Simulation and modeling of stator flux estimator for induction motor using artificial neural network technique

Accurate stator flux estimation for high performance induction motor drives is very important to ensure proper drive operation and stability. Unfortunately, there is some problems occurred when estimating stator flux especially at zero speed and at low frequency. Hence a simple open loop controller of pulse width modulation voltage source inverter (PWM-VSI) fed induction motor configuration is presented. By a selection of voltage model-based of stator flux estimation, a simple method using artificial neural network (ANN) technique is proposed to estimate stator flux by means of feed forward back propagation algorithm. In motor drives applications, artificial neural network has several advantages such as faster execution speed, harmonic ripple immunity and fault tolerance characteristics that will result in a significant improvement in the steady state performances. Thus, to simulate and model stator flux estimator, Matlab/Simulink software package particularly power system block set and neural network toolbox is implemented. A structure of three-layered artificial neural network technique has been applied to the proposed stator flux estimator. As a result, this technique gives good improvement in estimating stator flux which the estimated stator flux is very similar in terms of magnitude and phase angle if compared to the real stator flux.