Estimator-based fuzzy credit-assigned cerebellar model articulation controller design for vector-controlled induction motor drives

Abstract

This study has designed and implemented a novel speed controller and multi-estimator in a sensorless field-oriented control system for controlling induction motor (IM) speed. The speed controller was designed based on a fuzzy credit-assigned cerebellar model articulation controller (FCA-CMAC) to provide the online learning ability required for IM speed control. In contrast to the fuzzy cerebellar model articulation controller, the FCA-CMAC provides a faster convergence speed in the learning process for approximating a nonlinear function. Additionally, the multi-estimator provides a real-time adaptive estimation of motor speed and rotor resistance for achieving robustness for the IM controller against varying motor parameters. The multi-estimator is implemented by designing a cerebellar model articulation controller (CMAC) PI controller based on model reference adaptive system theory to adjust the adaptive pseudo-reduced-order flux observer parameters. Experiments performed on a 3-hp IM confirmed the effectiveness of the proposed approach. The experimental results confirm that the proposed control scheme achieves excellent dynamic and tracking responses to varying motor parameters.