基于改进粒子群算法的PID控制器参数自整定

摘要

针对标准粒子群算法寻优精度不高、易出现早熟收敛等缺陷,提出一种自适应混沌移民变异粒子群算法IPSO.该算法通过引入基因距离来反映粒子间合作与竞争的隐性知识,使粒子种群的多样性得到量化,采取自适应混沌移民变异策略对陷入聚集区域的粒子进行处理,使之获得继续搜索的能力,从而防止算法过早陷入局部最优.仿真结果表明,IPSO算法在PID控制器参数寻优问题上具有遗传算法和标准粒子群算法无法比拟的优势.%Aiming at the problems of low optimization accuracy and premature convergence for standard particle swarm optimization , this paper presented an adaptive chaos immigration and mutation particle swarm optimization (IPSO). By analyzing the gene distance, the implif.it knowledge of cooperation and competition between the particles were reflected and particle population diversity was quantified. By taking adaptive chaotic immigration and mutation strategy, it processed the particles which were caught in gathering areas, and the particles obtained the ability to continue search, therefore preventing the algorithm into a local optimum too early . Simulation results show that the IPSO has a better performance than both the conventional particle swarm optimization and genetic algorithm in the PID controller parameters optimization problem.