Sensorless speed and position control of induction motor servo drives using MLP neural network and sliding mode controller

• Authors: Morteza Majdi;Farzan Rashidi
• Venue: NOLASC'05 Proceedings of the 4th WSEAS International Conference on Non-linear Analysis, Non-linear Systems and Chaos
• Year: 2005

In this paper, the sensorless speed and position control of induction motor drive is studied. A Sliding Mode Controller (SMC) is designed and analyzed to achieve high-dynamic performance both in the speed and position command tracking and load regulation responses based on the closed-loop tracking transfer function. An artificial neural network (ANN) is adopted to estimate the motor speed and thus provide a sensorless speed estimator according to the required specifications for the IM servo drive system. The performance of the proposed controller for induction motor servo drive is investigated by some simulations including startup, step changes in reference speed, unknown load torque and parameters variations. In spite of the simple structure of the proposed speed and position controller, the obtained results show that this controller can provide a fast and accurate dynamic response in tracking and disturbance rejection characteristics under parameter variations. At the same time, a reduction of the computation time has been occurred as a result of the simple construction of the sliding mode controller. The proposed SMC can compensate the induction machine drive system at nominal values and is insignificantly affected by variations in the induction machine's parameters. The position response of the proposed SM position control scheme is influenced slightly by the load disturbance, whether the system parameters varied or not.