基于混合递归算法优化的PID控制器  

Adaptive PID Control Based on RBFNN Identification

作　　者：李广军[1] 张靓[2] 张晶[1] 

机构地区：[1]宜宾学院计算机系,四川宜宾64400 [2]成都航空职业技术学院,四川成都610021

出　　处：《佳木斯大学学报（自然科学版）》2007年第6期729-731,共3页Journal of Jiamusi University：Natural Science Edition

摘　　要：针对RBF神经网络PID控制器,使用递阶遗传算法和梯度下降法的混合算法来优化隐含层到输出层的权值、隐层节点的中心和核宽度.仿真显示,精度高,性能优于梯度下降法.To nonlinear system, a PID control system based on RBF Identification is used. Hybrid hierarchy genetic algorithms is introduced to configure the structure and parameters of RBF network, and the RBNN identification results are compared with wtfich produced by grads - dropping algorithms. The simulation results show that the identification effects of RBFNN which is optimized by hybrid hierarchy genetic algorithms is better than those of what is opfiby agads- gropping algorithms.

关 键 词：RBF神经网络 混合递阶遗传算法 PID控制器 梯度下降法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]