Font Size: a A A

Multi-Objective Gradient-Enhanced Particle Swarm Optimization Algorithm And Application In Sheet Metal Forming

Posted on:2022-01-02Degree:MasterType:Thesis
Country:ChinaCandidate:Y XiaoFull Text:PDF
GTID:2481306734998649Subject:Mechanical engineering
Abstract/Summary:PDF Full Text Request
Sheet metal forming is a complex and highly nonlinear process,with many parameters that affect its forming quality,and the optimization process is complicated and timeconsuming to solve.In dealing with such complex engineering optimization problems,the Multi-objective Particle Swarm optimization algorithm is widely used because of its simple concept,easy implementation,and few parameters involved.Because of its weak local search ability,it is easy to cause the algorithm to fall into the local optimal solution,and the later convergence is relatively slow,which has certain limitations in the optimization of sheet metal forming.Aiming at this problem,this paper improves the multi-objective particle swarm algorithm based on the multi-object gradient synchronous descent method to improve the local search ability and convergence efficiency of the algorithm.And the enhanced multiobjective particle swarm algorithm is applied in the optimization design of sheet metal forming.The main research contents include:A multi-object gradient-enhanced particle swarm algorithm is proposed based on the Multiple-Gradient Descent Algorithm.Combining the search strategy of the MultipleGradient Descent Algorithm with the speed update formula of the Multi-objective Particle Swarm optimization algorithm,strengthens the local search capability of the Multi-objective Particle Swarm optimization algorithm and improves its convergence efficiency.In order to prevent the algorithm from falling into the local optimal solution prematurely,a repulsive mechanism is proposed to prompt the particles in the crowded area to quickly jump out of the local optimal solution to ensure diversity.The test verifies the effectiveness of the MultiObjective Gradient-enhanced Particle Swarm Optimization Algorithm.Based on the Multi-Objective Gradient-enhanced Particle Swarm Optimization Algorithm,the forming process parameters of the inner panel of the automobile hood are optimized.Aiming at the defects of cracks and wrinkles that are likely to occur during the forming process of the inner panel of the automobile hood,decreasing the maximum thinning rate and maximum thickening rate of the formed parts as the objective function,and the drawbead resistance coefficient,blank holder force and friction coefficient are used as design variables.The second-order response surface model is used to construct the mapping relationship between the design parameters and the objective function,and the response surface optimization model is optimized based on the Multi-Objective Gradient-enhanced Particle Swarm Optimization Algorithm to obtain the optimization parameter combination.The reliability of the optimization results is verified by forming numerical simulation software,and the Multi-Objective Gradient-enhanced Particle Swarm Optimization Algorithm effectively improves the optimization efficiency of the inner panel of the automobile hood.
Keywords/Search Tags:Multi-objective optimization, Multiple-Gradient Descent Algorithm, Multi-objective Particle Swarm optimization algorithm, Response Surface Surrogate model, sheet metal forming
PDF Full Text Request
Related items