摘要
利用多层神经网络构建模糊自适应PID控制器,通过神经网络自学习能力在线提取模糊控制规则,优化控制器隶属度函数,根据不同时刻的误差e和误差变化ec运用模糊推理在线自整定PID参数。仿真实验表明,该控制系统具有优良的控制性能。此外,通过遗传算法对模糊神经网络的学习速率和惯性系数等进行了优化,为控制系统实现最优控制提供了有力保证。
This paper utilizes multilayer neual network to construct a fuzzy self tuning PID controller. The controller can get hold of fuzzy rules and optimize its subjection function online by self-learning ability of the neual network ,and it also can adjust PID parameter in operation according to ＂e＂ and ＂ec ＂at different time by fuzzy reasoning . The excellent control performance of the control system is proved by computer Simulation. In addition, The paper makes use of Ge netic Algorithms to optimize learning rates and inertia coefficients of Fuzzy-neural network, which can ensure that the controller achieves optimization control.
出处
《太原理工大学学报》
CAS
北大核心
2006年第3期298-301,305,共5页
Journal of Taiyuan University of Technology
关键词
模糊神经
自适应PID
遗传算法
建模
仿真
Fuzzy-Neural
self-tuning PID
genetic algorithms
modeling
simulation
