Adaptive PID Control Based on Improved RBF Neural Network and Its Application in Nonlinear System

摘要：

An adaptive PID control strategy based on self-learning Radial Basis Function (RBF) neural network(NN) is presented in this paper. An off-line optimization algorithm is employed to choose the number of hidden nodes of RBFNN. According to the theory of optimization in groups, an improved on-line learning algorithm is used to adjust center node parameters and estimate connection weight values. The adaptive controller combines this improved RBFNN with conventional PID control, and it is applied to a nonlinear and time varying system.Simulation results show that the proposed controller has the adaptability, strong robustness and satisfactory control performance.

作者: Mingguang Zhang Zhaogang Wang Peng Wang

作者单位: School of Electrical and Information Engineering Lanzhou University of Technology Lanzhou ,Gansu, 730050, P.R. China

会议类型: 国际会议

会议名称: Fourth International Conference on Impulsive and Hybrid Dynamical Systems(ICIHDS 2007)(第四届国际脉冲和混合动力系统学术会议)

会议地点: 南宁

会议语种:英文

在线出版日期: 2007-07-20（万方平台首次上网日期，不代表论文的发表时间）