A Neuro-Based Classification Algorithm for Implementation of Space Vector Modulation for Multi-Level Converters

Abstract

This paper proposes a novel, simple and fast classification algorithm for implementation of Space Vector Modulation (SVM) method for a multi-level Diode Clamped Converter (DCC) with any number of levels. The proposed algorithm is based on a classifier neural network. The proposed algorithm provides a straightforward and computationally efficient approach without the use of trigonometric calculations or look-up tables to identify the location of reference voltage vector, its adjacent switching voltage vectors, and their corresponding on-duration time intervals. The feasibility of the proposed SVM algorithm is validated based on theoretical analysis, simulation studies and experimental tests on a DSPcontrolled, 5 kVA, three-level DCC system.