Fuzzy-neural networks controller-based adapatation mechanism for MRAS sensorless induction motor drives

This paper presents a fuzzy-neural control for speed tracking of induction motor using model-reference adaptive scheme (MRAS) approach in a direct field oriented control system. In particular, it addresses two important subjects of AC induction motor drives: the control of the machine and the speed estimation is sensorless drives. On this basis, this work summarizes the fuzzy-neural control and the speed estimator based on a MRAS. Speed control performance and sensorless speed estimation and induction motors are affected by parameter variations and nonlinearities in the induction motor. This paper also uses a very realistic and practical scheme to estimate and control the noise content in the speed load torque characteristic of the motor. The technique MRAS rotor speed estimator has been incorporated for which stability, robustness and parameter variations are assured. The aim of the proposed control fuzzy-neural ANFIS is to improve the performance and robustness of the induction motor drives under non linear loads variations is presented in this work. The availability of the proposed structure scheme is verified by through a laboratory implementation and under computation simulations with Matlab-software. The proposed technique can be generalized to other motor drives. Simulation results are presented in order to prove the excellent tracking performance of the scheme.