Robust fuzzy neural network controller with nonlinear disturbance observer for two-axis motion control system

Abstract

A robust fuzzy neural network controller with nonlinear disturbance observer (RFNNCNDO) is proposed for the precision control of a two-axis motion control system. The adopted two-axis motion control system is composed of two permanent magnet linear synchronous motors (PMLSMs). The single-axis motion dynamics with the introduction of a lumped disturbance, which includes parameter variations, external disturbances, cross-coupled interference between the two PMLSMs and fiction force, is derived. Then, a nonlinear disturbance observer is applied to estimate the lumped disturbance and a feedback linearisation controller is adopted to stabilise the control system. However, the system responses are degraded by the existed observer error. To improve the control performance in the tracking of the reference contours, a Sugeno-type adaptive fuzzy neural network (SAFNN) is employed in the proposed RFNNCNDO to estimate the observer error directly. The online learning algorithms of the SAFNN guarantee the stability of closed-loop systems on the basis of the Lyapunov theorem. Moreover, the proposed control algorithms are implemented in a TMS320C32 digital signal processor (DSP)-based control computer. From the simulated and experimental results, the contour tracking performance of the two-axis motion control system is significantly improved and the robustness can be obtained as well using the proposed RFNNCNDO control system.