一种改进粒子群算法及其在PID参数整定中的应用  

A Modified PSO Algorithm and Its Application in Tuning of PID

作　　者：张洪涛[1] 胡红丽[2] 王斌[1] 

机构地区：[1]河北省电力研究院,河北石家庄050000 [2]北方设计研究院,河北石家庄050000

出　　处：《自动化技术与应用》2008年第12期14-16,共3页Techniques of Automation and Applications

摘　　要：针对基本粒子群算法易早熟、易陷入局部最优解及搜索精度不高的缺点,提出了一种新的学习因子取法,综合随机惯性权重和变异机制,得到一种改进的粒子群算法,通过复杂函数寻优验证了该方法的可行性及全局收敛方面的优越性;并将该算法应用于PID参数整定中,取得了良好的效果。Because of the problem that the particle swarm optimization is difficult to deal with premature and local minimum a novel PSO algorithm is presented in the paper. The modified PSO algorithm is based on the method of random learning-gene in combination with the random inertia weights and mutation The results of complex function testing and of the tunning of PID are also presented.

关 键 词：粒子群 PID 学习因子 

分 类 号：O232[理学—运筹学与控制论]