Eur. Phys. J. AP 11, 21-27 (2000)
https://doi.org/10.1051/epjap:2000142

Neural control and transient analysis of the LCL-type resonant converter

¹ University Mohammed 1er, École Supérieure de Technologie, Oujda Hay EL QODS, Complexe Universitaire, BP 473, 60000 Oujda, Morocco
² Computer & Electrical Engineering department, College of Engineering Michigan State University, USA

Corresponding author: zouggar@est.univ-oujda.ac.ma

Received: 17 July 1999
Revised: 25 January 2000
Accepted: 7 April 2000
Published online: 15 July 2000

Abstract

This paper proposes a generalised inverse learning structure to control the LCL converter. A feedforward neural network is trained to act as an inverse model of the LCL converter then both are cascaded such that the composed system results in an identity mapping between desired response and the LCL output voltage. Using the large signal model, we analyse the transient output response of the controlled LCL converter in the case of large variation of the load. The simulation results show the efficiency of using neural networks to regulate the LCL converter.