Trajectory tracking for direct drive x-y table using T-S recurrent fuzzy network controller

This paper presents a control system using a T-S recurrent fuzzy network (TSRFN) to control the position of the mover of x-y table to track periodic reference trajectories. The two-axis motion control system is an x-y table composed of two permanent-magnet linear synchronous motors (PMLSM). The proposed TSRFN combines the merits of self-constructing fuzzy neural network (SCFNN), T-S fuzzy inference mechanism, and recurrent neural network (RNN). The structure and the parameter learning phases are preformed concurrently and online in the TSRFN. The structure learning is based on the partition of input space, and the parameter learning is based on the supervised gradient-descent method using a delta adaptation law. Moreover, to improve the control performance in reference contours tracking, the motions at x-axis and y-axis are controlled separately. The simulations show that the robustness to parameter variations, external disturbances, is effective and yield superior results.