用免疫量子粒子群算法优化控制决策表  

Using Quantum-behaved Particle Swarm Optimization-immune Algorithm to Optimize Fuzzy Control Table

作　　者：唐雷[1] 薛福珍[1] 

机构地区：[1]中国科学技术大学自动化系,合肥230027

出　　处：《化工自动化及仪表》2008年第5期7-11,共5页Control and Instruments in Chemical Industry

基　　金：安徽省发改高技项目(2005661)

摘　　要：提出用免疫量子粒子群算法优化控制决策表,使控制决策表的参数整定简单易行。其核心思想是将控制决策表作为算法中的粒子,以迭代搜索的方式寻找全局最优粒子。该算法的全局寻优能力强,计算机实现简单,可调参数少。模糊控制器和控制决策表的优化设计在SCON-2000模糊控制平台进行了工程化实现,并对水箱液位进行模糊控制。从对比结果中可以看出,优化了控制决策表以后,系统响应更快,精度更高,抗扰动能力更强。这表明了该算法在模糊控制器参数优化中的可行性。A method was proposed to optimize the fuzzy control table using quantum-behaved particle swarm optimization-immune （QPSO） algorithm such that it was easier to set the parameters for fuzzy control table. The main idea is to treat each fuzzy control table as a particle in the algorithm, and find the global best particle through iterative search. The proposed algorithm has strong global search ability, less parameter, and is easy to realize by computer. The fuzzy controller and the optimization of fuzzy control table have been realized on SCON-2000 fuzzy control plat- form to control the water tank level. It can be seen from the comparison that, after the optimization of fuzzy control table, the system＇s response is faster, accuracy is higher, anti-disturbance ability is stronger. This shows that the method is effective and easy to implement.

关 键 词：免疫量子粒子群 参数优化 模糊控制器 控制决策表 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]