基于遗传算法的模糊神经网络控制器的仿真  

Simulation of fuzzy neutral network controllers based on genetic algorithm

作　　者：胡波[1] 张斌[1] 林锦国[1] 

机构地区：[1]南京化工大学信息科学与工程学院,江苏南京210009

出　　处：《南京化工大学学报》2001年第5期53-56,共4页Journal of Nanjing University of Chemical Technology(Natural Science Edition)

摘　　要：对遗传算法 (GA)和模糊神经网络控制器的结构进行了说明。为了克服反向传播算法 (BP)的缺点 ,通过遗传算法对模糊神经网络控制器的参数进行优化 ,亦即对模糊神经网络进行训练。用通过优化后的模糊神经网络控制器控制一个带有纯滞后的非线性对象 ,仿真结果证实了其性能较常规模糊控制器优越。The genetic algorithm and the structure of the controller based on fuzzy neutral network were described. In order to overcome the disadvantage of the back propagation algorithm,the parameters of fuzzy neutral network were optimized through the genetic algorithm,this means that the fuzzy neutral network was trained. A nonlinear object with delay was controlled through the controller optimized by the method and the simulating result verifies that the controller has a better performance than normal fuzzy controllers.

关 键 词：遗传算法 模糊控制 神经网络 模糊神经网络控制器 仿真 

分 类 号：TP273.4[自动化与计算机技术—检测技术与自动化装置] TP183[自动化与计算机技术—控制科学与工程]