Comparative analysis of ANN and SSM controllers in a ZVCS-Full Bridge Series-Parallel Resonant DC-DC converter

Author

Malekjamshidi, Zahra ; Jafari, Mohammad

Author_Institution

Dept. of Electr. Eng., Islamic Azad Univ., Marvdasht, Iran

fYear

2011

fDate

5-8 Dec. 2011

Firstpage

643

Lastpage

647

Abstract

In this paper, two methods of control for high-voltage Full Bridge Series-Parallel Resonant (FBSPR) DC-DC converter are proposed and the results are compared. Soft switching operation using Zero Current Switching (ZCS) and Zero Voltage Switching (ZVS) technologies is employed to decrease the losses and optimize the efficiency of converter. The way of obtaining small-signal model of FBSPR converter using the generalized averaging method is discussed. Then two control methods using Artificial Neural Networks (ANN) and Sequential State Machine (SSM) are explained and the experimental results are compared. Comparison between experimental results for both ANN and SSM controllers show better speed performances for SSM controller in small changes in load and more reliability for ANN controller in case of large variations.

Keywords

DC-DC power convertors; neural nets; power engineering computing; resonant power convertors; sequential machines; zero current switching; zero voltage switching; ANN controllers; SSM controllers; ZVCS; artificial neural networks; full bridge series-parallel DC-DC converter; high-voltage DC-DC converter; reliability; resonant DC-DC converter; sequential state machine; small-signal model; soft switching operation; zero current switching; zero voltage switching; Artificial neural networks; Control systems; Equations; Mathematical model; Voltage control; Zero current switching; Zero voltage switching; Artificial Neural Networks; Full Bridge; Sequential State Machine; Series-Parallel Resonant Converter; ZCS; ZVS;

fLanguage

English

Publisher

ieee

Conference_Titel

Power Electronics and Drive Systems (PEDS), 2011 IEEE Ninth International Conference on

Conference_Location

Singapore

ISSN

2164-5256

Print_ISBN

978-1-61284-999-7

Electronic_ISBN

2164-5256

Type

conf

DOI

10.1109/PEDS.2011.6147319

Filename

6147319