Extended Kalman Filter Based Learning Fuzzy for Parameters Adaptation of Induction Motor Drive

This paper develops a novel sensorless vector control of induction motor (IM) drive robust against rotor resistance variation. The rotor resistance and speed are identified using extended Kalman filter (EKF). Then, we introduce a new fuzzy logic (FL) speed controller based on self learning by minimizing cost function. This approach is based on a topology control self-organized and an algorithm for modifying the knowledge base of fuzzy corrector. Indeed, the learning mechanism addresses the consequences of corrector rules, which are changed according to the comparison between the actual motor speed and an output signal or a desired trajectory. The FL associative memory is built to meet the criteria imposed in problems either control or pursuit. Inter alia, the consequent algorithm updating consists of a regulator mechanism allowing a fast and robust learning without unnecessarily compromising the control signal and steady state performance. The robustness of this new strategy is satisfactory, even in the presence of noise or when there are variations in the parameters of IM drive.