Intelligent backstepping control using recurrent feature selection fuzzy neural network for synchronous reluctance motor position servo drive system

The synchronous reluctance motor (SynRM) is a high-efficiency and low-cost motor with rugged structure. However, the nonlinear and time-varying control characteristics of the SynRM with high torque ripple confine the high-performance applications of this motor. Therefore, an intelligent backstepping control (BSC) using recurrent feature selection fuzzy neural network is proposed to construct a high-performance SynRM position servo drive system. First, the dynamic model of a vector control SynRM position servo drive is introduced. Second, a BSC system is designed for the tracking of the position reference. Since the lumped uncertainty of the SynRM position servo drive system is unavailable in advance, it is very difficult to design an effective BSC in practical applications. Moreover, the sign function in BSC will cause undesired chattering phenomenon, which will excite unknown dynamics and wear the ball bearing of the SynRM. To alleviate the existed difficulties in the BSC, the recurrent feature selection fuzzy neural network (RFSFNN) is proposed in this study to approximate an idea BSC. In addition, to compensate the possible approximated error of the RFSFNN, an improved adaptive compensator is augmented. The online learning algorithms of the RFSFNN are derived by using the Lyapunov stability method to assure asymptotical stability. Finally, the proposed control system is implemented in a 32-bit floating point digital signal processor. The effectiveness and robustness of the proposed intelligent BSC system are verified by some experimental results.