Past Issues

Studies in Informatics and Control
Vol. 8, No. 2, 1999

Artificial Neural Networks Application to Boolean Input Systems Control

William Halderbaum, Regis Canart, Pierre Borne
Abstract

Boolean input systems have hecome important in the electrical industry. These systems mainly include power supply associated with converters and electric motors. In this paper we present a method for controlling Boolean input systems by using Artificial Neural Network. This method is based on classification of system variations associated with input configurations. The supervised backpropagation algorithm is used to train the networks. The training of the Artificial Neural Network and the control of Boolean input systems are presented. The design procedure of control systems is implemented on a non-linear system. These results are applied to an electrical system composed of a synchronous motor and its power converter. The control of this system is performed on its speed.

Keywords

Boolean control, Commutation, State space, Classification, Artificial Neural Networks, Backpropagation.

View full article