Speed Regulation Based on Adaptive Control and RBFNN for PMSM Considering Parametric Uncertainty and Load Fluctuation

Abstract

A novel speed control scheme combining adaptive speed controller and radial basis function neural network (ASC-RBFNN) is proposed for the speed regulation of permanent magnet synchronous motor (PMSM) in this paper. On one hand, in order to reduce the effect of parametric uncertainty and complicated load fluctuation on the speed control performance, an ASC is proposed. Meanwhile, the speed control system (SCS) of PMSM with the proposed ASC is asymptotically stable even though the parametric uncertainty and complicated load fluctuation exist. On the other hand, with consideration of the uncertainty of complicated load, PMSM parameters, and ASC parameters, the RBFNN is used to optimize all ASC parameters for optimal speed control performance. Finally, the performance is verified on an experiment platform. The results indicate that the SCS with the ASC-RBFNN speed control scheme is with good system stability, fast speed response, and strong anti-fluctuation performance in whole-speed range.

Keywords

• Adaptive speed controller
• load fluctuation
• parametric uncertainty
• PMSM
• RBFNN