CMAC-Based Speed Estimator Design for Induction Motor Drive

In this paper, a novel speed estimation method of an induction motor using cerebellar model articulation controller (CMAC) is presented. The CMAC neural network is trained online by using the gradient-type learning algorithm, and the training starts simultaneously with the induction motor working. The estimated speed of the CMAC is then fed back in the speed control loop, and the speed-sensorless vector drive is realized. The proposed CMAC speed estimator has shown good performance in the transient and steady states, and also at either variable-speed operation or load variation. The validity and the usefulness of the proposed algorithm are thoroughly verified with experiments on fully digitalized 3-hp induction motor drive system.