Intelligent Backstepping Control of Synchronous Reluctance Motor Drive System

Abstract

An intelligent backstepping control (BSC) using recurrent feature selection fuzzy neural network (RFSFNN) is proposed to construct a high-performance synchronous reluctance motor (SRM) position drive system. First, the dynamics of the SRM position drive system and the BSC are briefly introduced. However, the lumped uncertainty of the SRM is unavailable to obtain in advance. Therefore, an intelligent backstepping control using recurrent feature selection fuzzy neural network (IBSCRFSFNN), which combines the advantages of recurrent neural network, fuzzy logic system and feature selection method, is developed to approximate an idea BSC and to maintain the stability of SRM position drive system. The network structure and online learning algorithm of the IBSCRFSFNN are described in detail. At last, the proposed control system is implemented in a floating-point TMS320F28075 digital signal processor. The experimental results are illustrated to show the validity of the proposed intelligent BSC system.