Design of a Simplified Neuro-Fuzzy-GA-based IM Drive Deploying Linearization Approach

Abstract

This paper focuses on the design and implementation of a genetic algorithm (GA) tuned modified simple neuro-fuzzy control (NFC) for optimal performance of induction motor (IM) drive employing feedback linearization (FBL) approach. The intuitive FBL with the proposed simplified NFC with GA (SNFC-GA) substantially reduces the torque chattering and improves the speed response of the IM drive. This new technique also has the main advantage of improved computational efficiency by reducing computational burden over classical NFC and thus, fit for real-time industrial applications. Moreover, the GA searches the optimal parameters of the simplified NFC in order to ensure the global convergence of error. The efficacy of the proposed controller using FBL IM drive is investigated in simulation as well as in experiment, and it is evident that the robust and optimal dynamic performance of the system is achieved in terms of parameter variations and external load disturbance.