Artificial neural network based implementation of space vector modulation for voltage fed inverter induction motor drive

In this paper, a neural network based implementation of space vector modulation (SVM) of a two-level voltage fed inverter is proposed. This network has the advantage of very fast implementation of SVM algorithm, particularly when a dedicated application- specific IC chip is used instead of a digital signal processor (DSP). The proposed neural network consists of several subnets, a counter and a logic circuit. Subnets are used to implement the stages of SVM algorithm while the counter is used to apply the switching state vectors in their specified times to inverter. The logic circuit generates the inverter switches commands according to the outputs of the subnets. The scheme has been evaluated on an induction motor drive which results in an excellent performance. According to straight forward steps of the artificial neural network (ANN) design, the modulator can be easily extended to multi-level inverters.