a"'(2)-a"'(a) nonlinear system identification via recurrent neural networks

作者：Ahn Choon Ki^*

来源：Nonlinear Dynamics, 2010, 62(3): 543-552.

DOI：10.1007/s11071-010-9741-3

• L-2-L-infinity identification
• Recurrent neural networks
• Input-to-state stability (ISS)
• Linear matrix inequality (LMI)
• Weight learning law

This paper proposes an a"'(2)-a"'(a) identification scheme as a new robust identification method for nonlinear systems via recurrent neural networks. Based on linear matrix inequality (LMI) formulation, for the first time, the a"'(2)-a"'(a) learning algorithm is presented to reduce the effect of disturbance to an a"'(2)-a"'(a) induced norm constraint. New stability results, such as boundedness, input-to-state stability (ISS), and convergence, are established in some senses. It is shown that the design of the a"'(2)-a"'(a) identification method can be achieved by solving LMIs, which can be easily facilitated by using some standard numerical packages. A numerical example is presented to demonstrate the validity of the proposed identification scheme.

• 出版日期2010-11