Development of a neuro-fuzzy controller for induction motor

摘要

This paper presents a novel neuro-fuzzy (NF) controller based speed control scheme for a high performance induction motor (IM) drive. A 5-layer ANN structure is utilized to train the parameters of the FLC based on the minimization of the square of the error, which is considered as the object function. The FLC and ANN structures were developed based on motor control theory incorporating various uncertainties. A complete simulation model for indirect field oriented control of IM incorporating the proposed NF controller is developed. The performance of the proposed NF based IM drive is investigated at different operating conditions such as sinusoid reference speed, load disturbance and parameter disturbances. It is found that the performance of the proposed drive is robust and suitable for application in high performance industrial drive applications.