Recurrent Self-Tuning Neuro-Fuzzy for Speed Induction Motor Drive

Abstract

This paper proposes a hybrid recurrent neuro-fuzzy (RNF) architecture for rotor speed regulation of indirect field oriented controlled (IFOC) induction motor (IM) drive. This approach incorporates Takagi–Sugeno–Kang (TSK) model-based fuzzy logic (FL) laws with a four-layer artificial neural networks (ANNs) scheme. Moreover, for the proposed RNF an improved self-tuning method is developed based on the IM theory and its high performance requirements. The principal task of the tuning method is to adjust the parameters of the FL in order to minimize the square of the error between actual and reference output. The convergence/divergence of the weights is discussed and investigated by simulation.