Optimization Simulation Method for Frame Stranding Process Parameters

Abstract

The present invention relates to the technical field of data processing. More specifically, the present invention relates to a method for optimizing and simulating the process parameters of frame stranding. The method includes: presetting the number of particles in the particle swarm, randomly generating the positions of the particles, and iteratively updating the positions of the particles according to the fitness values of each position; obtaining the route preference degree of the particles after the k-th iteration by the ratio of the maximum value of the position change of the particles after the k-th iteration to the cumulative sum of the displacements before and after all iterations of the particles after the k-th iteration; calculating the optimal solution tendency degree of the particles after the k-th iteration; determining the preference degree of the k-th iteration of the particles by the product of the route preference degree and the optimal solution tendency degree of the particles after the k-th iteration; after screening the particles in response to the comparison result between the preference degree of the k-th iteration of the particles and the preset threshold, continue to iteratively update to optimize the process parameters of frame stranding, effectively improving the optimization efficiency of the process parameters of frame stranding.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing. More specifically, the present invention relates to a method for optimizing and simulating the process parameters of a frame stranding process. Background Art

[0002] The frame stranding process can be applied to industries such as cables, communications, and automobiles. Through the stranding and compacting of fan-shaped conductors of copper and aluminum cable cores by a frame stranding machine, as well as the stranding and drawing and compacting of round conductors, a large number of wire rods can be wound in a short time, improving the flexibility and tensile strength of the wire rods. In order to ensure the stability and safety of electrical connections, it is necessary to continuously optimize the process parameters of the frame stranding process.

[0003] In order to improve the process technology, there is a lot of research content on the optimization of process parameters in the prior art. For example, the patent application document with the publication number CN111069328A discloses an optimization method for isothermal extrusion process parameters based on a particle swarm algorithm. This method uses a support vector machine to establish a prediction model for process parameters and the energy consumption of isothermal extrusion forming and the temperature of the profile outlet surface, constructs a multi-objective optimization model, and uses the particle swarm algorithm to solve the multi-objective optimization model, thereby optimizing the isothermal extrusion process parameters to achieve an optimization scheme with the best profile quality and the minimum forming energy consumption.

[0004] Although the above prior art can optimize the process parameters to reduce energy consumption to a certain extent, there are many types of process parameters involved in the production process, resulting in some particles not being able to reach the global optimal solution. Iterating such particles not only wastes the computational amount but also affects the acquisition of the global optimal solution, reducing the computational efficiency.

[0005] Based on this, how to improve the optimization efficiency of the frame stranding process parameters is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0006] To solve the above technical problem of how to improve the optimization efficiency of the frame stranding process parameters, the present invention proposes a method for optimizing and simulating the frame stranding process parameters, which includes the following steps:

[0007] Obtain the parameter values corresponding to each data point in the dataset of the frame stranding process parameters; preset the number of particles in the particle swarm, randomly generate the positions of the particles through the parameter value range in the dataset, determine the fitness values of each position, and iteratively update the positions of the particles according to the fitness values; according to the maximum value of the position change of the particle after the th iteration and the cumulative sum of all displacements before and after the th iteration of the particle, obtain the route preference degree of the particle after the th iteration; according to the distance between the particle after the th iteration and the global optimal solution in the historical iteration process, calculate the particle after the The degree of convergence of the optimal solution after the th iteration; By multiplying the route optimization degree after the th iteration of the particle by the degree of convergence of the optimal solution, the optimization degree of the th iteration of the particle is determined; After screening the particles in response to the comparison result between the optimization degree of the

[0008] th iteration of the particle and a preset threshold, continue the iterative update to achieve the optimization of the frame stranding process parameters.

[0009] According to the frame stranding process parameter optimization simulation method provided by the present invention, obtaining the parameter values corresponding to each data point in the dataset of the frame stranding process parameters includes: taking the parameter values corresponding to each batch of stranding as a data point, and preprocessing all batches of data points to form a dataset of the frame stranding process parameters.

[0010] The present invention takes into account that there may be noise interference and other situations in the originally collected data. Therefore, the overall quality of the process parameters is improved through preprocessing to prepare for the subsequent optimization of the process parameters.

[0011] According to the frame stranding process parameter optimization simulation method provided by the present invention, determining the fitness value of each position includes: determining a fitness function according to the process parameters of the frame stranding; substituting the process parameters in the particle position into the fitness function to obtain the fitness value of this position.

[0012] According to the frame stranding process parameter optimization simulation method provided by the present invention, iteratively updating the position of the particle according to the fitness value includes: if the fitness value of the position after the particle iteration is greater than the fitness value of the position before the iteration, then take the position after the iteration as the latest position of the particle, otherwise take the position before the iteration as the latest position of the particle.

[0013] By comparing the fitness values before and after particle iteration, the particles are continuously moved towards the position with a higher fitness value, so that the entire particle swarm gradually tends to the global optimal solution, and the parameter values corresponding to the global optimal solution can be accurately obtained.

[0014] According to the frame stranding process parameter optimization simulation method provided by the present invention, through the maximum value of the position change after the -th iteration of the particle and the ratio of the cumulative sum of all displacements before and after iteration after the -th iteration of the particle, the route preference degree after the -th iteration of the particle is obtained.

[0015] According to the frame stranding process parameter optimization simulation method provided by the present invention, the degree of approaching the optimal solution after the -th iteration of the particle satisfies the relational expression:

[0016] ;

[0017] In the formula, represents the degree of approaching the optimal solution after the -th iteration of the i-th particle, represents the number of iterations, , respectively represent the distances between the i-th particle after the -th iteration and the -th iteration and the global optimal solution, represents the exponential function with e as the base.

[0018] According to the frame stranding process parameter optimization simulation method provided by the present invention, the method for obtaining the maximum value of the position change after the -th iteration of the particle includes: obtaining the positions after all historical iterations after the -th iteration of the particle, determining the maximum displacement between all positions, and recording it as the maximum value of the position change after the -th iteration of the particle.

[0019] According to the frame stranding process parameter optimization simulation method provided by the present invention, screening particles in response to the comparison result between the preference degree of the -th iteration of the particle and a preset threshold includes: if the preference degree of the -th iteration of the particle is not greater than the preset threshold, then eliminating the particle; otherwise, retaining the particle.

[0020] By screening by obtaining the preference degree of the particle, the present invention can reduce the influence of particles with lower quality on the iterative convergence process and effectively improve the efficiency of particle iteration.

[0021] According to the frame stranding process parameter optimization simulation method provided by the present invention, the continuous iteration and update to achieve the optimization of the frame stranding process parameters include: in response to the particle iteration termination condition, outputting the maximum fitness value during all particle iteration processes as the target fitness; adjusting the frame stranding process parameters to the parameter values corresponding to the target fitness; wherein, the iteration termination condition includes a preset number of particle iterations and / or the fitness difference before and after particle iteration within a preset number of convergence times is less than a preset difference threshold.

[0022] According to the frame stranding process parameter optimization simulation method provided by the present invention, after achieving the optimization of the frame stranding process parameters, it further includes: performing abnormal monitoring on the process parameters during the frame stranding process.

[0023] The present invention takes into account that there may be potential safety hazards when the frame stranding process parameters are abnormal, so abnormal monitoring is used to remind the staff to handle it in a timely manner.

[0024] The present invention has the following beneficial effects:

[0025] Based on the above technical solution, when the present invention optimizes the frame stranding process parameters through the particle swarm algorithm, by obtaining the displacement change situation during each particle iteration to get the degree of route optimization preference, using the particles that do not reciprocate near the local optimal solution for iterative convergence, the optimization efficiency of the process parameters is improved; on this basis, the present invention also obtains the degree of tendency of the particle after iteration to the optimal solution, and corrects the degree of route optimization preference of the particle through the degree of tendency of the optimal solution, reducing the influence of the particles that reciprocate near the global optimal solution on particle screening, so that high-quality particles can be accurately screened for iterative convergence, effectively improving the optimization efficiency of the frame stranding process parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become easily understood. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0027] Figure 1 It is a schematic flowchart of a frame stranding process parameter optimization simulation method provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0029] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0030] It should be noted that the frame stranding process can be applied to industries such as cables, communications, and automobiles. Through the stranding and compacting of copper and aluminum cable core sector conductors and the stranding and drawing and compacting of round conductors by a frame stranding machine, a large number of wire rods can be wound in a short time, improving the flexibility and tensile strength of the wire rods. In order to ensure the stability and safety of electrical connections, it is necessary to continuously optimize the frame stranding process parameters.

[0031] The particle swarm algorithm is an optimization method based on swarm intelligence, which finds the optimal solution through the cooperation of individuals in the swarm. Each particle updates its position according to its own historical experience and the experience of other particles in the swarm, enabling the algorithm to quickly approach the global optimal solution with a relatively fast convergence speed. At the same time, through the velocity and position update mechanism of the particles, the algorithm has strong global search ability.

[0032] However, there are many types of process parameters involved in the frame stranding production process, resulting in some particles being unable to reach the global optimal solution. Iterating such particles not only wastes computational effort but also affects the acquisition of the global optimal solution, reducing the computational efficiency.

[0033] Based on this, the embodiments of the present invention disclose an optimization simulation method for frame stranding process parameters. By obtaining the preference degree of each particle during the iteration process and then screening, particles with lower quality are eliminated, and particles with better iteration effects are retained, effectively improving the efficiency of optimizing the frame stranding process parameters.

[0034] Specifically, please refer to Figure 1 as shown in Figure 1 which is a schematic flow chart of an optimization simulation method for frame stranding process parameters provided by the embodiments of the present invention. The method specifically includes the following steps.

[0035] S1: Obtain the parameter values corresponding to each data point in the dataset of frame stranding process parameters; preset the number of particles in the particle swarm, randomly generate the positions of the particles according to the parameter value range in the dataset, determine the fitness values of each position, and iteratively update the positions of the particles according to the fitness values.

[0036] Among them, the frame stranding process parameters may include the diameter of the wire, the tensile strength of the material, the yield strength of the material, the stranding angle, the stranding rate, the tension during the stranding process, the production environment temperature, humidity, production efficiency, and the insulation layer thickness, etc. Specifically, it can be set according to actual needs, and the embodiments of the present invention do not limit this too much here. The parameter values of the frame stranding process parameters jointly determine the stranding strength.

[0037] Exemplarily, the number of particles in the particle swarm can be preset to , where represents the particle coefficient, , represents the number of parameter values corresponding to each data point; the number of particles in the particle swarm can be specifically set according to actual needs, and the embodiments of the present invention do not impose excessive restrictions here.

[0038] Exemplarily, in the embodiments of the present invention, obtaining the parameter values corresponding to each data point in the dataset of the frame stranding process parameters includes: taking the parameter values corresponding to each batch of stranding as a data point, and after preprocessing all batches of data points, forming a dataset of the stranding process parameters.

[0039] Among them, the preprocessing can be data cleaning, data format conversion, dimension elimination, etc., which can be specifically set according to actual needs.

[0040] It can be understood that the parameter values corresponding to each data point are the values of each process parameter, and all the parameter values of each data point correspond to a stranding strength. The position of a particle is randomly composed of a set of parameter values, and each particle represents a possible solution. Therefore, the particle swarm is a set of solutions, and the maximum stranding strength corresponding to the particle parameter values obtained through iterative calculation is the global optimal solution of the particle swarm, that is, the maximum fitness value of the particle position.

[0041] Exemplarily, in the embodiments of the present invention, determining the fitness value of each position includes: determining a fitness function according to the process parameters of the frame stranding; substituting the process parameters in the particle position into the fitness function to obtain the fitness value of this position.

[0042] Exemplarily, when determining the fitness function according to the process parameters of the frame stranding, each process parameter is an evaluation index, and a set of evaluation indexes includes all process parameter categories; by setting corresponding weights for the normalized parameter values of each group of evaluation indexes, the corresponding stranding strength, that is, the fitness value, can be obtained; through each group of evaluation indexes and the corresponding fitness values, a fitness function for evaluating the stranding strength can be obtained.

[0043] Among them, the specific steps of obtaining the fitness function through each group of evaluation indexes and the corresponding fitness values can be set according to actual needs, and the embodiments of the present invention do not impose excessive restrictions here.

[0044] Exemplarily, in the embodiments of the present invention, iteratively updating the position of a particle according to the fitness value includes: if the fitness value of the position after particle iteration is greater than the fitness value of the position before iteration, then taking the position after iteration as the latest position of the particle, otherwise taking the position before iteration as the latest position of the particle.

[0045] In this way, in the embodiment of the present invention, by iteratively updating the positions of the particles, the updated particle positions gradually tend to the position of the global optimal solution, that is, the parameter value corresponding to the maximum value of the strand strength.

[0046] For the sake of easy understanding, in the embodiment of the present invention, the process of the i-th iteration of the particle is taken as an example for illustration, but it does not mean that the embodiment of the present invention is only limited to this.

[0047] S2: Obtain the route preference degree of the i-th iteration of the particle by the ratio of the maximum value of the position change after the i-th iteration of the particle to the cumulative sum of all displacements before and after iteration after the i-th iteration of the particle. after the i-th iteration of the particle and the cumulative sum of all displacements before and after iteration after the i-th iteration of the particle, to obtain the route preference degree of the i-th iteration of the particle.

[0048] It should be noted that for any particle, if it keeps moving repeatedly near a position during the iteration process, it means that the particle may fall into a local optimal solution. Such a particle with a local optimal solution will hinder the process of the particle swarm approaching the global optimal solution, thus affecting the optimization effect of the process parameters.

[0049] Based on this, in order to evaluate the performance of each particle during the iteration process, in the embodiment of the present invention, by obtaining the historical iteration data after each iteration of the particle, the route preference degree of the particle is obtained through the position change situation in the historical iteration data. If the particle keeps moving repeatedly near the same position, the route preference degree of the particle is relatively low.

[0050] Exemplarily, in the embodiment of the present invention, when determining the position change situation after the i-th iteration of the particle, it can be obtained by obtaining the maximum value of the position change after the i-th iteration of the particle and all displacements before and after iteration after the i-th iteration of the particle. after the i-th iteration of the particle, to obtain the position change situation of the particle. after the i-th iteration of the particle and all displacements before and after iteration after the i-th iteration of the particle.

[0051] Exemplarily, in the embodiment of the present invention, the method for obtaining the maximum value of the position change after the i-th iteration of the particle includes: obtaining all positions after all historical iterations after the i-th iteration of the particle, determining the maximum displacement between all positions, and recording it as the maximum value of the position change after the i-th iteration of the particle. after the i-th iteration of the particle, including: obtaining all positions after all historical iterations after the i-th iteration of the particle, determining the maximum displacement between all positions, and recording it as the maximum value of the position change after the i-th iteration of the particle. after the i-th iteration of the particle.

[0052] Exemplarily, to determine the route preference degree after the i-th iteration of the particle, the following relational expression can be specifically referred to:

[0053] ;

[0054] In the formula, represents the i-th particle at the​​ The route optimization degree after the i-th iteration denotes the maximum value of the position change of the i-th particle after the i-th iteration denotes the number of iterations denotes the displacement of the i-th particle before and after the i-th iteration

[0055] In the above formula denotes the cumulative sum of the displacements before and after all iterations of the i-th particle after the i-th iteration. The smaller the ratio of the maximum value of the position change of the particle after iteration to the displacements before and after all iterations, the smaller the degree of displacement change of the particle in the historical displacements, the greater the possibility that the particle makes reciprocating movements at the same position, and the smaller the corresponding route optimization degree

[0056] The following is an example to illustrate the parameters in the above formula: If then are 1, 2, and 3 respectively. The displacement before and after the first iteration is the displacement between the initial position and the position after the first iteration. The displacement before and after the second iteration is the displacement between the position after the first iteration and the position after the second iteration. The displacement before and after the third iteration is the displacement between the position after the second iteration and the position after the third iteration. The cumulative sum of the displacements in the three iterations is used as the cumulative sum of the displacements before and after all iterations of the particle after the third iteration. The maximum value among the displacements between the position after the first iteration and the position after the second iteration, the displacements between the position after the first iteration and the position after the third iteration, and the displacements between the position after the second iteration and the position after the third iteration is taken as the maximum value of the position change of the particle after the third iteration

[0057] After obtaining the route optimization degree of each particle after the i-th iteration based on the above steps, the following steps are continued

[0058] S3: Calculate the optimal solution tendency degree of the particle after the i-th iteration

[0059] It should be noted that the reciprocating movement of the particle at the same position may also be that the particle is already near the global optimal solution, and the reciprocating movement of the particle is around the global optimal solution. If the optimization degree of the particle after iteration directly obtained based on the above steps is used to determine the optimization degree of the particle, the particles near the global optimal solution may be misjudged as particles with low optimization degree

[0060] It can be understood that there will be an individual optimal solution of the particle and a global optimal solution among all particles after each iteration of each particle in the particle swarm

[0061] Based on this, in the embodiments of the present invention, by obtaining the position between the particle and the global optimal solution, it is further determined whether the reciprocating motion of the particle is near the global optimal solution. The closer the particle position is to the global optimal solution, the higher its preference level.

[0062] Specifically, according to the distance between the particle and the global optimal solution during the historical iteration after the -th iteration of the particle, the degree of tendency of the optimal solution of the particle after the -th iteration is calculated.

[0063] Exemplarily, in the embodiments of the present invention, to determine the degree of tendency of the optimal solution of the particle after the -th iteration, the following relational expression can be specifically referred to:

[0064] ;

[0065] In the formula, represents the degree of tendency of the optimal solution of the i-th particle after the -th iteration, represents the number of iterations, , respectively represent the distances between the i-th particle and the global optimal solution after the -th and -th iterations, represents the exponential function with base e;

[0066] In the above formula, represents the distance deviation between the i-th particle and the global optimal solution after the -th and -th iterations, that is, the distance deviation between the positions before and after the -th iteration and the global optimal solution. Since the overall direction of particle iteration is towards the global optimal solution, the larger this value is, the closer the particle is to the global optimal solution through iteration.

[0067] Based on the above steps to analyze the distance deviation between the particle before and after iteration and the global optimal solution, the degree of tendency of the particle towards the optimal solution can be accurately obtained, and the following steps can be continued.

[0068] S4: Determine the preference level of the i-th particle for the -th iteration by multiplying the route preference level of the particle after the -th iteration by the degree of tendency of the optimal solution; after screening the particles in response to the comparison result between the preference level of the i-th particle for the -th iteration and a preset threshold, continue the iterative update to optimize the process parameters of the frame stranding process.

[0069] It should be noted that based on the above steps, the route optimization degree of the particle and the optimal solution tendency degree of the particle can be obtained respectively. The route optimization degree of the particle is used to characterize the quality of the particle route, and the optimal solution tendency degree of the particle is used to characterize the tendency degree between the particle and the global optimal solution. By combining the two, the optimization degree of the particle can be accurately obtained, and thus the particles with low optimization degree can be accurately screened out based on this.

[0070] Exemplarily, in the embodiment of the present invention, in response to the comparison result between the optimization degree of the particle at the th iteration and a preset threshold, screening the particles includes: if the optimization degree of the particle at the th iteration is not greater than the preset threshold, then eliminating the particle; otherwise, retaining the particle.

[0071] Among them, the preset threshold can be set to 0.3; the preset threshold can be specifically set according to actual needs, and the embodiment of the present invention does not limit it too much here.

[0072] It can be understood that if the optimization degree of the particle at the th iteration is not greater than the preset threshold, it indicates that the quality performance of the particle after the th iteration is poor. After eliminating the particles with poor quality performance, the particle swarm iteration can converge better according to other particles with better quality performance.

[0073] Exemplarily, in the embodiment of the present invention, continue to iterate and update to optimize the process parameters of the frame stranding, including: in response to the particle iteration termination condition, outputting the maximum fitness value during the iteration process of all particles as the target fitness; adjusting the process parameters of the frame stranding to the parameter values corresponding to the target fitness.

[0074] Among them, the iteration termination condition includes a preset number of particle iterations and / or the fitness difference before and after particle iteration within a preset number of convergence times is less than a preset difference threshold.

[0075] Exemplarily, the number of particle iterations, the number of convergence times, and the preset difference threshold can be specifically set according to actual needs, and the embodiment of the present invention does not limit it too much here.

[0076] In the embodiment of the present invention, based on the above steps, screening the particles with better quality performance for iterative convergence can accurately obtain the parameter values corresponding to the maximum stranding strength. In this process, the embodiment of the present invention also considers that there may be potential safety hazards when the process parameters of the frame stranding are abnormal, so it is necessary to monitor its abnormality.

[0077] Exemplarily, in the embodiment of the present invention, after realizing the optimization of the process parameters of the frame stranding, it further includes: monitoring the abnormality of the process parameters during the frame stranding process.

[0078] Among them, the steps for abnormal monitoring of process parameters in the frame stranding process can be specifically set according to actual needs, and the embodiments of the present invention do not limit this too much here.

[0079] It can be seen that in the embodiments of the present invention, when optimizing the frame stranding process parameters, the parameter values corresponding to each data point in the dataset of the frame stranding process parameters can be obtained; the number of particles in the preset particle swarm is set, the positions of the particles are randomly generated through the parameter value range in the dataset, the fitness values of each position are determined, and the positions of the particles are iteratively updated according to the fitness values; according to the maximum value of the position change of the particle after the th iteration and the cumulative sum of all displacements before and after iteration of the particle after the th iteration, the route preference degree of the particle after the th iteration is obtained; according to the distance between the particle after the th iteration and the global optimal solution in the historical iteration process, the optimal solution tendency degree of the particle after the th iteration is calculated; through the product of the route preference degree and the optimal solution tendency degree of the particle after the th iteration, the preference degree of the particle after the th iteration is determined; in response to the comparison result between the preference degree of the particle after the th iteration and the preset threshold, the particles are screened and then continue to be iteratively updated to realize the optimization of the frame stranding process parameters.

[0080] In this way, the embodiments of the present invention can realize the optimization of the frame stranding process parameters through the particle swarm algorithm. In this process, the embodiments of the present invention consider that the particles may reciprocate near the local optimal solution, affecting the efficiency of the particle swarm to obtain the global optimal solution. Based on this, the embodiments of the present invention obtain the route preference degree of each particle by obtaining the displacement change situation during the iteration process, so as to obtain the particles that do not reciprocate near the local optimal solution for iterative convergence, improving the efficiency of process parameter optimization; on this basis, the embodiments of the present invention also consider that the particles may also reciprocate near the global optimal solution. Directly screening based on the route preference degree may classify such particles as particles with a low route preference degree. Based on this, the embodiments of the present invention obtain the tendency degree of the particle after iteration with respect to the optimal solution, and correct the route preference degree of the particle through the tendency degree of the optimal solution, accurately screening out high-quality particles that do not reciprocate near the local optimal solution for iterative convergence, effectively improving the efficiency of optimizing the frame stranding process parameters.

[0081] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. Optimization simulation method for frame stranding process parameters, characterized in that Including: Obtaining the parameter values corresponding to each data point in the dataset of the frame stranding process parameters; The number of particles in the preset particle swarm, randomly generating the positions of the particles according to the parameter value range in the dataset, determining the fitness values of each position, and iteratively updating the positions of the particles according to the fitness values; By the maximum value of the position change after the -th iteration of the particle and the ratio of the cumulative sum of displacements before and after all iterations after the -th iteration of the particle, the degree of route optimization after the -th iteration of the particle is obtained; According to the distance between the particle and the global optimal solution in the historical iteration process after the -th iteration, calculate the degree of tendency of the optimal solution after the -th iteration of the particle; the degree of tendency of the optimal solution after the -th iteration of the particle satisfies the relational expression: ； In the formula, represents the degree of the optimal solution tendency of the i-th particle after the -th iteration, represents the number of iterations, , respectively represent the distances between the i-th particle after the -th and the -th iterations and the global optimal solution, represents the exponential function with e as the base; By multiplying the route optimization degree after the -th iteration of the particle by the degree of approaching the optimal solution, determine the optimization degree of the -th iteration of the particle; after screening the particles in response to the comparison result between the optimization degree of the -th iteration of the particle and a preset threshold, continue iterative update to optimize the process parameters of the frame stranding; the screening of the particles in response to the comparison result between the optimization degree of the -th iteration of the particle and the preset threshold includes: if the optimization degree of the -th iteration of the particle is not greater than the preset threshold, then eliminate the particle; Otherwise, keep the particle.

2. The optimized simulation method for the frame stranding process parameters according to claim 1, wherein The obtaining the parameter values corresponding to each data point in the dataset of the frame stranding process parameters includes: Taking the parameter values corresponding to each batch of stranding as a data point, and preprocessing all batches of data points to form a dataset of the stranding process parameters.

3. The method for optimizing and simulating the process parameters of the frame stranding according to claim 1, characterized in that The determining the fitness values of each position includes: Determining a fitness function according to the process parameters of the frame stranding; substituting the process parameters in the particle position into the fitness function to obtain the fitness value of this position.

4. The optimized simulation method for the frame stranding process parameters according to claim 1, wherein The iteratively updating the positions of the particles according to the fitness values includes: If the fitness value of the position after particle iteration is greater than the fitness value of the position before iteration, then taking the position after iteration as the latest position of the particle, otherwise taking the position before iteration as the latest position of the particle.

5. The optimized simulation method for the frame stranding process parameters according to claim 1, characterized in that The method for obtaining the maximum value of the position change of the particle after the th iteration includes: Obtain the positions of all historical iterations after the -th iteration of the particle, and determine the maximum displacement between all positions, denoted as the maximum value of the position change after the -th iteration of the particle.

6. The optimized simulation method for frame stranding process parameters according to claim 1, characterized in that The continuing to iteratively update to optimize the frame stranding process parameters includes: In response to the particle iteration termination condition, outputting the maximum fitness value during the iteration of all particles as the target fitness; adjusting the frame stranding process parameters to the parameter values corresponding to the target fitness; wherein, the iteration termination condition includes that the fitness difference before and after particle iteration within the preset number of particle iterations and / or the preset number of convergence times is less than the preset difference threshold.

7. The optimized simulation method for the frame stranding process parameters according to claim 1, characterized in that After the optimizing of the frame stranding process parameters, it further includes: Performing anomaly monitoring on the process parameters during the frame stranding process.

Images