Self-Organizing Recurrent Fuzzy Wavelet Neural Network-Based Mixed H₂/H_∞ Adaptive Tracking Control for Uncertain Two-Axis Motion Control System

In this paper, an intelligent adaptive tracking contro system (IATCS) based on the mixed H₂/H_∞approach fo achieving high precision performance of a two-Axis motion contro system is proposed. The two-Axis motion control system is a X-Y table driven by two permanent-magnet linear synchronou motors (PMLSMs) servo drives. The proposed control schem incorporates a mixed H₂/H_∞controller, a self-organizing recurren fuzzy-wavelet-neural-network controller (SORFWNNC) and a robust controller. The SORFWNNC is used as the mai tracking controller to adaptively estimate an unknown nonlinea dynamic function (UNDF) that includes the lumped paramete uncertainties, external disturbances, cross-coupled interference and frictional force. Furthermore, a robust controller is designed t deal with the approximation error, optimal parameter vectors, an higher order terms in Taylor series. Besides, the mixed H₂/H_∞controller is designed such that the quadratic cost function is minimize and the worst case effect of the UNDF on the tracking erro must be attenuated below a desired attenuation level. The onlin adaptive control laws are derived based on Lyapunov theorem an the mixed H₂/H_∞ tracking performance so that the stability o the IATCS can be guaranteed. The experimental results confir that the proposed IATCS grants robust performance and precis dynamic response to the reference contours regardless of externadisturbances and parameter uncertainties.