混沌—微粒群算法及其在机械优化设计中的应用

Chaos-Particle Swarm Optimization Algorithm and Its Application to Mechanical Optimal Design

针对机械优化设计中变量多、目标函数和约束条件复杂而难以求解的问题,建立了基于微粒群算法的机械优化设计的数学模型;并针对传统罚函数法处理约束条件而引起的病态问题,提出一种利用混沌变量来更新产生违约解个体的方式来改进微粒群算法,增加了个体的多样性、避免微粒群算法出现早熟,从而加快算法的收敛速度。实例计算表明该算法能较好地解决机械优化设计问题。

Aimed at the problems of multivariable and complicated target function and constraint conditions in mechanical optimal design, the mathematical model combing mechanical optimal design with Particle Swarm Optimization （PSO） is constructed, Due to the morbidity problem of traditional penalty function dealing with the constraint conditions in mechanical optimal design, the method using Chaos variable to update the individual particle producing infeasible solution is proposed for improv-ing PSO, The improved Chaos-PSO algonthm can increase individual diversity, avoid prematurity of PSO and speed up the step of convergence, The practical example shows that the result of mechanical optimal design based on Chaos-PSO is remarkable.