PERFORMANCE EVALUATION OF ARTIFICIAL NEURAL NETWORK BASED SPACE VECTOR PWM CONTROLLED INDUCTION MOTOR DRIVE

Abstract

Space vector Modulatioh (SVM) is a very popular pulsewidth modulation for voltage — fed converter ac drives because of its superior harmonic quality and extended linear range of operation. However, a difficulty of SVM is that it requires it requires complex online computation that usually limits its operation up to several kilohertz of switching frequency. Switching frequency can be extended by using a high-speed digital signal _ processor (DSP) and simplifying computations with the help of lookup tables. Lookup tables, unless very large, tend to reduce the pulsewidth resolution. For the higher switching frequencies needed by the modern ultrafast IGBTs, the DSP. based SVM practically fails in this region where artificial neural network (ANN) based SVM can possibly take over. A backpropagation type ANN which has high computational capability can implement an SVM algorithm. The ANN has inherent learning capability that can give improved precision by interpolation unlike the standard lookup table.