ANFIS Based Reference Flux Estimator with GA Tuned Controller for DTC of Induction Motor

Abstract

Direct Torque Control (DTC) of induction motor provides simple control scheme with high dynamic performance. The voltage vector selection strategy is based on flux and torque response. A common strategy to control induction motor using DTC is through “Proportional– Integral (PI) speed controller as reference torque estimator” and “flux weakening controller as reference flux estimator This paper makes an attempt to replace the conventional reference flux estimator by an Adaptive Network Based Fuzzy Inference System (ANFIS). Also the PI controller used for estimating the reference torque is tuned using Genetic Algorithm (GA). The Proposed DTC system is tested for both load and source variations. To analyse the performance, the flux, torque and speed variations are measured using the performance indices like Integral Squared Error (ISE), Integral Time Absolute Error (ITAE) and Integral Time Squared Error (ITSE). The analysis proves that the proposed ANFIS based reference flux estimator and GA tuned PI controller provides better robustness and disturbance rejection ability.