Copper strip overlapping parameter determination method and device, equipment, storage medium and product

Abstract

The invention discloses a copper strip overlapping parameter determination method, device and equipment, a storage medium and a product, and relates to the technical field of medium-voltage copper strip overlapping production, and the method comprises the steps: determining the target copper strip overlapping width; the target copper strip overlapping width and a preset copper strip overlapping parameter interval serve as constraint conditions, the copper strip overlapping fitting model is solved through a genetic algorithm, and target copper strip overlapping parameters are obtained; the copper strip overlapping fitting model is obtained by fitting a plurality of groups of copper strip overlapping parameters and copper strip overlapping width measured values corresponding to each group of copper strip overlapping parameters, and is used for obtaining the copper strip overlapping parameters of the copper strip overlapping fitting model, wherein the copper strip overlapping parameters comprise a wrapping speed, a traction speed, a wrapping motor current, a traction motor current, a wrapping motor torque and a traction motor torque. According to the invention, excellent copper strip overlapping rate control can be realized, and the cable production efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of medium-voltage copper strip covering production, and in particular to a method, device, equipment, storage medium and product for determining copper strip covering parameters. Background Art

[0002] The overlap ratio of medium-voltage copper tape (the ratio of the overlap width to the width of a single copper tape turn) is a key indicator of the shielding layer of medium-voltage cables, directly affecting the cable's shielding effectiveness, electrical performance, and long-term reliability. In related technologies, manufacturers typically control the overlap ratio by adjusting process parameters such as wrapping speed and wrapping angle based on historical experience to achieve the target overlap width and achieve an optimal overlap ratio.

[0003] However, the above-mentioned method that relies entirely on manual experience is difficult to fully consider the dynamic changes of various factors in the cable production process, resulting in that the overlap rate of medium-voltage copper tape is difficult to achieve a better value; at the same time, when production materials and equipment are replaced, operators need to spend a lot of time repeatedly debugging production parameters, which will also affect the production efficiency of the cable. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device, equipment, storage medium and product for determining copper tape overlapping parameters, aiming to solve the technical problems that the copper tape overlapping parameter determination method of the related art is difficult to achieve the optimal copper tape overlapping rate and easily affects the production efficiency of the cable.

[0005] To achieve the above objectives, the present application proposes a method for determining copper tape overlapping parameters, which includes:

[0006] Determine the target copper tape overlap width;

[0007] The target copper tape overlapping width and the preset copper tape overlapping parameter range are used as constraints, and the genetic algorithm is used to solve the copper tape overlapping fitting model to obtain the target copper tape overlapping parameters; the copper tape overlapping fitting model is obtained by fitting multiple groups of copper tape overlapping parameters and the actual measured values ​​of the copper tape overlapping width corresponding to each group of copper tape overlapping parameters. The copper tape overlapping parameters used to obtain the copper tape overlapping fitting model include winding speed, traction speed, winding motor current, traction motor current, winding motor torque and traction motor torque.

[0008] In one embodiment, before the step of solving the copper tape overlap fitting model using a genetic algorithm and obtaining the target copper tape overlap parameters, the method further includes:

[0009] Obtain a sample data set; the sample data set includes multiple sets of copper tape overlapping parameters and measured values ​​of copper tape overlapping widths corresponding to each set of copper tape overlapping parameters;

[0010] The preset fitting model is trained based on the sample data set to obtain a copper strip covering fitting model; the preset fitting model includes a random forest model.

[0011] In one embodiment, after the step of training a preset fitting model based on a sample data set to obtain a copper tape overlapping fitting model, the method further includes:

[0012] For each set of copper tape overlapping parameters in the sample data set, the copper tape overlapping parameters are input into the copper tape overlapping fitting model to obtain the copper tape overlapping width fitting value corresponding to the copper tape overlapping parameters;

[0013] The preset correction model is trained based on multiple sets of copper tape overlap parameters and corresponding residual values ​​to obtain a residual correction model; the residual value is the difference between the measured value of the copper tape overlap width and the fitted value of the copper tape overlap width, and the preset correction model is the XGBOOST model;

[0014] The copper tape covering fitting model is updated based on the residual correction model to obtain an updated copper tape covering fitting model.

[0015] In one embodiment, the step of obtaining a sample data set includes:

[0016] Obtain a historical production sample data set; the historical production sample data set includes multiple sets of historical production sample data on a shielding process production line, and the historical production sample data includes historical copper tape overlap parameters and corresponding historical copper tape overlap width measured values;

[0017] Inputting the historical production sample data set into the generative adversarial network model for data simulation to obtain a simulated sample data set; the simulated sample data set includes multiple groups of simulated sample data, and the simulated sample data have consistent data characteristics with the historical production sample data;

[0018] A sample data set is obtained based on a historical production sample data set and a simulation sample data set.

[0019] In one embodiment, after the step of obtaining a historical production sample dataset, the method further includes:

[0020] Perform preprocessing operations on the historical production sample data set to obtain a processed historical production sample data set; the preprocessing operations include outlier processing, missing value filling and normalization processing;

[0021] Based on the fluctuation state of the data in the processed historical production sample data set, the historical production sample data corresponding to the unstable stage of the shielding process production line is identified and eliminated to obtain a stable production sample data set;

[0022] Input the historical production sample dataset into the generative adversarial network model for data simulation. The steps to obtain the simulated sample dataset include:

[0023] Input the stable production sample data set into the generative adversarial network model for data simulation to obtain a simulated sample data set;

[0024] Based on the historical production sample dataset and the simulation sample dataset, the steps for obtaining the sample dataset include:

[0025] A sample data set is obtained based on a stable production sample data set and a simulation sample data set.

[0026] In one embodiment, the target copper tape overlap width and the preset copper tape overlap parameter range are used as constraints, and a genetic algorithm is used to solve the copper tape overlap fitting model to obtain the target copper tape overlap parameters. The steps include:

[0027] Generate a copper tape covering parameter cluster within a preset copper tape covering parameter range based on a genetic algorithm; the copper tape covering parameter cluster includes at least one set of candidate copper tape covering parameters;

[0028] determining at least one set of target copper tape overlapping parameters from the copper tape overlapping parameter cluster based on a width difference between the copper tape overlapping width fitting values ​​corresponding to each set of candidate copper tape overlapping parameters and the target copper tape overlapping width; the copper tape overlapping width fitting values ​​are obtained by inputting the candidate copper tape overlapping parameters into a copper tape overlapping fitting model;

[0029] The target copper tape overlapping parameters are subjected to crossover and mutation operations to generate a new copper tape overlapping parameter cluster, and the step of determining at least one group of target copper tape overlapping parameters from the copper tape overlapping parameter cluster based on the width difference between the copper tape overlapping width fitting value corresponding to each group of candidate copper tape overlapping parameters and the target copper tape overlapping width is returned to be executed until the width difference is less than a preset difference or the number of iterations reaches a preset number.

[0030] In addition, to achieve the above-mentioned purpose, the present application also proposes a copper tape overlapping parameter determination device, which includes:

[0031] A determination module is used to determine a target copper tape overlap width;

[0032] An acquisition module is used to use the target copper tape overlapping width and the preset copper tape overlapping parameter range as constraints, and use the genetic algorithm to solve the copper tape overlapping fitting model to obtain the target copper tape overlapping parameters; the copper tape overlapping fitting model is obtained by fitting multiple groups of copper tape overlapping parameters and the actual measured values ​​of the copper tape overlapping width corresponding to each group of copper tape overlapping parameters. The copper tape overlapping parameters used to obtain the copper tape overlapping fitting model include winding speed, traction speed, winding motor current, traction motor current, winding motor torque and traction motor torque.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a copper tape overlapping parameter determination device, which includes: a memory, a processor, and a computer program stored in the memory and runnable on the processor, and the computer program is configured to implement the steps of the copper tape overlapping parameter determination method as described above.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the copper tape overlapping parameter determination method as described above are implemented.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the copper tape overlapping parameter determination method as described above.

[0036] One or more technical solutions proposed in this application have at least the following technical effects:

[0037] The copper tape overlapping parameter determination method proposed in the present application can first determine the target copper tape overlapping width; then use the target copper tape overlapping width and the preset copper tape overlapping parameter range as constraints, and use the genetic algorithm to solve the copper tape overlapping fitting model to obtain the target copper tape overlapping parameters; wherein, the copper tape overlapping fitting model is obtained by fitting multiple sets of copper tape overlapping parameters and the actual measured values ​​of the copper tape overlapping width corresponding to each set of copper tape overlapping parameters, and the copper tape overlapping parameters used to obtain the copper tape overlapping fitting model include winding speed, traction speed, winding motor current, traction motor current, winding motor torque and traction motor torque, etc.

[0038] The copper tape overlap fitting model in this application takes into account multiple influencing factors such as wrapping speed, traction speed, motor current, torque, etc., and after determining the target copper tape overlap width, a genetic algorithm with high dynamic adaptability is used to solve the problem based on the copper tape overlap fitting model. A wide search can be conducted in the parameter space to automatically find the optimal parameter combination that meets the conditions. Compared with relying on manual experience to control simple process parameters such as wrapping speed and wrapping angle in the production process, this application comprehensively considers the influencing factors of the copper tape overlap width, automatically searches for the optimal solution through a genetic algorithm, and through global optimization and dynamic adaptability, can achieve a better copper tape overlap rate, improve the shielding effect, electrical performance and long-term reliability of the cable, and at the same time, the automated parameter determination reduces the dependence on operator experience and improves production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0041] Figure 1 A schematic diagram of a process flow provided in Example 1 of the method for determining copper tape overlapping parameters of the present application;

[0042] Figure 2 Schematic diagram of the basic structure of the GAN model;

[0043] Figure 3 Schematic diagram of the data before and after the copper strip covering fitting model was corrected using the XGBOOST model;

[0044] Figure 4 This is a schematic diagram of the fitting results of the revised copper tape covering fitting model;

[0045] Figure 5 Schematic diagram of the genetic algorithm process;

[0046] Figure 6 This is a schematic block diagram of the overall process of an example method for determining copper tape overlay parameters;

[0047] Figure 7 This is a schematic diagram of the module structure of the device for determining copper strip overlapping parameters according to an embodiment of the present application;

[0048] Figure 8 Schematic diagram of the equipment structure of the hardware operating environment involved in the method for determining copper tape overlapping parameters in the embodiment of the present application.

[0049] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0051] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0052] The main solution of the embodiment of the present application is: determining the target copper strip overlap width; using the target copper strip overlap width and the preset copper strip overlap parameter range as constraints, using a genetic algorithm to solve the copper strip overlap fitting model to obtain the target copper strip overlap parameters; the copper strip overlap fitting model is obtained by fitting multiple sets of copper strip overlap parameters and the actual measured values ​​of the copper strip overlap width corresponding to each set of copper strip overlap parameters, and the copper strip overlap parameters used to obtain the copper strip overlap fitting model include winding speed, traction speed, winding motor current, traction motor current, winding motor torque and traction motor torque.

[0053] The overlap rate of medium-voltage copper tape is a key indicator of the medium-voltage cable shielding layer, directly affecting the cable's shielding effectiveness, electrical performance, and long-term reliability. Insufficient overlap rates can reduce the cable's shielding effectiveness, weaken its electromagnetic interference protection capabilities, and even affect the cable's mechanical strength and corrosion resistance. Excessive overlap rates, on the other hand, can lead to material waste and increase production costs. In related technologies, manufacturers rely primarily on the operator's experience to adjust wrapping process parameters such as tension, speed, and wrapping angle to achieve the target copper tape overlap width, thereby achieving an optimal medium-voltage copper tape overlap rate.

[0054] However, the above-mentioned method that relies entirely on manual experience lacks systematic data support for variables such as copper strip thickness uniformity, equipment accuracy, and environmental fluctuations. This experience-based method is difficult to fully consider the dynamic changes of various factors in the production process, resulting in large fluctuations in the overlap rate and difficulty in reaching a better value, and poor product quality consistency. At the same time, when replacing raw materials (such as copper strips from different batches or suppliers) or equipment (such as wrapping machines, tension controllers), operators often need to repeatedly debug parameters, which not only consumes a lot of time, but may also cause production interruptions and affect overall efficiency. Therefore, it is necessary to seek a method for determining the copper strip overlap parameters to achieve precise and automated adjustment of parameters and improve product quality and production efficiency.

[0055] This application provides a solution that uses a target copper tape overlap width and a preset copper tape overlap parameter range as constraints, and uses a genetic algorithm to solve a copper tape overlap fitting model to obtain the target copper tape overlap parameters. This copper tape overlap fitting model simultaneously considers multiple influencing factors such as wrapping speed, pulling speed, motor current, and torque. Once the target copper tape overlap width is determined, a genetic algorithm with high dynamic adaptability is used to solve the copper tape overlap fitting model. This algorithm can conduct an extensive search in the parameter space and automatically find the optimal parameter combination that meets the requirements. Compared to relying on manual experience to control simple process parameters such as wrapping speed and wrapping angle during the production process, this application comprehensively considers the factors affecting the copper tape overlap width, automatically searches for the optimal solution through a genetic algorithm, and through global optimization and dynamic adaptability, can achieve a better copper tape overlap rate, improve the shielding effect, electrical performance, and long-term reliability of the cable. At the same time, the automated parameter determination reduces dependence on operator experience and improves production efficiency.

[0056] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication, and program execution capabilities, such as a tablet computer, personal computer, or an electronic device capable of performing the aforementioned functions. This embodiment and the following embodiments will be described below using a device for determining copper tape overlap parameters as an example.

[0057] Based on this, the embodiment of the present application provides a method for determining copper tape overlapping parameters, referring to Figure 1 , Figure 1 This is a flow chart of Example 1 of the method for determining copper strip overlapping parameters of this application.

[0058] In this embodiment, the method for determining the copper tape overlapping parameters includes steps S100 to S200:

[0059] Step S100, determining a target copper tape overlapping width.

[0060] Step S200 : Taking the target copper tape overlap width and the preset copper tape overlap parameter range as constraints, a genetic algorithm is used to solve the copper tape overlap fitting model to obtain the target copper tape overlap parameters.

[0061] Among them, the copper tape overlapping fitting model is obtained by fitting multiple sets of copper tape overlapping parameters and the actual measured values ​​of the copper tape overlapping width corresponding to each set of copper tape overlapping parameters. The copper tape overlapping parameters used to obtain the copper tape overlapping fitting model include winding speed, traction speed, winding motor current, traction motor current, winding motor torque and traction motor torque.

[0062] Specifically, the medium voltage copper tape overlap rate is the ratio of the copper tape overlap width to the width of a single turn of copper tape. Therefore, in actual production operations, in order to achieve a better value for the medium voltage copper tape overlap rate, it is necessary to make the copper tape overlap width of the cables produced by the production line better; the target copper tape overlap width refers to the copper tape width expected to be achieved during the cable production process. The target copper tape overlap width can be set according to the product design requirements or the quality standards that need to be achieved during the production process.

[0063] After determining the target copper strip overlap width, the target copper strip overlap width and the preset copper strip overlap parameter range can be used as constraints, and the copper strip overlap fitting model can be solved using a genetic algorithm to obtain the equipment control parameters (i.e., target copper strip overlap parameters) that can produce the target copper strip overlap width. The copper strip overlap fitting model is established using multiple sets of copper strip overlap parameters and their corresponding measured values ​​of the copper strip overlap width, and can reflect the potential correlation between the copper strip overlap parameters and the copper strip overlap width. In actual applications, factors affecting the copper strip overlap width (i.e., copper strip overlap parameters) can be determined through daily production experience and root cause analysis of copper strip overlap rates based on massive production data, including but not limited to wrapping speed, traction speed, wrapping motor current, traction motor current, wrapping motor torque, and traction motor torque.

[0064] A large number of copper tape overlap parameters and copper tape overlap widths can be used to establish a mathematical model or a machine learning model to predict the change in copper tape overlap width under different copper tape overlap parameters. The trained model can be used as the copper tape overlap fitting model. In one feasible embodiment, steps A100 to A200 can be included before step S200 to construct the copper tape overlap fitting model:

[0065] Step A100 , obtaining a sample data set; the sample data set includes multiple sets of copper tape overlapping parameters and measured values ​​of copper tape overlapping width corresponding to each set of copper tape overlapping parameters.

[0066] Step A200: training a preset fitting model based on a sample data set to obtain a copper strip covering fitting model; the preset fitting model includes a random forest model.

[0067] Specifically, the sample data set includes multiple sets of copper tape overlap parameters and the measured values ​​of the copper tape overlap width corresponding to each set of parameters. These data can be obtained from actual data in historical production processes. In order to enrich the data volume of the sample data set and improve the generalization ability and accuracy of model training, in a feasible implementation, step A100 can specifically include steps A110 to A130:

[0068] Step A110, obtaining a historical production sample data set; the historical production sample data set includes multiple groups of historical production sample data on the shielding process production line, and the historical production sample data includes historical copper tape overlapping parameters and corresponding historical copper tape overlapping width measured values.

[0069] In step A120 , the historical production sample data set is input into the generative adversarial network model for data simulation to obtain a simulated sample data set; the simulated sample data set includes multiple groups of simulated sample data, and the simulated sample data has consistent data features with the historical production sample data.

[0070] Step A130 : Acquire a sample data set based on the historical production sample data set and the simulation sample data set.

[0071] Understandably, the copper tape overlap width is primarily related to the shielding process of cable production. Shielding is a common cable shielding method that reduces electromagnetic interference and radio frequency interference by spirally wrapping or longitudinally wrapping copper tape around the cable insulation. Copper tape has good conductivity and flexibility, and can fit tightly against the cable structure to provide a uniform shielding effect. The copper tape shielding process requires strict quality control (such as strict control of the copper tape overlap width) to ensure that the shielding layer is continuous and seamless, so as to improve the cable's anti-interference ability and reliability; therefore, multiple groups of historical production sample data on the shielding process production line can be obtained to construct a historical production sample data set. The historical production sample data include historical copper tape overlap parameters (wrapping speed, traction speed, wrapping motor current, traction motor current, wrapping motor torque and traction motor torque, etc.) and corresponding historical copper tape overlap width measured values; the shielding process production line is a production system including a wrapping unit, a pay-off device, a take-up device, an overlap detection device, a control system and various auxiliary devices. The wrapping speed, traction speed, wrapping motor current, traction motor current, wrapping motor torque and traction motor torque and other parameters can be monitored and collected through sensors installed on the wrapping unit, the pay-off device and the take-up device. At the same time, the overlap detection device can also monitor and obtain the corresponding copper tape overlap width measured values. These data can be used to construct a historical production sample data set.

[0072] Then, the above historical production sample dataset is input into the Generative Adversarial Network (GAN) model to generate a new simulated sample dataset; Figure 2 As shown, Figure 2Figure 2 is a schematic diagram of the basic structure of the GAN model. The GAN model is a deep learning model that generates new samples through adversarial training of two neural networks. The structure of the GAN model consists of two main parts: the generator and the discriminator. The generator's task is to generate data that is as realistic as possible in an attempt to "fool" the discriminator: the generator generates initial samples from random noise. As training progresses, the generator gradually learns the distribution of the target sample data. The task of the discriminator is to distinguish between real samples and generated samples. It receives real sample data (Real Sample) and generated sample data (FakeSample) and outputs a probability value (predict label) to indicate the possibility that the input data is real data. During the training process, the generator and the discriminator compete with each other (the goal of the generator is to maximize the probability of the discriminator making mistakes, while the goal of the discriminator is to minimize its mistakes). This adversarial training enables both to continuously improve, and eventually the generator can generate simulated data that is very similar to the real sample data. Therefore, in the simulated sample data set obtained by inputting the historical production sample data set into the GAN model, multiple groups of simulated sample data and historical production data have the same data characteristics. In the subsequent fitting model training process, they can be used as additional training samples to enhance data diversity, thereby improving the generalization ability and accuracy of the fitting model.

[0073] In addition, in order to improve the data quality of the sample data set, after collecting the historical production sample data set, the historical production sample data set can also be preprocessed to obtain a processed historical production sample data set; the preprocessing operation includes outlier processing, missing value filling and normalization processing; based on the fluctuation state of the data in the processed historical production sample data set, the historical production sample data corresponding to the unstable stage of the shielding process production line is identified and eliminated to obtain a stable production sample data set.

[0074] Among them, outlier processing refers to correcting outliers for parameters with format anomalies, unit anomalies, and indentation anomalies in historical production sample data; missing value filling refers to filling in missing historical production sample data according to data definitions and related time series relationships. The filling methods may include but are not limited to filling by mean, filling by adjacent values, filling by median, or filling by category; the data after outlier processing and missing value filling are then normalized. Normalization is to convert the data into the range of [0, 1]. The normalization formula is: X i is the i-th historical production sample data, X min is the minimum value among the same sample data, X max is the maximum value among the same sample data, and X is the processed historical production sample data.

[0075] Based on the fluctuation state of the data in the processed historical production sample data set, the historical production sample data corresponding to the unstable stage of the shielding process production line are identified and eliminated to obtain a stable production sample data set. Specifically, the different production stages of the production line (including stable production stages and unstable stages) can be identified based on the fluctuation state of the two parameters of the wrapping speed and the pulling speed in the historical production sample data set; the stable production stage refers to the stage where the production line operates normally without interference from human factors. Generally, the parameters such as the wrapping speed and the pulling speed in the stable production stage show stable changes or regular fluctuations, while the unstable stage is generally the debugging stage, which is a stage that does not belong to production, including machine preheating, conductor replacement, personnel operation, etc., and the parameters such as the wrapping speed and the pulling speed fluctuate greatly. By eliminating the data in the unstable stage, a stable production sample data set is finally obtained, which can better represent the situation in the normal production process; after eliminating the unstable data, the remaining stable production sample data set is input into the GAN model to obtain a high-quality simulated sample data set. The simulated sample data set and the aforementioned stable production sample data set are integrated to obtain a sample data set for fitting model training.

[0076] The preset fitting model is trained using the sample data set to obtain a copper tape overlap fitting model, which can reflect the correlation between the copper tape overlap parameters and the copper tape overlap width. The preset fitting model can be continuously learned and trained based on the sample data, and the input copper tape overlap parameters are fitted into an output value, which is the copper tape overlap width fitting value. The above preset fitting model can be a random forest model; the random forest model is a machine learning algorithm that can construct multiple decision trees and combine their prediction results. It is often used for regression tasks and classification tasks. In actual model training, the model mean square error, R can be adjusted by adjusting the number of trees (n_estimators), maximum depth (max_depth), maximum number of features (max_features) and other parameters in the random forest model. 2 The evaluation indicators such as scores are optimized, and a fitting model with better performance is obtained.

[0077] It is worth mentioning that, in order to further improve the model output accuracy of the copper tape overlapping fitting model, in a feasible implementation, a residual correction model is introduced to correct the copper tape overlapping fitting model to obtain a more accurate fitting value; in this implementation, step A200 may further include steps A300 to A500:

[0078] Step A300: for each set of copper tape overlap parameters in the sample data set, the copper tape overlap parameters are input into a copper tape overlap fitting model to obtain a copper tape overlap width fitting value corresponding to the copper tape overlap parameters.

[0079] Step A400: Training a preset correction model based on multiple sets of copper tape overlap parameters and corresponding residual values ​​to obtain a residual correction model; the residual value is the difference between the measured value of the copper tape overlap width and the fitted value of the copper tape overlap width, and the preset correction model is an XGBOOST model.

[0080] Step A500: updating the copper tape overlapping fitting model based on the residual correction model to obtain an updated copper tape overlapping fitting model.

[0081] Specifically, each set of copper tape overlap parameters can obtain a corresponding copper tape overlap width fitting value after being processed by the copper tape overlap fitting model, and the difference between the copper tape overlap width fitting value and the copper tape overlap width measured value is calculated (the difference represents the fitting deviation of the copper tape overlap fitting model, which can also be called the residual value, residual value = measured value - fitting value), and the difference and the corresponding copper tape overlap parameters are used to train the preset correction model, so that the preset correction model can predict the possible residual value of the copper tape overlap fitting model output based on the input copper tape overlap parameters; thereby, the residual correction model can update and correct the copper tape overlap fitting model based on the predicted residual value to improve the accuracy of the output result of the copper tape overlap fitting model. Preferably, the preset correction model can be an XGBOOST model, which is a machine learning algorithm with the core principle of gradient boosting, which improves the prediction ability of the model by gradually constructing multiple weak classifiers (usually decision trees). For example, the predicted residual value of the trained XGBOOST model for the input copper tape overlap parameter is e. The residual value predicted by the XGBOOST model is added to the original fitting value of the random forest model to obtain the corrected fitting value, which is the final output of the copper tape overlap width fitting value of the copper tape overlap fitting model, as shown in Figure 3 As shown, Figure 3 This is a schematic diagram of the data before and after the copper strip covering fitting model was corrected using the XGBOOST model. Figure 3 The middle dot represents the original predicted value (i.e., original fitting value) output by the copper tape overlap fitting model when no correction is performed. Figure 3 The “×” point in the figure represents the adjusted predicted value (i.e. the corrected fitting value) output by the corrected copper tape overlap fitting model. Figure 3 The “Perfect Prediction” in the table represents the actual value. Figure 3 It is not difficult to see that the output of the revised copper tape covering fitting model is closer to the measured value and has higher fitting accuracy. In addition, in order to verify the reliability of the revised model, nearly 25,000 sets of copper tape covering parameters were input into the updated (revised) copper tape covering fitting model for fitting. Figure 4 The diagram is a schematic diagram of the fitting results of the modified copper tape covering fitting model. Figure 4As shown in the figure, “Actual Data” is the measured value of the copper tape overlap width corresponding to the copper tape overlap parameters, and “Predicted Data” is the fitting value of the copper tape overlap width output by the copper tape overlap fitting model. Figure 4 It can be seen that the fitting value of the copper tape overlap width can be very close to the measured value, the reliability of the fitting model is high, and it can better reflect the correlation between the copper tape overlap parameters and the copper tape overlap width.

[0082] After determining the copper tape overlap fitting model, the genetic algorithm can then, based on the copper tape overlap fitting model, use the target copper tape overlap width and the preset copper tape overlap parameter range as constraints to reversely determine the copper tape overlap parameters. A genetic algorithm (GA) is an optimization and search algorithm based on natural selection and genetics principles. It simulates the process of biological evolution and gradually approaches the optimal solution through operations such as selection, crossover (recombination), and mutation. In one feasible embodiment, step S200 can specifically include steps S210 to S230:

[0083] Step S210: generating a copper tape overlapping parameter cluster within a preset copper tape overlapping parameter range based on a genetic algorithm; the copper tape overlapping parameter cluster includes at least one group of candidate copper tape overlapping parameters.

[0084] Step S220: Determine at least one set of target copper tape overlap parameters from the copper tape overlap parameter cluster based on the width difference between the copper tape overlap width fitting values ​​corresponding to each set of candidate copper tape overlap parameters and the target copper tape overlap width; the copper tape overlap width fitting values ​​are obtained by inputting the candidate copper tape overlap parameters into the copper tape overlap fitting model.

[0085] Step S230, performing crossover and mutation operations on the target copper tape overlapping parameters to generate a new copper tape overlapping parameter cluster, and returning to execute the step of determining at least one group of target copper tape overlapping parameters from the copper tape overlapping parameter cluster based on the width difference between the copper tape overlapping width fitting value corresponding to each group of candidate copper tape overlapping parameters and the target copper tape overlapping width, until the width difference is less than the preset difference or the number of iterations reaches the preset number.

[0086] Specifically, the preset copper tape overlapping parameter range refers to the feasible value range of the predetermined target copper tape overlapping parameter, which can be determined based on engineering experience (such as determining a reasonable parameter range based on industry standards), physical limitations (such as considering the physical properties of the material, the parameter value may not exceed a certain limit), etc. Figure 5 As shown, Figure 5This is a flow chart of a genetic algorithm. Based on the genetic algorithm, a copper tape overlapping parameter cluster (i.e., an initialized total cluster) is randomly generated within a preset copper tape overlapping parameter range. The copper tape overlapping parameter cluster includes at least one group of candidate copper tape overlapping parameters, representing multiple possible configurations of the copper tape overlapping parameters. Then, based on the width difference between the copper tape overlapping width fitting value corresponding to each group of candidate copper tape overlapping parameters and the target copper tape overlapping width, at least one group of target copper tape overlapping parameters is determined from the copper tape overlapping parameter cluster. This is essentially a fitness assessment, that is, the quality of each group of copper tape overlapping parameters is evaluated through a fitness function. The fitness function is usually calculated based on the width difference between the copper tape overlapping width fitting value and the target copper tape overlapping width. The smaller the difference, the higher the fitness value.

[0087] At least one set of parameters with high fitness value is selected from the copper tape covering parameter cluster as the target copper tape covering parameter. The target copper tape covering parameter can be regarded as the parent individual, and then the parent individual is crossed to generate a new parameter combination (i.e. Figure 5 The offspring in the crossover operation are generated by exchanging part of the genetic information of the two parent individuals. The offspring then explore new possible solutions (i.e., new copper tape covering parameters) through mutation. The mutation operation randomly perturbs the offspring to increase genetic diversity. The new copper tape covering parameters replace the parameters in the original copper tape covering parameter cluster to form a new copper tape covering parameter cluster. The above operations are repeated to gradually approach the optimal solution until the termination condition is reached. The termination condition can be that the width difference is less than the preset difference or that the number of iterations reaches the preset number. The target copper tape covering parameters finally output are the optimal control parameters that can achieve the target copper tape covering width.

[0088] It should be noted that in actual applications, it was found that the two parameters of winding speed and pulling speed have the greatest impact on the copper strip overlap width, which can reach more than 90%. Therefore, when executing the step of using the target copper strip overlap width and the preset copper strip overlap parameter range as constraints and solving the copper strip overlap fitting model using the genetic algorithm to obtain the target copper strip overlap parameters, the winding speed and pulling speed can be used as the target copper strip overlap parameters to be determined. The remaining parameters with relatively small impact on the copper strip overlap width, such as the winding motor current, pulling motor current, winding motor torque, and pulling motor torque, can be directly set based on experience or production standards. It is understandable that the computational complexity of the genetic algorithm increases exponentially with the number of variables. If all parameters (such as current, torque, etc.) are included in the optimization, the search space will be too large and the computational time will increase. Focusing on the key variables (winding speed + pulling speed) can significantly reduce the optimization time and meet the real-time control requirements.

[0089] It is not difficult to understand that the copper tape overlap parameter determination method provided in the embodiments of the present application can use the target copper tape overlap width and the preset copper tape overlap parameter range as constraints, and use a genetic algorithm to solve the copper tape overlap fitting model to obtain the target copper tape overlap parameters. The copper tape overlap fitting model simultaneously considers multiple influencing factors such as wrapping speed, pulling speed, motor current, and torque. After determining the target copper tape overlap width, a genetic algorithm with high dynamic adaptability is used to solve the copper tape overlap fitting model, which can conduct an extensive search in the parameter space and automatically find the optimal parameter combination that meets the conditions. Compared with relying on manual experience to control simple process parameters such as wrapping speed and wrapping angle during the production process, the present application comprehensively considers the factors affecting the copper tape overlap width, automatically searches for the optimal solution through a genetic algorithm, and through global optimization and dynamic adaptability, can achieve a better copper tape overlap rate, improve the shielding effect, electrical performance, and long-term reliability of the cable. At the same time, the automated parameter determination reduces the dependence on operator experience and improves production efficiency.

[0090] For example, in order to help understand the implementation process of the method for determining the copper tape overlapping parameters provided in this embodiment, please refer to Figure 6 , Figure 6 A schematic block diagram of the overall process of a method for determining copper tape overlay parameters is provided, specifically:

[0091] First, all data related to raw materials, process parameters, equipment parameters, production parameters and inspection in the shielding process production line of the medium-voltage workshop within three months can be obtained. The data collection frequency can be one data point every 10 seconds; the collected data can also be quality analyzed and the available value of the analysis data can be evaluated. Data quality analysis mainly evaluates whether the data meets the conditions for data analysis from six dimensions: accuracy, validity, completeness, timeliness, consistency and uniqueness. Among them, accuracy refers to the authenticity and correctness of the data, ensuring that the data must reflect the real business content; validity refers to the applicability and compliance of the data with the intended use, and the value and format of the data must comply with the requirements of the data definition or business definition; integrity refers to the comprehensiveness and completeness of the data, measuring the completeness of the required data; timeliness refers to the timeliness and update frequency of the data, ensuring that the data is updated in a timely manner; consistency refers to the logic and compliance with expectations of the data, and the type, format, standard and meaning of the data must be consistent and clear; uniqueness refers to the unique identification and deduplication of the data, and there are no duplicate data values ​​for a certain data item or a group of data.

[0092] Data preprocessing is then performed on the data that has undergone quality assessment and analysis. This can correct outliers, including format anomalies, unit anomalies, and indentation anomalies. Missing data can be filled in by using the mean, adjacent values, median, or category, based on data definitions and time series relationships. To facilitate subsequent calculations, the data can also be normalized. Based on the fluctuations of key factors, stable production and unstable debugging stages can be identified, and the unstable debugging stage can be eliminated. The key factors are the wrapping speed and traction speed on the production line, with changes in these two speeds representing different production periods. A stable production stage is one in which data changes steadily or regularly, is not affected by human factors, and the production line operates normally. An unstable debugging stage is a non-production stage, including machine preheating, conductor replacement, and personnel operation. The data fluctuation characteristics and change patterns of the factors affecting the copper strip overlap rate during the stable production stage are analyzed. Combined with the production process mechanism model (production relationship logic, etc.), six controllable and adjustable parameters are determined: wrapping speed, traction speed, wrapping motor current, traction motor current, wrapping motor torque, and traction motor torque. It should be noted that the above content is mainly to analyze and determine the copper tape overlap parameters used to construct the copper tape overlap fitting model. After determining these parameters, these parameters and the corresponding copper tape overlap width measured values ​​can be directly collected in the subsequent data collection. Then, outlier processing, missing value filling, normalization and other processing can be performed, and the above data in the unstable stage can be eliminated without collecting all the data of the production line.

[0093] The processed data (wrap speed, traction speed, wrap motor current, traction motor current, wrap motor torque, traction motor torque and corresponding copper strip overlap width measured value) are integrated into the historical production sample data set and input into the GAN model for data enhancement to obtain a simulated sample data set. The historical production sample data set and the simulated sample data set are combined to jointly train the random forest model. The residual of the copper strip overlap width fitting value generated by the random forest model and the measured value of the copper strip overlap width is calculated, and the residual data is input into the XGBOOST model for training, so as to feedback and regulate according to the output results of the XGBOOST model to correct the random forest model. Lin model, thereby obtaining the final copper strip lap fitting model, and then based on the fitting model, the genetic optimization algorithm is used to optimize the wrapping speed, pulling speed and other parameters with the target copper strip lap width as the optimization target, and the optimal wrapping speed, pulling speed and other parameter values ​​that can achieve the target copper strip lap width are determined. Therefore, the above method can ensure the precise control of the copper strip lap width and the consistency of the copper strip lap quality. Combining high-precision fitting model with genetic optimization algorithm, through data-driven precise parameter intelligent reverse control adjustment, the debugging frequency and production stagnation caused by raw material differences, equipment fluctuations or environmental changes are greatly reduced, and production efficiency and production costs are significantly improved.

[0094] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the method for determining the copper tape overlapping parameters of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0095] This application also provides a copper tape overlapping parameter determination device, which can be configured in a copper tape overlapping parameter determination device, please refer to Figure 7 The copper tape overlapping parameter determination device comprises:

[0096] A determination module 10 is used to determine a target copper strip overlap width;

[0097] An acquisition module 20 is used to use the target copper strip overlap width and the preset copper strip overlap parameter range as constraints, and use a genetic algorithm to solve the copper strip overlap fitting model to obtain the target copper strip overlap parameters; the copper strip overlap fitting model is obtained by fitting multiple groups of copper strip overlap parameters and the actual measured values ​​of the copper strip overlap width corresponding to each group of copper strip overlap parameters. The copper strip overlap parameters used to obtain the copper strip overlap fitting model include winding speed, traction speed, winding motor current, traction motor current, winding motor torque and traction motor torque.

[0098] The copper tape overlap parameter determination device provided in this application utilizes the copper tape overlap parameter determination method described in the aforementioned embodiment, resolving the technical issues with the related art copper tape overlap parameter determination method, which struggles to achieve optimal copper tape overlap rates and easily impacts cable production efficiency. Compared to the related art, the copper tape overlap parameter determination device provided in this application achieves the same beneficial effects as the copper tape overlap parameter determination method described in the aforementioned embodiment. Other technical features of the copper tape overlap parameter determination device described in this application are the same as those disclosed in the aforementioned embodiment and are not further elaborated upon here.

[0099] The present application provides a device for determining copper tape overlapping parameters, which includes: 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 the copper tape overlapping parameter determination method in the above-mentioned embodiment 1.

[0100] Reference below Figure 8 , which shows a schematic diagram of the structure of a device for determining copper tape overlap parameters suitable for implementing embodiments of the present application. The device for determining copper tape overlap parameters in embodiments of the present application may include, but is not limited to, mobile terminals such as laptop computers and PADs (Portable Application Descriptions), as well as fixed terminals such as desktop computers. Figure 8The copper tape overlapping parameter determination device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0101] like Figure 8 As shown, the copper tape overlap parameter determination device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the copper tape overlap parameter determination device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to I / O interface 1006: input devices 1007, such as a touch screen, touchpad, keyboard, mouse, image sensor, microphone, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003, such as a magnetic tape or hard disk; and communication device 1009. The communication device 1009 can allow the copper tape overlap parameter determination device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a copper tape overlap parameter determination device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems can be implemented or have alternatively.

[0102] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0103] The copper tape overlap parameter determination device provided in this application utilizes the copper tape overlap parameter determination method described in the aforementioned embodiment, resolving the technical issues with the related art copper tape overlap parameter determination method, which struggles to achieve optimal copper tape overlap rates and easily impacts cable production efficiency. Compared to the related art, the copper tape overlap parameter determination device provided in this application achieves the same beneficial effects as the copper tape overlap parameter determination method described in the aforementioned embodiment. Other technical features of this copper tape overlap parameter determination device are the same as those disclosed in the aforementioned embodiment and are not further elaborated upon here.

[0104] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0105] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0106] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, wherein the computer-readable program instructions are used to execute the method for determining the copper tape overlapping parameters in the above-mentioned embodiment.

[0107] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0108] The computer-readable storage medium may be included in the copper tape overlap parameter determination device; or may exist independently without being assembled into the copper tape overlap parameter determination device.

[0109] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the copper strip overlapping parameter determination device, the copper strip overlapping parameter determination device is enabled to: determine the target copper strip overlapping width; use the target copper strip overlapping width and the preset copper strip overlapping parameter range as constraints, and use a genetic algorithm to solve the copper strip overlapping fitting model to obtain the target copper strip overlapping parameters; the copper strip overlapping fitting model is obtained by fitting multiple groups of copper strip overlapping parameters and the actual measured values ​​of the copper strip overlapping width corresponding to each group of copper strip overlapping parameters. The copper strip overlapping parameters used to obtain the copper strip overlapping fitting model include winding speed, traction speed, winding motor current, traction motor current, winding motor torque and traction motor torque.

[0110] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0111] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0112] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0113] The computer-readable storage medium provided herein stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned method for determining copper tape overlap parameters. This computer-readable storage medium addresses the technical issues of related art methods for determining copper tape overlap parameters, which struggle to achieve optimal copper tape overlap rates and easily impact cable production efficiency. Compared to related art methods, the computer-readable storage medium provided herein offers the same beneficial effects as the method for determining copper tape overlap parameters provided in the aforementioned embodiments, and will not be further elaborated upon here.

[0114] The present application also provides a computer program product, comprising a computer program, which implements the steps of the copper tape overlapping parameter determination method as described above when the computer program is executed by a processor.

[0115] The computer program product provided in this application can address the technical issues with the related art copper tape overlap parameter determination methods, which struggle to achieve optimal copper tape overlap rates and easily impact cable production efficiency. Compared to the related art, the computer program product provided in this application offers the same beneficial effects as the copper tape overlap parameter determination methods provided in the aforementioned embodiments, and will not be further elaborated upon here.

[0116] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for determining copper tape overlapping parameters, characterized in that: The method for determining the copper tape overlapping parameters comprises: Determine the target copper tape overlap width; The target copper strip overlap width and the preset copper strip overlap parameter range are used as constraints, and the copper strip overlap fitting model is solved using a genetic algorithm to obtain the target copper strip overlap parameters; the copper strip overlap fitting model is obtained by fitting multiple groups of copper strip overlap parameters and the actual measured values ​​of the copper strip overlap width corresponding to each group of copper strip overlap parameters, and the copper strip overlap parameters used to obtain the copper strip overlap fitting model include winding speed, traction speed, winding motor current, traction motor current, winding motor torque and traction motor torque.

2. The method for determining copper tape overlapping parameters according to claim 1, wherein: Before the step of using the target copper strip overlap width and the preset copper strip overlap parameter range as constraints and solving the copper strip overlap fitting model using a genetic algorithm to obtain the target copper strip overlap parameters, the method further includes: Acquire a sample data set; the sample data set includes multiple sets of copper tape overlapping parameters and measured values ​​of copper tape overlapping width corresponding to each set of copper tape overlapping parameters; A preset fitting model is trained based on the sample data set to obtain the copper strip overlapping fitting model; the preset fitting model includes a random forest model.

3. The method for determining copper tape overlapping parameters according to claim 2, wherein: After the step of training a preset fitting model based on the sample data set to obtain the copper strip overlapping fitting model, the method further includes: For each set of copper tape overlap parameters in the sample data set, the copper tape overlap parameters are input into the copper tape overlap fitting model to obtain a copper tape overlap width fitting value corresponding to the copper tape overlap parameters; A preset correction model is trained based on multiple sets of copper tape overlap parameters and corresponding residual values ​​to obtain a residual correction model; the residual value is the difference between the measured value of the copper tape overlap width and the fitted value of the copper tape overlap width, and the preset correction model is an XGBOOST model; The copper strip overlapping fitting model is updated based on the residual correction model to obtain an updated copper strip overlapping fitting model.

4. The method for determining copper tape overlapping parameters according to claim 2, wherein: The step of obtaining a sample data set includes: Acquire a historical production sample data set; the historical production sample data set includes multiple sets of historical production sample data on a shielding process production line, and the historical production sample data includes historical copper tape overlap parameters and corresponding historical copper tape overlap width measured values; Inputting the historical production sample data set into a generative adversarial network model for data simulation to obtain a simulated sample data set; the simulated sample data set includes multiple groups of simulated sample data, and the simulated sample data has consistent data features with the historical production sample data; The sample data set is acquired based on the historical production sample data set and the simulation sample data set.

5. The method for determining copper tape overlapping parameters according to claim 4, wherein: After the step of obtaining the historical production sample data set, the method further includes: Performing a preprocessing operation on the historical production sample data set to obtain a processed historical production sample data set; the preprocessing operation includes outlier processing, missing value filling and normalization processing; Based on the fluctuation state of the data in the processed historical production sample data set, identifying and eliminating the historical production sample data corresponding to the unstable stage of the shielding process production line to obtain a stable production sample data set; The step of inputting the historical production sample data set into the generative adversarial network model for data simulation to obtain the simulated sample data set includes: Inputting the stable production sample data set into a generative adversarial network model to perform data simulation to obtain the simulated sample data set; The step of obtaining the sample data set based on the historical production sample data set and the simulation sample data set includes: The sample data set is acquired based on the stable production sample data set and the simulation sample data set.

6. The method for determining copper tape overlapping parameters according to any one of claims 1 to 5, characterized in that: The step of using the target copper strip overlap width and the preset copper strip overlap parameter range as constraints and solving the copper strip overlap fitting model using a genetic algorithm to obtain the target copper strip overlap parameters includes: Generate a copper tape overlapping parameter cluster within the preset copper tape overlapping parameter range based on a genetic algorithm; the copper tape overlapping parameter cluster includes at least one group of candidate copper tape overlapping parameters; determining at least one set of target copper tape overlap parameters from the copper tape overlap parameter cluster based on a width difference between the copper tape overlap width fitting values ​​corresponding to each set of candidate copper tape overlap parameters and the target copper tape overlap width; the copper tape overlap width fitting values ​​are obtained by inputting the candidate copper tape overlap parameters into the copper tape overlap fitting model; Perform crossover and mutation operations on the target copper tape overlapping parameters to generate a new copper tape overlapping parameter cluster, and return to execute the step of determining at least one group of target copper tape overlapping parameters from the copper tape overlapping parameter cluster based on the width difference between the copper tape overlapping width fitting value corresponding to each group of the candidate copper tape overlapping parameters and the target copper tape overlapping width, until the width difference is less than a preset difference or the number of iterations reaches a preset number.

7. A device for determining copper tape overlapping parameters, characterized in that: The copper tape overlapping parameter determination device comprises: A determination module is used to determine a target copper tape overlap width; An acquisition module is used to use the target copper strip overlap width and the preset copper strip overlap parameter range as constraints, and use a genetic algorithm to solve the copper strip overlap fitting model to obtain the target copper strip overlap parameters; the copper strip overlap fitting model is obtained by fitting multiple groups of copper strip overlap parameters and the actual measured values ​​of the copper strip overlap width corresponding to each group of copper strip overlap parameters, and the copper strip overlap parameters used to obtain the copper strip overlap fitting model include winding speed, traction speed, winding motor current, traction motor current, winding motor torque and traction motor torque.

8. A copper tape covering parameter determination device, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for determining copper tape overlapping parameters according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for determining copper strip overlapping parameters according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method for determining copper strip overlap parameters according to any one of claims 1 to 6 are implemented.

Images