On-line gain-tuning IP controller using RFNN

In this study an integral-proportional (IP) controller with on-line gain-tu ning using a recurrent fuzzy neural network (RFNN) is proposed to control t he mover position of a permanent magnet linear synchronous motor (PMLSM) se rvo drive system. The structure and operating principle of the PMLSM are fi rst described in detail. A field-oriented control PMLSM servo drive is then introduced. After that, an LP controller with on line gain-tuning using an RFNN is proposed to control the mover of the PMLSM for achieving high-prec ision position control with robustness. The backpropagation algorithm is us ed to train the RFNN on line. Moreover, to guarantee the convergence of tra cking error for the periodic step-command tracking, analytical methods base d on a discrete-type Lyapunov function are proposed to determine the varied learning rates of the RFNN. Furthermore, the proposed control system is im plemented in a PC-based computer control system. Finally, the effectiveness of the proposed PMLSM servo drive system is demonstrated by some simulated and experimental results. Accurate tracking response and superior dynamic performance can be obtained due to the powerful on-line learning capability of the RFNN. In addition, the proposed on-line gain-tuning servo drive sys tem is robust with regard to parameter variations and external disturbances .