An Improved Torque Ripple Reduction Controller for Smooth Operation of Induction Motor Drive

This paper describes the development of a state-of-the-art controller for induction motor drive to achieve smooth speed control under its different running conditions. The controller adopts indirect field-oriented control (IFOC) scheme for precise estimation of equivalent circuit parameters (ECPs) to generate PWM signals. The challenges for estimation of ECPs during the running condition due to change in motor temperature as well as the sudden change in its loading are dealt with a model reference adaptive system (MRAS) controller. The H-G diagram method-based reference model is utilized to estimate the reference ECPs without performing any physical tests of the motor. The backpropagation algorithm with an artificial neural network (BPANN) is utilized in its plant model while the weight and gain parameters of this model are tuned based on reference ECPs. The AdaDelta rule is utilized for fast convergence of the BPANN weights during starting conditions while stator temperature and other feedback enhance the overall performance with increased accuracy in ripple-free speed regulation. The results from MATLAB-based simulation and a hardware prototype controller using a DSPIC microcontroller with different running conditions show the efficacy of the proposed algorithm.