A new approach based on recurrent neural networks for system identification


KALINLI A. , Sagiroglu S.

COMPUTER AND INFORMATION SCIENCES - ISCIS 2003, vol.2869, pp.568-575, 2003 (Journal Indexed in SCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 2869
  • Publication Date: 2003
  • Doi Number: 10.1007/978-3-540-39737-3_71
  • Title of Journal : COMPUTER AND INFORMATION SCIENCES - ISCIS 2003
  • Page Numbers: pp.568-575

Abstract

This paper introduces a new approach based on artificial neural networks (ANNs) to identify a number of linear dynamic systems with single recurrent neural model. The structure of single neural model is capable of dealing with systems up to a given maximum number. Single recurrent neural model is trained by the backpropagation with momentum. Total nine systems from first to third orders have been used to validate the approach presented in this work. The results have shown that the recurrent single neural model is capable of identifying a number of systems successfully. The approach presented in this work provides simplicity, accuracy and compactness to system identification.