一种基于GA的模糊神经网络控制器设计及应用

GA-Based Fuzzy Neural-Network Controller Design and Application

结合模糊控制、神经网络、遗传算法三种方法的优点 ,提出了一种基于遗传算法的模糊神经网络控制器 ,并分析了其网络结构和离线学习的方法 遗传算法基于全局优化策略 ,避免了反向传播学习算法易陷入局部最优的缺陷 仿真实验和在汽车防抱死制动系统中的应用表明这种控制方案是有效的 。

A fuzzy neural network controller based on genetic algorithm (GA) is proposed. It combines the advantages of the three methods: fuzzy control, neural network and GA. And the network off-line learning methods are analyzed. GA is a kind of global optimization techniques that can avoid the Back Propagation alg orithm's shortcoming of getting into local solution. Simulation and t he application in automobile anti-lock system show that the scheme is effective and feasible.