摘要
提出了一种基于去模糊优化的模糊神经网络控制器及模糊神经网络的遗传学习算法.利用遗传算法优化包含控制器性能的指标来离线寻找最优的模糊神经网络控制器结构和参数,经过遗传算法训练的模糊神经网络控制器被接入模糊神经网络智能控制系统中.仿真结果表明,利用此方法实现的控制,系统的控制精度高,超调量小,鲁棒性能很强,获得了良好的控制效果.
A fuzzy neural network controller based on the optimization of defuzzification is presented.A fuzzy neural network optimal control by genetic algorithm is put forward based on the ideal of optimal control.Through simulating the process of the control system,the structure and the parameters of the fuzzy neural network are optimized off-line using GAs by optimizing an index of the controller performance.The trained fuzzy neural network is then introduced into the fuzzy nerual network intelligent control system.The computer simulation results demonstrate that the system has high control precise and small overshoot,possesses strong robustness and results show good control performance.
出处
《微电子学与计算机》
CSCD
北大核心
2010年第10期149-151,155,共4页
Microelectronics & Computer
基金
国家自然科学基金项目(50605051)
关键词
模糊神经网络
遗传算法
模糊神经网络控制器
最优控制
fuzzy neural network
genetic algorithm
fuzzy neural network controller
optimal control
