Neural network controller based sequential switch cascaded H-bridge multilevel inverter

Abstract

This paper presents a novel cascaded multilevel inverter structure with reduced devices. This structure is termed as sequential switch cascaded multilevel inverter. The basic asymmetrical hybrid circuit is described and is capable of generating 17 voltage levels. The various modes of deriving 17 levels are explained and the proposed topology is compared with existing topologies in various aspects. Neural network controller can be used to generate the gating pulses. The algorithm can be trained online by using back propagation algorithm and also an algorithm to determine the number of levels, maximum voltage ratings and power loss is explained. The simulation can be done by MATLAB Simulink.

Generalised predictive controller (GPC) design on single‐phase full‐bridge inverter with a novel identification method

“…However, for the second scheme, a closed‐loop control strategies have been introduced [7]. However, the following advanced controllers are used based on the switching properties of Inverters: deadbeat technique [8], sliding‐mode control [9, 10], and fuzzy‐based structure [11–14].…”

“…Stability proof of the filter is the primary concern which can harm system dynamics; thus, two strategies were presented for this challenge: passive and active damping schemes.In passive damping strategy, the inductor is modelled with a series resistor, while total system efficiency can be affected. However, for the second scheme, a closed-loop control strategies have been introduced [7]. However, the following This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.…”