THE SELF-TUNING PID DECOUPLING CONTROL BASED ON THE DIAGONAL RECURRENT NEURAL NETWORK

摘要：

The diagonal recurrent neural networks (DRNN) is a powerful computational tools that have been used extensively in the areas of pattern recognition, systems modeling and identification. This paper proposes a self-tuning PID decoupling control based on DRNN neural networks for solving the time-varying coupling nonlinear control problems.The approach can on-line identify the controlled plant using the DRNN identifier and tune the parameters of the PID controller automatically. The simulation results show that the proposed control algorithm is an efficient method to solve nonlinear coupling problems. From the simulation results we see that the system output can tract and decouple the reference input satisfactorily, and the performance of the proposed controller is better than that of the conventional PID decoupling controller in the time-varying coupling nonlinear system, such as good adaptability, strong robustness and fast response speed.

关键词： Diagonal recurrent neural network PID Decoupling control Self-tuning

作者: MING-GUANG ZHANG XING-GUI WANG WEN-HUI LI

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

会议类型: 国际会议

会议名称: 2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)

会议地点: 大连

会议语种:英文

页码: 3016-3020

在线出版日期: 2006-08-13（万方平台首次上网日期，不代表论文的发表时间）