper wire according to texture features extracted from historical transformer winding copper wire disassembly images, uses a pre-labeled sample data set, and sets the kernel function to a radial basis function (RBF), optimizes hyperparameters through grid search to train a support vector machine, and then uses the trained support vector machine to classify the newly collected surface roughness feature vector of the transformer winding copper wire to determine whether the copper wire surface is damaged; then, based on the classification result of the support vector machine, if it is determined that there is surface damage, the damage area ratio and the maximum damage depth are calculated as the degree of surface damage. Quantitative indicators, and combined with the current disassembly tension, the corresponding relationship between the quantitative indicators of the degree of damage and the disassembly tension is established. The functional relationship between the proportion of the damage area, the maximum damage depth and the disassembly tension is fitted by polynomial regression, and a quadratic polynomial model of the form y=a0+a1x+a2x^2 is obtained, where y represents the degree of damage index, x represents the disassembly tension, and a0, a1, and a2 are fitting coefficients; finally, the fitting coefficients are determined by the least squares method, and a mathematical model of the correlation between the surface damage of the copper wire and the disassembly tension is established, so that the surface damage data of the transformer winding copper wire and the correlation between the disassembly tension can be obtained. The present invention combines the correlation between the surface roughness characteristics of the copper wire and the disassembly tension, and can monitor and evaluate the surface damage of the copper wire during the disassembly process in real time, adjust the disassembly strategy in time, and protect the copper wire from unnecessary damage.

[0082] In one embodiment, extracting texture features of the historical transformer winding copper wire disassembly image includes:

[0083] The surface texture features of the disassembled image of the historical transformer winding copper wire are highlighted by local binary pattern transformation to obtain a surface clear texture image;

[0084] Extracting surface features of the surface clear texture image through a gray level co-occurrence matrix, and calculating feature statistics based on the surface features; the feature statistics include energy, contrast, entropy, correlation, average roughness and maximum contour height;

[0085] The texture features of the historical transformer winding copper wire disassembly image are determined according to the feature statistics.

[0086] Specifically, the collected historical transformer winding copper wire disassembly images are preprocessed, that is, Gaussian filtering is used to remove image noise, histogram equalization is used to enhance image contrast, and local binary pattern (LBP) transform is applied to highlight surface texture features to obtain a clear surface texture image of the copper wire surface; then the grayscale co-occurrence matrix is ​​used to extract the texture features of the copper wire surface, and six feature statistics of energy, contrast, entropy, correlation, average roughness (Ra) and maximum profile height (Rz) are calculated, and these feature statistics are comprehensively evaluated. If the image has a large energy, high contrast, and large entropy value, and the average roughness and maximum profile height are also large, then it can be considered that the texture of the image is coarser and more complex. The extracted eigenvalues ​​can also be compared with the texture eigenvalues ​​of the transformer winding copper wire disassembly images in the historical database. By comparison, the similarities and differences in texture features between the current image and the historical image can be judged, so as to determine the texture features of the historical transformer winding copper wire disassembly images, so as to accurately determine the surface damage of the transformer winding copper wire under different disassembly tensions, and support the formulation of subsequent disassembly strategies.

[0087] S3, obtaining the tear strength and thickness uniformity of the insulating layer in the copper wire of the transformer winding to establish a constitutive model of the insulating layer, and based on the constitutive model of the insulating layer, determining the stress distribution and deformation of the insulating layer under different disassembly tensions through finite element analysis and analyzing them to obtain the critical disassembly tension range required for completely stripping the insulating layer;

[0088] Specifically, the present invention obtains the tear strength and thickness uniformity of the copper wire insulation layer material measured by a laser interferometer, and obtains the elastic modulus, Poisson's ratio and yield stress of the insulation layer measured by a material tensile test, to establish an elastic-plastic constitutive model of the insulation layer material taking into account the thickness non-uniformity. The model uses the thickness distribution data as an input parameter, and a piecewise linear hardening model is used to describe and output the stress-strain relationship of the insulation layer.

[0089] In one embodiment, the constitutive model based on the insulating layer determines and analyzes the stress distribution and deformation of the insulating layer under different disassembly tensions through finite element analysis to obtain the critical disassembly tension range required for completely stripping the insulating layer, including:

[0090] Based on the constitutive model of the insulating layer, the bonding strength and fracture energy of the interface between the insulating layer and the transformer winding copper wire are obtained to construct a cohesive force parameter model of the transformer winding copper wire interface;

[0091] Based on the constitutive model of the insulating layer and the cohesive force parameter model of the transformer winding copper wire interface, the disassembly process of the transformer winding copper wire is simulated by finite element analysis to obtain the stress distribution and deformation data of the insulating layer under different disassembly tensions;

[0092] Determining the stress-strain curve and the peeling force-displacement curve of the insulating layer according to the stress distribution and deformation data, so as to generate a peeling behavior evolution model of the insulating layer under different disassembly tensions;

[0093] The peeling force sudden drop point is taken as the curve characteristic point, and the preset peeling area is taken as the critical point. The critical disassembly tension range required for completely peeling off the insulating layer in the peeling behavior evolution model is determined according to the curve characteristic point and the critical point.

[0094] Specifically, based on the established constitutive model of the insulating layer, the bonding strength and fracture energy of the interface between the insulating layer and the copper wire measured by the double cantilever beam test and the 90-degree peel test were obtained, and the exponential cohesion model was used to describe the interface adhesion characteristics. The cohesion model parameters were fit by the nonlinear least squares method to obtain the cohesion parameter model of the transformer winding copper wire interface. Then, a numerical model of insulation layer stripping was constructed using the finite element software ABAQUS, and the insulation layer constitutive model and interface cohesion model were imported into the software. The boundary conditions and load steps were set, and the explicit dynamics solver was selected. The time step was set to 1e-6s, and the damping coefficient was taken as 0.05. The mass scaling technology was used to improve the calculation efficiency, so as to calculate the stress distribution and deformation of the insulation layer under different disassembly tensions, and extract the stress-strain curve and the stripping force-displacement curve in the insulation layer stripping process to generate the stripping behavior evolution model of the insulation layer under different disassembly tensions. The model includes the stripping behavior evolution process under different disassembly tensions and the stress and strain, stripping force and displacement data contained therein. By defining the stripping force drop point as the characteristic point of the curve and taking 50% stripping area as the critical point, the critical disassembly tension range required for complete stripping of the insulation layer in the stripping behavior evolution model is determined according to the characteristic point and the critical point, and the functional relationship between the stripping area and the disassembly tension is established to predict the degree of insulation layer stripping under different disassembly tensions, providing a basis for optimizing the disassembly process.

[0095] The present invention constructs a cohesive force parameter model of the transformer winding copper wire interface based on the constitutive model of the insulating layer, providing accurate basic data for subsequent finite element analysis; the stress distribution and deformation data obtained through finite element analysis further determine the stress and strain curve and the peeling force and displacement curve of the insulating layer, which not only reveals the mechanical behavior of the insulating layer during the disassembly process, but also provides key information for generating a stripping behavior evolution model, which is helpful to optimize the disassembly strategy; taking the stripping force drop point as the curve characteristic point and the preset stripping area as the critical point, the critical disassembly tension range required for completely stripping the insulating layer in the stripping behavior evolution model is determined, which is helpful to improve the disassembly efficiency.

[0096] S4, constructing and solving a multi-objective optimization model according to the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range to obtain an optimal disassembly tension control strategy;

[0097] In one embodiment, step S4 includes:

[0098] constructing a plurality of single-objective models according to the critical disassembly tension threshold, the association relationship and the critical disassembly tension range;

[0099] Taking disassembly tension as a decision variable and maximizing the quality of copper wire recovery of transformer windings as an optimization goal, a plurality of single-objective models are transformed into a multi-objective optimization model;

[0100] The multi-objective optimization model is solved by improving the non-dominated sorting genetic algorithm to obtain the optimal disassembly tension control strategy.

[0101] Specifically, the present invention establishes a mathematical model of disassembly tension and copper wire recycling quality and recycling efficiency according to the critical disassembly tension threshold of permanent deformation of copper wire, the correlation law between surface damage and disassembly tension, and the critical disassembly tension range of insulation stripping, that is, a quadratic function is used to describe the relationship between disassembly tension T and permanent deformation degree D as D=a1T²+b1T+c1; an exponential function is used to express the relationship between surface damage degree S and disassembly tension T as S=a2exp(b2T)+c2; a logarithmic function is used to describe the relationship between insulation stripping rate R and disassembly tension T as R=a3ln(T)+ b3; where a1, b1, c1, a2, b2, c2, a3, b3 are undetermined coefficients; then the disassembly tension T is used as the decision variable, and the value range of the disassembly tension is set to [Tmin, Tmax]; the constraints include the degree of permanent deformation D≤Dmax, the degree of surface damage S≤Smax, and the insulation stripping rate R≥Rmin; the optimization goal is to maximize the copper wire recovery quality Q=f1(D,S) and maximize the recovery efficiency E=f2(R), where f1 and f2 are corresponding objective functions, and multiple single-objective models are converted into multi-objective optimization models. The multi-objective optimization model constructed by the present invention can consider multiple performance indicators at the same time, so as to find the best disassembly tension setting under the premise of satisfying multiple constraints to achieve the optimization of the overall performance, which is helpful to improve the recovery quality of transformer winding copper wire, and the optimized disassembly process can also improve the disassembly efficiency and reduce the disassembly time and cost.

[0102] In one embodiment, solving the multi-objective optimization model by improving the non-dominated sorting genetic algorithm to obtain the optimal disassembly tension control strategy includes:

[0103] Initialize a population containing several individuals, and set the initial values ​​of population size, crossover probability, mutation probability and number of iterations;

[0104] The individuals in the initialized population are stratified according to non-dominated relationships, and the crowding degree of each individual is calculated by the multi-objective optimization model;

[0105] The parent individuals are selected according to the non-dominated hierarchical level and crowding degree of each individual through the binary tournament selection strategy;

[0106] Based on the crossover probability after the initial value setting and the mutation probability after the initial value setting, the crossover probability and the mutation probability are adjusted by uniform crossover and uniform mutation according to the crowding degree of each individual, and the individuals are crossovered and mutated respectively by the adjusted crossover probability and mutation probability to obtain offspring individuals;

[0107] The parent individuals and the offspring individuals are merged to obtain a new population, and non-dominated sorting and crowding degree calculation are performed on the new population to obtain new parent individuals and new offspring individuals to iteratively update the new population until the number of iterations is reached, and a final population is output;

[0108] The final population is comprehensively evaluated by the superior and inferior solution distance method to calculate the Euclidean distance of each solution in the final population relative to the ideal solution and the negative ideal solution to obtain a comprehensive performance index, and the solution with the highest comprehensive performance index is selected as the optimal disassembly tension control strategy.

[0109] First, the population is initialized, relevant parameters are set and several individuals are randomly generated. Each individual corresponds to a disassembly tension control strategy, which at least includes the size of the disassembly tension, expressed in binary or other coding methods; then the fitness value of each individual is calculated through the multi-objective optimization model, and the individuals in the population are stratified according to the non-dominated relationship, that is, the Pareto frontier, and the crowding degree is calculated to measure its diversity in the population. The greater the crowding degree, the higher the uniqueness of the individual in the population; then two individuals are randomly selected from the population, and the non-dominated stratification level and crowding degree are compared to select the better individual as the parent individual, and this process is repeated until enough parent individuals are selected; according to the crossover probability Pc, the selected parent individuals are uniformly crossed to generate offspring individuals. The crossover probability can be dynamically adjusted according to the crowding degree of the individual, Pc=k1 / (1+exp(k2*(f-favg))), to increase the diversity of the population, and according to the mutation probability Pm, the offspring individuals are uniformly mutated to increase the diversity of the population. New gene information is introduced, and the mutation probability can also be dynamically adjusted according to the crowding degree of the individual, Pm=k3 / (1+exp(k4*(fmax-f))), where k1, k2, k3, k4 are adjustment parameters, f is the individual fitness, favg is the average fitness of the population, and fmax is the maximum fitness of the population; the parent individuals and the offspring individuals are merged to form a new population, and the new population is non-dominated sorting and crowding degree are calculated to prepare for the next round of iteration. According to the non-dominated sorting and crowding degree, the excellent individuals in the new population are selected as the parent individuals of the next round for iterative update; until the preset number of iterations is reached, the iteration is stopped; and the individuals in the final population are comprehensively evaluated by the superior and inferior solution distance method (TOPSIS), and the weight vector is [0.4, 0.3, 0.3], which corresponds to the degree of permanent deformation, the degree of surface damage and the stripping rate, respectively. The solution with the highest comprehensive performance index is selected as the optimal disassembly tension control strategy, and the disassembly tension value that takes into account the mechanical properties, surface quality and insulation stripping effect of the copper wire is obtained.

[0110] The present invention gradually approaches the optimal solution through the steps of initializing the population, non-dominated sorting and crowding calculation, selecting parent individuals, crossover and mutation operations, new population generation and iterative updating, so as to improve the search efficiency and global convergence; through non-dominated sorting and crowding calculation, the scheme can effectively deal with the conflicts and trade-offs in multi-objective optimization problems, find a set of Pareto optimal solutions, and provide more choices for decision makers.

[0111] In one embodiment, step S4 includes:

[0112] Acquire a real-time disassembly image of the transformer winding copper wire when the optimal disassembly tension control strategy is executed, and extract real-time roughness characteristics of the transformer winding copper wire surface and stripping state characteristics of the insulation layer from the real-time disassembly image of the transformer winding copper wire;

[0113] The real-time roughness characteristics of the transformer winding copper wire surface and the peeling state characteristics are input into a multi-layer feedforward neural network, and the fitness function constructed by the evaluation index of the real-time roughness characteristics of the transformer winding copper wire surface and the evaluation index of the peeling state characteristics is used to guide the standard particle swarm algorithm and the cooperative particle swarm algorithm to search for the optimal weight and the optimal bias of the multi-layer feedforward neural network, so that the multi-layer feedforward neural network with the optimal weight and the optimal bias is set to output the optimal disassembly tension optimization value;

[0114] The optimal disassembly tension optimization value, the deviation of the current disassembly tension and the deviation change rate are input into a fuzzy PID controller to convert the input quantity of the fuzzy PID controller into a language variable, and the language variable is inferred based on a preset fuzzy rule to obtain a PID parameter adjustment quantity;

[0115] The tension applying mechanism is controlled to adjust the disassembly tension according to the tension adjustment amount corresponding to the PID parameter adjustment amount.

[0116] Specifically, the present invention adopts a tension roller driven by a servo motor to form a flexible and adjustable tension applying mechanism, and constructs a closed-loop feedback control system through an encoder and a tension sensor. The encoder monitors the speed of the servo motor in real time, and the tension sensor directly measures the size of the disassembly tension. The two cooperate to achieve precise control of the disassembly tension. The controller adjusts the speed and torque output of the servo motor according to the feedback signal, and dynamically adjusts the rotation angle and pressure of the tension roller. At the same time, a confocal microscope and a high-speed camera are used to construct a real-time monitoring system. The confocal microscope scans the surface of the copper wire to obtain three-dimensional contour data and calculates the surface roughness parameters. The high-speed camera collects the insulation layer peeling image, and the peeling area is extracted by an image segmentation algorithm, and the peeling area ratio is calculated; then the collected data is subjected to bandpass filtering to remove noise, and statistical features such as mean, standard deviation and kurtosis are extracted.

[0117] The processed feature data is transmitted to the multi-layer feedforward neural network of the central controller, and the error function of the input data is used as the fitness function, and the particle swarm is initialized. Each particle represents a set of weights and biases of the multi-layer feedforward neural network. During initialization, the position and velocity of the particle (i.e., initial weights and biases) are randomly generated; then, for each particle (i.e., each set of weights and biases), the multi-layer feedforward neural network is used for forward propagation, the network output, i.e., the predicted disassembly tension, is calculated, and its fitness is evaluated according to the fitness function; and according to the current position, velocity, global optimal position and individual optimal position of each particle, the position and velocity of the particle are updated according to its corresponding inertia weight; then, on the basis of the standard particle swarm algorithm, multiple sub-populations are introduced, each sub-population independently searches for the optimal solution, and exchanges information regularly to achieve cooperative search, so as to increase the diversity of the search and avoid premature convergence, iterate the above process until the maximum number of iterations is reached, then stop the search, output the optimal weights and biases of the multi-layer feedforward neural network, set the multi-layer feedforward neural network to have the optimal weights and biases, and then use the network for real-time prediction to output the optimal disassembly tension optimization value.

[0118] At the same time, the three continuous physical quantities of the optimal disassembly tension optimization value, the current disassembly tension deviation and the deviation change rate are converted into input language variables of the fuzzy controller. According to the fuzzy rules determined by historical data, the fuzzy reasoning method (such as Mamdani reasoning, Sugeno reasoning, etc.) is used to calculate the adjustment amount of the PID parameters. The result of the fuzzy reasoning is converted into specific PID parameter adjustment amount through the center of gravity method. The PID controller is controlled to calculate the control amount according to the adjusted parameters to realize dynamic adjustment of the disassembly tension.

[0119] The present invention inputs the real-time roughness characteristics of the copper wire surface and the stripping state characteristics of the insulation layer into a multi-layer feedforward neural network, and the network finds the optimal weight and bias through a joint search of a standard particle swarm algorithm and a cooperative particle swarm algorithm, thereby outputting the optimal disassembly tension optimization value; the obtained optimization value is input into a fuzzy PID controller, and the controller adjusts the PID parameters according to the deviation and deviation change rate of the current disassembly tension, thereby achieving precise control of the disassembly tension. Through real-time image processing and feature extraction, the roughness of the copper wire surface and the stripping state of the insulation layer can be accurately obtained, thereby achieving precise control of the disassembly tension, which can not only improve the disassembly efficiency, but also reduce the copper wire damage or insulation layer residue caused by improper tension, and improve the disassembly quality; the solution combines a variety of intelligent technologies such as multi-layer feedforward neural network, particle swarm algorithm and fuzzy PID controller to achieve intelligent control of disassembly tension to adapt to different disassembly environments and conditions, and improve the robustness and adaptability of the system; through automated and intelligent disassembly tension control, it can reduce dependence on manual operation, reduce labor intensity, improve the safety and reliability of the disassembly process, and improve the copper wire disassembly rate and efficiency.

[0120] In one embodiment, after step S4, the method further includes:

[0121] Constructing original quality evaluation data of the transformer winding copper wire according to the real-time roughness characteristics of the transformer winding copper wire surface and the peeling state characteristics;

[0122] Extracting the time domain features and frequency domain features of the original quality evaluation data to obtain quality evaluation features, and quantifying the degree of correlation between the quality evaluation features by a correlation analysis method to obtain feature correlation;

[0123] Based on the relationship between the feature correlation and the preset correlation threshold, a transformer winding copper wire quality assessment model is constructed by a random forest algorithm to determine the quality grade of the disassembled transformer winding copper wire, and the corresponding processing technology is determined according to the quality grade of the disassembled transformer winding copper wire.

[0124] Specifically, the present application uses the real-time roughness characteristics and peeling state characteristics of the transformer winding copper wire surface as the original quality evaluation data of the transformer winding copper wire, uses wavelet transform to denoise the original quality evaluation data, uses Fourier transform to extract frequency domain characteristics, and uses statistical methods to calculate time domain characteristics to obtain quality evaluation characteristics; then uses Pearson correlation coefficient, mutual information, principal component analysis and maximum information coefficient and other methods to quantify the correlation between evaluation features and determine feature correlation. If the feature correlation is greater than a preset correlation threshold, a random forest algorithm is used to construct a transformer winding copper wire quality evaluation model. The random forest algorithm The method includes setting the number of trees, the maximum depth and the minimum number of leaf node samples, deploying the copper wire quality assessment model to the edge computing device, performing online reasoning based on the real-time quality evaluation data received by the edge computing device, judging the quality grade of the recycled copper wire, and using an automatic sorting system to transport copper wires of different grades to the corresponding processing areas. High-quality copper wires with a conductivity ≥ 98% enter the direct remelting remelting area, low-quality copper wires with a conductivity < 95% enter the electrolytic refining area, and medium-quality copper wires with a conductivity of 95% ≤ < 98% are dynamically allocated according to the impurity content. Those with an impurity content < 0.1% enter the remelting area, otherwise they enter the refining area. If the recycled copper wire is low-quality copper wire, the surface impurities and oxide layer are removed through a pretreatment system, which includes pickling and high-pressure water jet cleaning devices. The treated copper wire is then put into an electrolytic cell as an anode, and an intelligent power management system is used to control the electrolytic current density. The process parameters and quality data of each processing link are obtained, and a correlation model between the process parameters and product quality is established through a random forest algorithm based on the process parameters and quality data. According to the prediction results of the correlation model, the processing parameters are optimized in real time, and the smelting temperature or electrolytic current density is adjusted.

[0125] The present invention can obtain the quality information of copper wire instantly by real-time monitoring the surface roughness characteristics and stripping state characteristics of transformer winding copper wire, and provide timely data support for subsequent processing and treatment; the extraction and feature analysis of original quality evaluation data (including time domain and frequency domain characteristics) can more comprehensively reflect the quality status of copper wire and improve the accuracy of evaluation; the correlation analysis method is used to quantify the correlation between quality evaluation features, which is helpful to identify the key factors that have the greatest impact on the quality of copper wire, and provide an important basis for the subsequent quality evaluation model construction; based on the relationship between feature correlation and preset correlation threshold, the random forest algorithm is used to construct the transformer winding copper wire quality evaluation model, which can realize intelligent quality grade determination; according to the quality grade of the disassembled transformer winding copper wire, the corresponding processing technology can be determined in a targeted manner, and the rational use of resources and the maximization of processing efficiency can be realized. The entire process, from data collection, feature extraction, correlation analysis to the construction of quality evaluation model, reflects the trend of automation and intelligence. This intelligent quality evaluation and management method helps to reduce manual intervention and errors, improve production efficiency and product quality, and reduce production costs.

[0126] In the embodiment of the present application, based on the problem that the current processing scheme for transformer winding copper wire is time-consuming and inefficient, a transformer winding copper wire processing method based on tension monitoring is designed, which realizes obtaining the mechanical performance parameters of the transformer winding copper wire to establish a mechanical model of the transformer winding copper wire, and based on the transformer winding copper wire mechanical model, the stress and strain distribution of the transformer winding copper wire under different disassembly tensions is determined and analyzed by finite element analysis to obtain the critical disassembly tension threshold for permanent deformation of the transformer winding copper wire; the historical transformer winding copper wire disassembly image is obtained, and the transformer winding copper wire surface roughness characteristics extracted from the historical transformer winding copper wire disassembly image are determined. The invention discloses a method for realizing a technical scheme of intelligent disassembly of copper wire of transformer winding by using a finite element method to analyze the surface damage data of copper wire of transformer winding and the disassembly tension; obtaining the tear strength and thickness uniformity of the insulating layer in the copper wire of transformer winding to establish the constitutive model of the insulating layer; determining the stress distribution and deformation of the insulating layer under different disassembly tensions through finite element analysis based on the constitutive model of the insulating layer and analyzing them, so as to obtain the critical disassembly tension range required for completely peeling off the insulating layer; constructing a multi-objective optimization model according to the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range and solving it, so as to obtain the technical scheme of the optimal disassembly tension control strategy; realizing the efficient and intelligent disassembly and recycling of copper wire of transformer winding, and improving the recycling quality and efficiency of copper wire of transformer winding.

[0127] It should be noted that although the steps in the above flowchart are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders.

[0128] In another embodiment, if Figure 2 As shown, the second aspect of the present invention provides a transformer winding copper wire processing system based on tension monitoring, comprising:

[0129] The tension threshold analysis module 10 is used to obtain the mechanical performance parameters of the transformer winding copper wire to establish a mechanical model of the transformer winding copper wire. Based on the mechanical model of the transformer winding copper wire, the stress and strain distribution of the transformer winding copper wire under different disassembly tensions is determined by finite element analysis and analyzed to obtain a critical disassembly tension threshold at which the transformer winding copper wire undergoes permanent deformation;

[0130] The correlation determination module 20 is used to obtain the historical transformer winding copper wire disassembly image, and determine the correlation between the surface damage data of the transformer winding copper wire and the disassembly tension according to the surface roughness characteristics of the transformer winding copper wire extracted from the historical transformer winding copper wire disassembly image;

[0131] A tension range generating module 30 is used to obtain the tear strength and thickness uniformity of the insulating layer in the copper wire of the transformer winding to establish a constitutive model of the insulating layer, and based on the constitutive model of the insulating layer, determine the stress distribution and deformation of the insulating layer under different disassembly tensions through finite element analysis and analyze them to obtain the critical disassembly tension range required for completely stripping the insulating layer;

[0132] The optimal strategy solving module 40 is used to construct and solve a multi-objective optimization model according to the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range to obtain an optimal disassembly tension control strategy.

[0133] It should be noted that each module in the above-mentioned transformer winding copper wire processing system based on tension monitoring can be fully or partially implemented by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. For the specific definition of a transformer winding copper wire processing system based on tension monitoring, please refer to the definition of a transformer winding copper wire processing method based on tension monitoring above. The two have the same functions and effects, which will not be repeated here.

[0134] In summary, the present invention relates to the field of information technology, and discloses a transformer winding copper wire processing method and system based on tension monitoring. A transformer winding copper wire mechanical model established by mechanical property parameters of the transformer winding copper wire is combined with finite element analysis technology to determine the critical disassembly tension threshold for permanent deformation of the transformer winding copper wire; through the surface roughness characteristics of the transformer winding copper wire of the historical transformer winding copper wire disassembly image, the finite element analysis technology is combined to determine the correlation between the surface damage data of the transformer winding copper wire and the disassembly tension, as well as the critical disassembly tension range required for completely stripping the insulation layer of the transformer winding copper wire; based on the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range, a multi-objective optimization model is constructed and solved to obtain the optimal disassembly tension control strategy. This scheme realizes efficient and intelligent disassembly and recycling of the transformer winding copper wire, and improves the recycling quality and recycling efficiency of the transformer winding copper wire.

[0135] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be directly referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0136] The above-mentioned embodiments only express several preferred implementation modes of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in the technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be based on the protection scope of the claims.

Claims

1. A transformer winding copper wire processing method based on tension monitoring, characterized in that: include: Obtaining mechanical property parameters of the transformer winding copper wire to establish a mechanical model of the transformer winding copper wire, and based on the mechanical model of the transformer winding copper wire, determining the stress and strain distribution of the transformer winding copper wire under different disassembly tensions through finite element analysis and analyzing, to obtain a critical disassembly tension threshold at which the transformer winding copper wire undergoes permanent deformation; Acquire a historical transformer winding copper wire disassembly image, and determine a correlation between surface damage data of the transformer winding copper wire and disassembly tension based on a surface roughness feature of the transformer winding copper wire extracted from the historical transformer winding copper wire disassembly image; The tear strength and thickness uniformity of the insulating layer in the copper wire of the transformer winding are obtained to establish a constitutive model of the insulating layer. Based on the constitutive model of the insulating layer, the stress distribution and deformation of the insulating layer under different disassembly tensions are determined and analyzed by finite element analysis to obtain a critical disassembly tension range required for completely stripping the insulating layer. A multi-objective optimization model is constructed and solved according to the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range to obtain an optimal disassembly tension control strategy; The constitutive model based on the insulating layer determines and analyzes the stress distribution and deformation of the insulating layer under different disassembly tensions through finite element analysis to obtain the critical disassembly tension range required for completely stripping the insulating layer, including: Based on the constitutive model of the insulating layer, the bonding strength and fracture energy of the interface between the insulating layer and the transformer winding copper wire are obtained to construct a cohesive force parameter model of the transformer winding copper wire interface; Based on the constitutive model of the insulating layer and the cohesive force parameter model of the transformer winding copper wire interface, the disassembly process of the transformer winding copper wire is simulated by finite element analysis to obtain the stress distribution and deformation data of the insulating layer under different disassembly tensions; Determining the stress-strain curve and the peeling force-displacement curve of the insulating layer according to the stress distribution and deformation data, so as to generate a peeling behavior evolution model of the insulating layer under different disassembly tensions; The peeling force sudden drop point is taken as the curve characteristic point, and the preset peeling area is taken as the critical point. The critical disassembly tension range required for completely peeling off the insulating layer in the peeling behavior evolution model is determined according to the curve characteristic point and the critical point.

2. A transformer winding copper wire processing method based on tension monitoring according to claim 1, characterized in that: Based on the mechanical model of the transformer winding copper wire, the stress and strain distribution of the transformer winding copper wire under different disassembly tensions is determined by finite element analysis and analyzed to obtain the critical disassembly tension threshold at which the transformer winding copper wire undergoes permanent deformation, including: Setting boundary conditions and load steps, and calculating stress and strain distribution data of the transformer winding copper wire under different disassembly tensions by a finite element solver; Calculating the maximum equivalent stress and equivalent plasticity of the transformer winding copper wire under different disassembly tensions according to the stress and strain distribution data to determine the critical disassembly tension of the transformer winding copper wire when yielding; Introducing a plastic strain accumulation rule, and establishing a relationship model between the plastic strain and disassembly tension of the transformer winding copper wire based on the critical disassembly tension; The critical plastic strain threshold of the transformer winding copper wire during permanent deformation is obtained, and the relationship model is solved by the critical plastic strain threshold to obtain the critical disassembly tension threshold of the transformer winding copper wire during permanent deformation.

3. The method for processing transformer winding copper wire based on tension monitoring according to claim 1, characterized in that: The determining of the correlation between the surface damage data of the transformer winding copper wire and the disassembly tension according to the surface roughness features of the transformer winding copper wire extracted from the historical transformer winding copper wire disassembly image comprises: Extracting texture features of the historical transformer winding copper wire disassembly image, and constructing a surface roughness feature vector of the transformer winding copper wire according to the texture features, so as to determine whether the surface of the transformer winding copper wire is damaged; When there is damage on the surface of the transformer winding copper wire, calculating the damage area ratio and the maximum damage depth of the transformer winding copper wire as quantitative indicators of the degree of surface damage; The functional relationship between the quantitative index and the disassembly tension is fitted by a polynomial regression method to obtain the correlation between the surface damage data of the transformer winding copper wire and the disassembly tension.

4. The method for processing transformer winding copper wire based on tension monitoring according to claim 3, characterized in that: The extracting of texture features of the historical transformer winding copper wire disassembly image comprises: The surface texture features of the disassembled image of the historical transformer winding copper wire are highlighted by local binary pattern transformation to obtain a surface clear texture image; Extracting surface features of the surface clear texture image through a gray level co-occurrence matrix, and calculating feature statistics based on the surface features; the feature statistics include energy, contrast, entropy, correlation, average roughness and maximum contour height; The texture features of the historical transformer winding copper wire disassembly image are determined according to the feature statistics.

5. The method for processing transformer winding copper wire based on tension monitoring according to claim 1, characterized in that: The multi-objective optimization model is constructed and solved according to the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range to obtain the optimal disassembly tension control strategy, including: constructing a plurality of single-objective models according to the critical disassembly tension threshold, the association relationship and the critical disassembly tension range; Taking disassembly tension as a decision variable and maximizing the quality of copper wire recovery of transformer windings as an optimization goal, a plurality of single-objective models are transformed into a multi-objective optimization model; The multi-objective optimization model is solved by improving the non-dominated sorting genetic algorithm to obtain the optimal disassembly tension control strategy.

6. The method for processing transformer winding copper wire based on tension monitoring according to claim 5, characterized in that: The multi-objective optimization model is solved by improving the non-dominated sorting genetic algorithm to obtain the optimal disassembly tension control strategy, including: Initialize a population containing several individuals, and set the initial values ​​of population size, crossover probability, mutation probability and number of iterations; The individuals in the initialized population are stratified according to non-dominated relationships, and the crowding degree of each individual is calculated by the multi-objective optimization model; The parent individuals are selected according to the non-dominated hierarchical level and crowding degree of each individual through the binary tournament selection strategy; Based on the crossover probability after the initial value setting and the mutation probability after the initial value setting, the crossover probability and the mutation probability are adjusted by uniform crossover and uniform mutation according to the crowding degree of each individual, and the individuals are crossovered and mutated respectively by the adjusted crossover probability and mutation probability to obtain offspring individuals; The parent individuals and the offspring individuals are merged to obtain a new population, and non-dominated sorting and crowding degree calculation are performed on the new population to obtain new parent individuals and new offspring individuals to iteratively update the new population until the number of iterations is reached, and a final population is output; The final population is comprehensively evaluated by the superior and inferior solution distance method to calculate the Euclidean distance of each solution in the final population relative to the ideal solution and the negative ideal solution to obtain a comprehensive performance index, and the solution with the highest comprehensive performance index is selected as the optimal disassembly tension control strategy.

7. The method for processing transformer winding copper wire based on tension monitoring according to claim 1, characterized in that: After constructing and solving a multi-objective optimization model according to the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range to obtain an optimal disassembly tension control strategy, the method includes: Acquire a real-time disassembly image of the transformer winding copper wire when the optimal disassembly tension control strategy is executed, and extract real-time roughness characteristics of the transformer winding copper wire surface and stripping state characteristics of the insulation layer from the real-time disassembly image of the transformer winding copper wire; The real-time roughness characteristics of the transformer winding copper wire surface and the peeling state characteristics are input into a multi-layer feedforward neural network, and the fitness function constructed by the evaluation index of the real-time roughness characteristics of the transformer winding copper wire surface and the evaluation index of the peeling state characteristics is used to guide the standard particle swarm algorithm and the cooperative particle swarm algorithm to search for the optimal weight and the optimal bias of the multi-layer feedforward neural network, so that the multi-layer feedforward neural network with the optimal weight and the optimal bias is set to output the optimal disassembly tension optimization value; The optimal disassembly tension optimization value, the deviation of the current disassembly tension and the deviation change rate are input into a fuzzy PID controller to convert the input quantity of the fuzzy PID controller into a language variable, and the language variable is inferred based on a preset fuzzy rule to obtain a PID parameter adjustment quantity; The tension applying mechanism is controlled to adjust the disassembly tension according to the tension adjustment amount corresponding to the PID parameter adjustment amount.

8. The method for processing transformer winding copper wire based on tension monitoring according to claim 7, characterized in that: After constructing and solving a multi-objective optimization model according to the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range to obtain an optimal disassembly tension control strategy, the method further includes: Constructing original quality evaluation data of the transformer winding copper wire according to the real-time roughness characteristics of the transformer winding copper wire surface and the peeling state characteristics; Extracting the time domain features and frequency domain features of the original quality evaluation data to obtain quality evaluation features, and quantifying the degree of correlation between the quality evaluation features by a correlation analysis method to obtain feature correlation; Based on the relationship between the feature correlation and the preset correlation threshold, a transformer winding copper wire quality assessment model is constructed by a random forest algorithm to determine the quality grade of the disassembled transformer winding copper wire, and the corresponding processing technology is determined according to the quality grade of the disassembled transformer winding copper wire.

9. A transformer winding copper wire processing system based on tension monitoring, characterized in that: include: A tension threshold analysis module is used to obtain the mechanical performance parameters of the transformer winding copper wire to establish a mechanical model of the transformer winding copper wire. Based on the mechanical model of the transformer winding copper wire, the stress and strain distribution of the transformer winding copper wire under different disassembly tensions is determined by finite element analysis and analyzed to obtain a critical disassembly tension threshold at which the transformer winding copper wire undergoes permanent deformation; A correlation determination module is used to obtain a historical transformer winding copper wire disassembly image, and determine the correlation between the surface damage data of the transformer winding copper wire and the disassembly tension according to the surface roughness characteristics of the transformer winding copper wire extracted from the historical transformer winding copper wire disassembly image; A tension range generation module is used to obtain the tear strength and thickness uniformity of the insulating layer in the copper wire of the transformer winding to establish a constitutive model of the insulating layer. Based on the constitutive model of the insulating layer, the stress distribution and deformation of the insulating layer under different disassembly tensions are determined and analyzed by finite element analysis to obtain a critical disassembly tension range required for completely stripping the insulating layer. An optimal strategy solving module, used to construct and solve a multi-objective optimization model according to the critical disassembly tension threshold, the correlation relationship and the critical disassembly tension range, to obtain an optimal disassembly tension control strategy; The constitutive model based on the insulating layer determines and analyzes the stress distribution and deformation of the insulating layer under different disassembly tensions through finite element analysis to obtain the critical disassembly tension range required for completely stripping the insulating layer, including: Based on the constitutive model of the insulating layer, the bonding strength and fracture energy of the interface between the insulating layer and the transformer winding copper wire are obtained to construct a cohesive force parameter model of the transformer winding copper wire interface; Based on the constitutive model of the insulating layer and the cohesive force parameter model of the transformer winding copper wire interface, the disassembly process of the transformer winding copper wire is simulated by finite element analysis to obtain the stress distribution and deformation data of the insulating layer under different disassembly tensions; Determining the stress-strain curve and the peeling force-displacement curve of the insulating layer according to the stress distribution and deformation data, so as to generate a peeling behavior evolution model of the insulating layer under different disassembly tensions; The peeling force sudden drop point is taken as the curve characteristic point, and the preset peeling area is taken as the critical point. The critical disassembly tension range required for completely peeling off the insulating layer in the peeling behavior evolution model is determined according to the curve characteristic point and the critical point.

Images