Premium
Lyapunov‐based training algorithm applied to a continually on line‐trained ANN used in the current‐loop control of a single‐phase switched rectifier
Author(s) -
Viola J. C.,
Restrepo J. A.
Publication year - 2008
Publication title -
international journal of adaptive control and signal processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.73
H-Index - 66
eISSN - 1099-1115
pISSN - 0890-6327
DOI - 10.1002/acs.1010
Subject(s) - rectifier (neural networks) , artificial neural network , computer science , control theory (sociology) , lyapunov stability , algorithm , metric (unit) , stability (learning theory) , lyapunov function , engineering , artificial intelligence , control (management) , machine learning , recurrent neural network , operations management , physics , stochastic neural network , nonlinear system , quantum mechanics
This paper presents an implementation of a PWM single‐phase switched rectifier controlled by a continually online‐trained artificial neural network (COT‐ANN). The stability of the COT‐ANN training is ensured by using a suitable description of the switched rectifier and a Lyapunov‐based training algorithm. The stability of the neural network is verified using a norm metric of the ANN matrix weights. The proposed switched rectifier can reverse the power flow direction while attaining power factor regulation. Simulations are used to test the validity of the proposed algorithm and the results are finally verified by a practical implementation of this system. Copyright © 2007 John Wiley & Sons, Ltd.