Development of a self-tuned neuro-fuzzy controller for induction motor drives

In this paper, a novel adaptive neuro-fuzzy (NF)-based speed control of an induction motor (IM) is presented. The proposed NF controller (NFC) incorporates fuzzy logic laws with a five-layer artificial neural network scheme. In this controller, only three membership functions are used for each input for low computational burden, which will be suitable for real-time implementation. Furthermore, for the proposed NFC, an improved self-tuning method is developed based on the knowledge of intelligent algorithms and high-performance requirements of motor drives. The main task of the tuning method is to adjust the parameters of the, fuzzy logic controller (FLC) in order to minimize the square of the error between actual and reference outputs. A complete model for indirect field-oriented control of IM incorporating the proposed NFC is developed. The performance of the proposed NFC-based IM drive is investigated extensively both in simulation and in experiment at different operating conditions. In order to prove the superiority of the proposed NFC, the results for the proposed controller are also compared to those obtained by conventional proportional-integral (PI) and FLC controllers. The proposed NFC-based IM drive is found to be more robust as compared to conventional PI and FLC controllers and, hence, suitable for high-performance industrial drive applications.