Journals Proceedings

Abstract

A novel concept of application of Artificial Neural Networks (ANN) for estimating the optimum switching angles for the voltage and harmonic control of cascaded multilevel inverters is presented. In this paper, the neural network is trained off line using the desired switching angles given by the classic harmonic elimination strategy to any value of the modulation index. After training the proposed ANN system, a large and memory-demanding look-up table is replaced with trained neural network to generate the optimum switching angles with lowest Total Harmonic Distortion (THD) for a given modulation index. This technique can be applied to multilevel inverters with any number of levels. As an example, a seven-level and eleven-level inverter is considered and the optimum switching angles are calculated, in order to eliminate the odd harmonics and to reduce THD. The ANN control algorithm is to be implemented using m-file program. Theoretical concepts have been validated in simulation results using artificial neural network technique which shows the high performance and technical advantages of the developed system.