Improving performance of sensorless vector control using artificial neural network against parametric uncertainty

Abstract

Field oriented control (FOC) method is one of the most efficient control schemes for induction motors (IMs). Major drawbacks of FOC schemes is their high sensitivity to slip angular velocity perturbations and changing parameters in during of operation. The analytical equations are provided to investigate the effect variation of parameters on the performance of FOC. This paper proposes a robust modified FOC scheme based on artificial neural network (ANN) for speed control of IM, with regard to improve the system performance as well as ensure the stability, robustness and fast dynamic response. Rotor flux and speed have been estimated in rotor reference frame using stator voltages and currents to achieve the aforementioned objectives. The estimation based on ANN to compensate for uncertain parameters in the motor's dynamic model. Moreover, this estimation leads to lack use of flux and speed sensor, therefore, the method is cost effective. Using function approximation property of ANN, measurable motor variables can be estimated. Multilayer feed forward neural networks (FFNN) are used. The training of the neural network and the simulation of the identification of the system are exposed in this paper. Speed and flux estimator were implemented upon these ANN's using MATLAB/SIMULINK neural-network toolbox. The control strategy is proved feasible by simulation under load and parameter variation and the reference value change of system parameters. The results show that the performance of system is independent of system uncertainty of parameters and variation load and presents the faster dynamic behavior.