PID Controller Tuning by Using Extremum Seeking Algorithm Based on Annealing Recurrent Neural Network

摘要：

This paper proposes a discrete-time extremum seeking algorithm based on annealing recurrent neural network (ESA-ARNN) for auto-tuning of PID controller parameters. Firstly, the process of tuning PID controller parameters is transformed into an extremum seeking problem by introducing a cost function, such as the integral squared error (ISE). Then, in order to solve this extremum seeking problem, a discretetime ESA-ARNN is proposed, which can realize autotuning for PID controller parameters. Lastly, the novel auto-tuning method is applied to tuning PID controller parameters of the process system with second-order plus dead time (SOPDT). Simulation results indicate that PID controller parameters tuned by ESA-ARNN have better performance than those tuned by the eight prevalent PID tuning schemes.

关键词： Extremum seeking algorithm Annealing recurrent neural network PID controller Auto-tuning SOPDT

作者: Bin Zuo Yun-an Hu Jing Li

作者单位: Department of Control Engineering Naval Aeronautical and Astronautical University Yantai,Shandong Pr Department of Control Engineering Naval Aeronautical and Astronautical University Yantai,Shandong Pr Department of Strategic Missile Engineering Naval Aeronautical and Astronautical University Yantai,

会议类型: 国际会议

会议名称: 2010 Third International Symposium on Knowledge Acquisition and Modeling(第三届知识获取与建模国际研讨会 KAN 2010)

会议地点: 武汉

会议语种:英文

页码: 132-135

在线出版日期: 2010-10-20（万方平台首次上网日期，不代表论文的发表时间）