Adaptive neural control of uncertain multi-variable nonlinear systems with saturation and dead-zone

Abstract

In this chapter, adaptive neural control is developed for a class of uncertain MIMO nonlinear systems using neural networks. The MIMO system under study is a strict-feedback uncertain nonlinear system with non-symmetric input nonlinearities. Variable structure control (VSC) technique in combination with backstepping is proposed to tackle the input saturation and dead-zone. The spectral radius of the control coefficient matrix is introduced to design adaptive neural control in order to cancel the nonsingular assumption of the control coefficient matrix. Using the cascade property of system, the semi-global uniform ultimate boundedness of all signals in the closed-loop system is achieved. The tracking errors converge to small residual sets which are adjustable by updating design parameters. Finally, case study results are presented to illustrate the effectiveness of the proposed adaptive neural control. © 2009 Springer London.