Neural network-based online H_∞ control for discrete-time affine nonlinear system using adaptive dynamic programming

详细信息    查看全文

• 作者：Chunbin Qin^a ; ^bAuthor Vitae ; Huaguang Zhang^c ; ^d ; ^{zhanghuaguangieee@gmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Yingchun Wang^cAuthor Vitae ; Yanhong Luo^cAuthor Vitae
• 关键词：H&infin ; H&infin ; control ; Adaptive dynamic programming ; Neural networks ; Nonlinear discrete-time system ; Two-person zero-sum game
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：19 July 2016
• 年：2016
• 卷：198
• 期：Complete
• 页码：91-99
• 全文大小：631 K

文摘

In this paper, the problem of H_∞$H_{\infty }$ control design for affine nonlinear discrete-time systems is addressed by using adaptive dynamic programming (ADP). First, the nonlinear H_∞$H_{\infty }$ control problem is transformed into solving the two-player zero-sum differential game problem of the nonlinear system. Then, the critic, action and disturbance networks are designed by using neural networks to solve online the Hamilton–Jacobi–Isaacs (HJI) equation associating with the two-player zero-sum differential game. When novel weight update laws for the critic, action and disturbance networks are tuned online by using data generated in real-time along the system trajectories, it is shown that the system states, all neural networks weight estimation errors are uniformly ultimately bounded by using Lyapunov techniques. Further, it is shown that the output of the action network approaches the optimal control input with small bounded error and the output of the disturbance network approaches the worst disturbance with small bounded error. At last, simulation results are presented to demonstrate the effectiveness of the new ADP-based method.