Optimization Method for Springback Amount in Roll Bending Forming of Aluminum Material

Abstract

Provided is an optimization method for the springback amount of roll bending forming of aluminum materials, which improves the accuracy of roll bending technology, improves production efficiency, and enhances the flexibility of production. 【Solution means】The method includes analyzing the process of roll bending forming of aluminum materials, determining the decision variables of the springback amount and thickness reduction amount of aluminum materials, constructing an optimization model for the springback of roll bending forming of aluminum materials based on a multi-objective optimization algorithm, clarifying the constraint conditions in the process of roll bending forming of aluminum materials, submitting a corresponding algorithm based on the characteristics of the model, optimizing the springback amount and thickness reduction amount of aluminum materials, updating each decision variable that affects the springback amount and thickness reduction amount of aluminum materials, judging the iteration stop condition, and outputting means for improving the springback amount of roll-bent aluminum materials.

Description

Technical Field

[0001] The present invention relates to the field of roll bending forming springback technology for aluminum materials, and particularly to a method for optimizing the springback amount of roll bending forming of aluminum materials.

Background Art

[0002] In the manufacturing industry of high-speed railway equipment, the requirements for the structural strength, dimensional accuracy, and product quality of the front part of the train are becoming increasingly strict. Due to the characteristics of aluminum materials such as light weight, high strength, and corrosion resistance, they are widely used in large structural members such as the front vehicles of trains. However, due to the complexity of the side member interface of the front vehicle of the train, the magnitude of its bending elastic modulus, length, and curvature change characteristics, the conventional bending equipment and processes cannot meet the demand for high-quality forming manufacturing when dealing with such complex cross-sections and difficult-to-deform aluminum materials. Therefore, how to improve the processing and forming accuracy of aluminum materials is particularly important at this time.

[0003] In the forming process of large structural members such as the front vehicle of the train, when the roll bending machine bends the aluminum material, a large springback amount is generated, which affects various aspects such as the processing shape and processing accuracy. To reduce the springback amount, it is necessary to change the thickness of the material. It is important to ensure not only that the aluminum material can reach the expected bending shape during the bending process but also that a sufficient thickness can be maintained, that is, how to perform high-precision control on the process parameters during processing.

[0004] The multi-objective optimization algorithm is a swarm intelligence algorithm that solves the optimization problem of multiple conflicting or interrelated objective functions. Such problems require considering multiple optimization objectives simultaneously, and there may be mutual constraint relationships between these objectives, making it difficult to achieve the optimization of a single objective simultaneously. The goal is to find a set of solutions that can satisfy each objective well in a balanced manner, rather than a single optimal solution. The multi-objective optimization algorithm has higher flexibility and adaptability. In practical applications, the multi-objective optimization algorithm has already been widely applied in various fields. For example, in engineering design, logistics planning, etc., it can find the optimal balance point between multiple objectives and achieve the maximization of overall benefits.

Summary of the Invention

[0005] The object of the present invention is to provide an optimization method for the springback amount of roll bending forming of aluminum materials, to solve the problem that the springback amount in roll bending technology is relatively large, to improve the accuracy of roll bending technology, to improve production efficiency and to enhance the flexibility of production.

[0006] To achieve the above object, the present invention provides an optimization method for the springback amount of roll bending forming of aluminum materials, including the following steps. S1, analyze the process of roll bending forming of aluminum materials, and determine the decision variables of the springback amount and thickness reduction amount of aluminum materials. S2, construct an optimization model for roll bending springback of aluminum materials based on the multi-objective optimization algorithm, and clarify the constraint conditions in the process of roll bending forming of aluminum materials. S3, propose a corresponding algorithm based on the characteristics of the model in S2, and optimize the springback amount and thickness reduction amount of aluminum materials. S4, update each decision variable that affects the springback amount and thickness reduction amount of aluminum materials. S5, judge the iteration stop condition, and output the means to improve the springback amount of roll bending aluminum materials.

[0007] Preferably, in step S1, digitalization is performed on the roll bending springback amount problem in the roll bending forming process of the aluminum material, and the current problem is expressed using a gene sequence, that is, the encoding process. When encoding the process, it is divided into four parts: the friction coefficient, the die gap, the angle between the roll wheels, and the speed difference between the upper and lower rolls.

Number

[0008] Preferably, the specific steps of step S2 are as follows. S201, construct an optimization model for the springback amount of the roll bending forming of the aluminum material based on the multi-objective optimization algorithm, and use the springback amount and the reduction amount of the thickness during the roll bending forming of the aluminum material as two objective functions. S202, construct the constraint conditions in the optimization model for the springback amount of the roll bending forming of the aluminum material based on the multi-objective optimization algorithm, and include the following constraint conditions during the roll bending forming of the aluminum material.

Number

[0009] Preferably, the specific steps of step S3 are as follows. S301, initialize the population, initialize the rebound amount and thickness reduction amount in the aluminum material forming process, the population size, selection probability, mutation probability of the multi-objective optimization model, and set the maximum number of iterations. S302, establish the fitness function, specifically describe the formula F as follows. F = min(f 1 , f 2 )(7) Here, f 1 represents the rebound amount during the roll bending forming of the aluminum material. f 2 represents the thickness reduction amount during the roll bending forming of the aluminum material.

[0010] Preferably, the specific steps of step S4 are as follows. S401, perform encoding and decoding. S402, perform the crossover operation of the chromosome sequence. S403, perform the mutation operation of the chromosome. S404, perform the environmental selection mechanism.

[0011] Preferably, the specific steps of step S401 are as follows. S4011 involves adopting the real - number encoding method. Four real numbers are randomly generated within each chromosome in the population. These four real numbers respectively represent the values of four decision variables: the friction coefficient u between the aluminum material and the contact surface of the upper roll of the roll - bending machine, the gap size G between the aluminum material and the roll during the roll - bending process, the angle size ω between the upper roll and the lower roll, and the speed difference Δv between the upper roll and the lower roll. These real numbers directly correspond to the parameter values in the target space. S4012 means that when generating the four real numbers, it is necessary to ensure that the values randomly generated in the chromosome satisfy the constraint conditions of step S202. Combining the four real numbers (μ, G, ω, Δv) constitutes the real - number encoding of one individual. S4013 indicates that if there are n individuals in the population, n chromosomes in the combination of (μ, G, ω, Δv) are generated. S4014 means that after the encoding is completed, since each value randomly generated in the chromosome at that time directly corresponds to the parameter value in the space, the decoding is also completed.

[0012] Preferably, the specific steps of step S402 are as follows. S4021 involves randomly selecting two intersection points C 1 , C 2 in the code sequences of two parent individuals and establishing a new archive set S. S4022 means that after the intersection points are determined, some genes between the intersection points of the two parent individuals p 1 , p 2 are exchanged to generate new offspring individuals. S4023 means evaluating the newly generated offspring individuals according to the target value. S4024 means that in the iterative process, if the newly generated offspring individual is superior to an individual in the archive set S, the new offspring individual is added to the archive set S, and the inferior individual is removed from the archive set S.

[0013] Preferably, the chromosome sequence mutation method in step S403 adopts a population evolution method, and its specific steps are as follows. S4031. After each chromosome crosses, recalculate the two target values f 1 , f 2 of the population individuals, and calculate the magnitude of the index value I in each individual. The calculation formula is as follows.

Number

[0014] Preferably, in step S404, the environmental selection is divided into individual convergence selection and diversity selection, and its specific steps are as follows. S4041. Generate a set of uniformly distributed reference vectors using the NBI method in the target space. The NBI method requires the number M of known optimization targets and the number p of divisions for each target. The division step size is 1 / p, and the formula for the number H of generated reference vectors is as follows.

Number

Number

[0015] Preferably, step S5 specifically is: Set the maximum number of iterations. When the individuals in the population reach the maximum number of iterations after multiple evolutionary iterations, obtain an executable solution that satisfies the constraint conditions. Then, use the multi-attribute decision-making TOPSIS method to select the optimal solution among a set of solutions, calculate the distance between each individual in the set of solutions and the most excellent point, and the distance between each individual and the most inferior point, and rank all the obtained distances. Consider the solution that is closest to the most excellent point and farthest from the most inferior point as the optimal solution.

[0016] Therefore, the present invention adopts the method for optimizing the springback amount of roll bending of the aluminum material, and has the following beneficial effects. 1) Improve the accuracy of the roll bending process. The multi-objective optimization algorithm processes two conflicting optimization objectives, namely the springback amount and the thickness reduction amount, searches for the optimal balance point between the objectives, optimizes these two important indicators at the same time, ensures that the aluminum material can reach the expected bending shape during the bending process and can maintain sufficient thickness, and thus meets the requirements for product accuracy in actual production. 2) Improve production efficiency. The multi-objective optimization algorithm can find the optimal process combination according to the specific process parameters of the roll bending machine and the characteristics of the aluminum material, accurately control the operating parameters of the roll bending machine, and enable the aluminum material to quickly and accurately reach the planned shape during the bending process. 3) Enhance production flexibility. Customized optimization can be performed for aluminum materials of different types, specifications, and materials. This means that the roll bending machine can adapt to more types of production tasks, improving the flexibility and diversity of the production line. Enterprises can quickly adjust the process parameters of the roll bending machine according to requirements to meet the production needs of different products.

[0017] In summary, in the present invention, the multi-objective optimization algorithm is used to optimize the springback amount and thickness reduction amount of the roll bending machine, improving the bending process accuracy, enhancing production efficiency, and increasing production flexibility. It can avoid the problem of production accuracy reduction caused by human errors, reduce the time spent in the process of manually adjusting process parameters, and improve the processing accuracy and processing efficiency. Hereinafter, the technical solution of the present invention will be further described in detail with reference to the accompanying drawings and embodiments.

Brief Description of the Drawings

[0018]

Figure 1

Figure 2

Modes for Carrying Out the Invention

[0019] Hereinafter, the technical solution of the present invention will be further described with reference to the accompanying drawings and embodiments. Unless otherwise defined, technical or scientific terms used in the present invention shall have the ordinary meanings as understood by those of ordinary skill in the field to which the present invention pertains.

[0020] Example 1 As shown in Figure 1, the present invention provides a method for optimizing the springback amount in roll bending forming of aluminum materials, including the following steps.

[0021] S1, which is to analyze the process of roll bending forming of aluminum materials and determine the decision variables of the springback amount and thickness reduction amount of the aluminum materials. Digitalization is performed on the springback amount problem in the roll bending forming process of aluminum materials, and the current problem is expressed using gene sequences, that is, the encoding process. When encoding the process, it is divided into four parts: the friction coefficient, the die gap, the angle between the roll wheels, and the speed difference between the upper and lower rolls.

Number

[0022] S2, which is to construct an optimization model for springback in roll bending forming of aluminum materials based on a multi-objective optimization algorithm and clarify the constraints in the roll bending forming process of aluminum materials. The flowchart of the multi-objective optimization algorithm is shown in Figure 2, and the specific steps are as follows. S201, which is to construct an optimization model for the springback amount in roll bending forming of aluminum materials based on a multi-objective optimization algorithm, and use the springback amount and the thickness reduction amount during roll bending forming of aluminum materials as two objective functions. S202 involves constructing the constraint conditions in the optimization model of the springback amount in the roll bending forming of aluminum materials based on the multi-objective optimization algorithm, and includes the following constraint conditions during the roll bending forming of aluminum materials.

Number

[0023] S3 involves constructing an algorithm framework aiming to reduce the springback amount and thickness reduction amount of the aluminum material during the processing, and performing optimization on the model in S2. The specific steps are as follows. S301 involves initializing the population, initializing the springback amount and thickness reduction amount of the aluminum material during the aluminum material forming process, the population size, selection probability, and mutation probability of the multi-objective optimization model, and setting the maximum number of iterations. S302 involves establishing a fitness function, and specifically describing the formula F as follows. F = min(f, f 2 )(7) Here, f 1 represents the springback amount during roll bending of the aluminum material. f 2 represents the thickness reduction amount during roll bending of the aluminum material. f 1 , f 2 are all functions of the friction coefficient u of the contact surface between the aluminum material and the upper roll of the roll bending machine, the size G of the gap between the aluminum material and the roll during the roll bending process, the size ω of the angle between the upper roll and the lower roll, and the speed difference Δv between the upper roll and the lower roll.

[0024] In S4, updates are made for each decision variable that affects the springback amount and thickness reduction amount of the aluminum material. The specific steps are as follows. In S401, encoding and decoding are performed. The specific steps are as follows. In S4011, the binary code is likely to lose accuracy when encoding two decision variables. To improve the accuracy of chromosome description, the code adopts the real - number coding method. Four real numbers are randomly generated for each chromosome in the population. These four real numbers respectively represent the friction coefficient μ of the contact surface between the aluminum material and the upper roll in the roll bending machine, the size G of the gap between the aluminum material and the roll during the roll bending process, the size ω of the angle between the upper roll and the lower roll, and the speed difference Δv between the upper roll and the lower roll. These real numbers directly correspond to the parameter values in the target space. In S4012, to generate the four real numbers, it is necessary to ensure that the randomly generated values in the chromosome satisfy the constraint conditions of step S202. The four real numbers (μ, G, ω, Δv) are combined to form the real - number code of one individual. In S4013, when there are n individuals in the population, n chromosomes of the combination (μ, G, ω, Δv) are generated. In S4014, after the coding is completed, since each value randomly generated in the chromosome at that time already directly corresponds to the parameter value in the space, the decoding is already completed. S402 is a chromosome sequence crossover operation. In the chromosome sequence crossover, a two-point crossover policy that introduces an external archive set is adopted. That is, two positions on one chromosome are randomly selected for crossover, and in the crossover process, the external archive is introduced to save excellent individuals or gene segments. The specific steps are as follows. S4021 means randomly selecting two crossover points c 1 、c 2 in the code sequences of two parent individuals. The positions of these two crossover points are random, and a new archive set S is created. S4022 means that after determining the crossover points, the partial genes between the crossover points of two parent individuals p1 and p2 are exchanged to generate new child individuals. S4023 means evaluating the newly generated child individuals by the target value, and the smaller the target value, the better. S4024 means that in the process of iteration, if the newly generated child individual is superior to the individuals in the external archive set, the inferior individuals are removed from the archive set, and the new child individual is added to the archive set S. S403 is a chromosome mutation operation. The chromosome sequence mutation method adopts a population evolution method, and its specific steps are as follows. S4031 means that after each chromosome is crossed, the two target values f 1 、f 2 of the population individuals are recalculated, and the magnitude of the index value I is calculated for each individual. The calculation formula is as follows.

Equation

Number

Number

Number

Number

[0025] S5, which determines the iteration stop condition and outputs a solution means to improve the springback amount of the roll-bent aluminum material, specifically as follows. Set the maximum number of iterations. When the individuals in the population reach the maximum number of iterations after multiple evolution iterations, obtain an executable solution that satisfies the constraint conditions. Then, use the multi-attribute decision-making TOPSIS method to select the optimal solution among a set of solutions, calculate the distance between each individual in the set of solutions and the most excellent point, and the distance between each individual and the most inferior point, and perform an ordering for all the obtained distances. Consider the solution that is closest to the most excellent point and farthest from the most inferior point as the optimal solution. Specifically, it includes the following steps: S501, which normalizes the attribute values according to Equation (13), then calculates the weighted sum of attributes for each solution according to Equation (14), and sets the weight values of each attribute to be the same.

Number

Number

Equation

[0026] Therefore, the present invention adopts the optimization method for the springback amount of roll bending forming of the aluminum material, analyzes the roll bending forming process of the aluminum material, combines with a multi-objective optimization algorithm, obtains decision variables with a relatively small springback amount and a relatively small thickness reduction amount, that is, appropriate contact surface friction parameters and gap parameters between the aluminum material and the upper roll of the roll bending machine, and realizes the parameter setting of high-precision roll bending technology.

[0027] Each chromosome in the algorithm corresponds to a decision variable array that affects the springback amount and the thickness reduction amount. Encoding and decoding are performed on the decision variable array, and operations such as crossover, mutation, and selection are executed among the arrays to continuously evolve and iterate the chromosomes. Moreover, multi-attribute decision-making is used to make a decision on a relatively good solution set, and the optimal technical setting parameters with the minimum springback amount and the minimum thickness reduction amount are obtained. It solves the problem of a relatively large springback amount in roll bending technology, has the advantages of improving the accuracy of roll bending technology, improving production efficiency, and enhancing production flexibility.

[0028] Finally, the following should be noted. The above embodiments are only for explaining the technical solutions of the present invention and do not limit it. Although the present invention has been described in detail with reference to relatively good embodiments, those skilled in the art should understand the following. That is, still, modifications or equivalent substitutions can be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot also cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for optimizing a bending rebound amount of an aluminum material during roll bending, comprising the steps of: S1: Analyzing the process of roll bending of the aluminum material, and determining the determining variables of the rebound amount and the thickness reduction amount of the aluminum material; S2. Construct an aluminum material roll bending rebound optimization model based on a multi-objective optimization algorithm, and clarify the constraints in the aluminum material roll bending process. The specific steps are as follows: S201, constructing an optimization model of the bending rebound amount of the roll bending of the aluminum material based on a multi-objective optimization algorithm, the rebound amount and the thickness reduction amount during the roll bending of the aluminum material are two objective functions; S202, constructing constraint conditions in a rebound amount optimization model of roll bending of an aluminum material based on a multi-objective optimization algorithm, the following constraint conditions are included during roll bending of the aluminum material: [0010] Equation (1) is the constraint on the friction coefficient of the contact surface between the aluminum material and the upper roll of the roll bending machine, where μ ｍｉｎ is the minimum allowable friction coefficient during bending, and μ ｍａｘ is the maximum allowable friction coefficient during bending, and equation (2) is the constraint on the gap between the aluminum material and the roll wheel during the roll bending process, G ｍｉｎ is the minimum allowable gap during bending, and G ｍａｘ is the maximum allowable gap during bending, and in equation (3), ω ｍaｘ represents the maximum angle between the upper and lower rolls, and ω ｍｉｎ represents the minimum angle between the upper roll and the lower roll, Δv in formula (4) represents the constraint on the speed difference between the upper roll and the lower roll, formula (5) is the constraint on the thickness reduction amount required by the aluminum material when processing a certain part, and T ｍａｘ is the maximum thickness reduction required, S3: provide a corresponding algorithm according to the characteristics of the model in S2 to optimize the aluminum material rebound amount and thickness reduction amount, the specific steps are as follows: S301: Initialize a species group; initialize the aluminum material rebound amount and thickness reduction amount during the aluminum material forming process; initialize the species group population, selection probability, and mutation probability of a multi-objective optimization model; and set the maximum iteration number; S302: Establish a fitness function, specifically, the formula F is written as follows: F=min(f,f ２ )(7) Here, f １ represents the rebound amount during roll bending of aluminum material, and f ２ indicates the amount of thickness reduction during roll bending of aluminum material, S4, updating each decision variable affecting the rebound amount and the thickness reduction amount of the aluminum material, the specific steps are as follows: S401, performing encoding and decoding; S402 is a chromosome sequence crossover operation, the specific steps of which are as follows: S4021, randomly selecting two crossover points c in the code strings of the two parent individuals １ , c ２ and create a new archive set S, S4022, after determining the crossing point, exchange partial genes between the crossing points of the two parent individuals p1 and p2 to generate a new child individual; S4023, evaluating the newly generated child individual according to the target value; S4024: in the process of iteration, if the newly generated child individual is superior to an individual in the archive set S, add the new child individual to the archive set S and remove the inferior individual from the archive set S; S403 is a chromosome mutation operation, in which the chromosome sequence mutation method adopts a species group evolution method, and its specific steps are as follows: S4031: After each chromosome crossover, two target values ​​f １ , f ２ Recalculate the magnitude of the index value I for each individual, and the calculation formula is as follows: [0025] S4032: Ranking the index values ​​I of 2N individuals in the species group, and the individual with the smallest index value I is ranked as the first species group P １ Then, the individuals with the highest index value I are placed in the second species group P ２ Put it in S4033, the second species group P ２ Mutate all individuals of , and the mutation method is differential mutation. S404 is an environmental selection mechanism, in which the environmental selection is divided into convergent selection and divergent selection of individuals, and its specific steps are as follows: S4041. Generate a set of uniformly distributed reference vectors in the target space using the NBI method, and the formula for the number H of generated reference vectors is as follows: [0030] Here, C represents the combination in the sequence combination, M represents the number of optimization targets, p represents the number of divisions per target, and 1 / p represents the division step size; In S4042, the parent individuals and the child individuals are integrated. In this case, the number of species groups is set to 2N. The target values ​​of all the individuals are calculated. The target values ​​of the individuals are normalized as follows: [0045] S4043, ordering the individuals in the regions in a non-dominant manner, and dividing all the individuals in the species group into different frontiers or strata according to two target normalization values; S4044, taking the first K frontier surfaces in each region, and making the number of individuals of the species group n greater than N; S4045, in order to reduce the number of individuals of the species group to N, cluster all currently held individuals using a hierarchical clustering method and remove a individuals from each class so that the number of individuals of the species group at this time is exactly N; S5. A method for optimizing the bending rebound amount of roll-bending of aluminum material, comprising: determining a condition for stopping the repetition; and outputting a plan for improving the bending rebound amount of the roll-bent aluminum material.

2. The method for optimizing the bending rebound amount during roll bending of aluminum material according to claim 1, characterized in that in step S1, the problem of the rebound amount during roll bending of the aluminum material is digitized, and the current problem is expressed by using gene sequence, that is, the coding process, and the coding process is divided into four parts, namely, friction coefficient, die gap, angle between roll wheels, and speed difference between upper and lower rolls. [0050] Here, μ represents the friction coefficient of the contact surface between the aluminum material and the upper roll of the roll bending machine, G represents the size of the gap between the aluminum material and the roll during the roll bending process, ω represents the angle between the upper roll and the lower roll, Δv represents the speed difference between the upper roll and the lower roll, n represents the number of individuals in the species group, and k = {1, 2, 3, ..., n}.

3. S5, A maximum number of iterations is set, and when the individuals in the species group reach the maximum number of iterations after multiple evolution iterations, a feasible solution that satisfies the constraints is obtained; The method for optimizing the bending rebound amount during roll bending of aluminum material as described in claim 1, characterized in that an optimal solution is then selected from the set of solutions using a multi-attribute decision TOPSIS method, the distance between each individual in the set of solutions and the best point, and the distance between each individual and the worst point are calculated, and the solution closest to the best point and farthest from the worst point is regarded as the optimal solution.

Images