改进差分进化PID参数优化及在凝絮中的应用  

Parameter optimization of PID controller based on modified differential evolution and its application in dosing coagulation process

作　　者：唐德翠[1,2] 朱学峰[1] 

机构地区：[1]华南理工大学自动化学院,广州510641 [2]广东技术师范学院自动化学院,广州510635

出　　处：《计算机工程与应用》2009年第24期204-206,共3页Computer Engineering and Applications

基　　金：佛山禅城区产学研项目(No2008B1034)

摘　　要：针对标准差分进化(DE)收敛速度慢和操作过程中参数为常数从而导致算法鲁棒性相对较差的缺点,采用以个体适应度值最优的个体为基矢量,沿次优个体方向搜索的变异策略来提高算法的搜索速度;提出根据差分矢量大小和个体收敛情况自适应调整变异参数F和交叉概率CR的自适应参数调整策略来确保搜索初期种群的多样性和后期算法的局部搜索能力。并将基于该改进差分进化算法(MDE)优化后的PID控制器用于水厂加药凝絮过程的控制,仿真结果表明该算法收敛速度快,基于该算法的MDE-PID控制器性能好,是PID控制器参数整定的有效搜索方法,也是实现水厂加药凝絮过程良好控制的有效途径。To improve the slow convergence speed and bad robustness due to fixed control parameters of basic Differential Evolution（DE）,a modified mutation operation according to fitness value has been proposed.At the same time,according to relative position of the two different individual vectors selected to generate a difference vector,a self-adapting strategy for the amplification factor F of the difference vector is proposed and a self-adapting crossover probability constant CR strategy is proposed in term of the convergence status of target vector.This method has been used to optimize PID＇s parameters which is applied to dos ing coagulation process in water plant,the simulation result proves this method has a rapid convergence speed and the PID controller based on MDE has good performance.This method is the valid searching method for PID parameter tuning and dosing coagulation control in water plant.

关 键 词：改进的差分进化 PID控制器 参数优化 加药凝絮 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]