摘要
通过对控制系统的过程模拟 ,提出一种模糊神经网络最优控制方案 .离线优化部分基于遗传算法 ,分三阶段实现模糊神经网络控制器结构和参数的优化 .在线优化部分通过重构模糊神经网络控制器的去模糊化部分 ,进一步调整控制规则 ,实现在线去模糊优化 .
An optimal control scheme based on fuzzy neural network is proposed through simulating the process of the control system. Firstly, the fuzzy neural network is optimized by three step scheme based on genetic algorithms off line. Then the defuzzification part of the fuzzy neural network is reconstructed and is optimized to refine control rules on line. The simulation result demonstrates that the response is more favorable than that of conventional fuzzy controllers and that of \{FNNC\} based on expert experience.
出处
《控制理论与应用》
EI
CAS
CSCD
北大核心
2000年第5期784-788,共5页
Control Theory & Applications
基金
广东省自然科学基金!(96 0 30 4)资助项目
关键词
最优控制
遗传算法
模糊神经网络
去模糊化
optimal control
genetic algorithms
fuzzy neural network
defuzzification
