Space Vector Modulation of a Voltage fed Inverter Using Artificial Neural Networks

Space Vector Modulation (SVM) is an optimum Pulse Width Modulation (PWM) technique for variable frequency drive applications. It is computationally rigorous and hence limits the switching frequency. Increase in switching frequency can be achieved using Neural Network (NN) based SVM, implemented on application specific chips. This paper proposes a neural network based SVM technique for a Voltage Source Inverter (VSI). The network proposed is independent of switching frequency. Different architectures are investigated keeping the total number of neurons constant. The interesting results observed are discussed. The performance of the inverter is compared for various switching frequencies for different architectures of NN based SVM. From the results obtained the optimal network architecture for SVM implementation is identified and presented. Further the feasibility of implementation is investigated.