AI EDAM

  • AI EDAM / Volume 15 / Issue 04 / September 2001, pp 349-365
  • Copyright © 2001 Cambridge University Press
  • DOI: http://dx.doi.org/ (About DOI), Published online: 11 January 2002

Special Issue: AI in Equipment Service

Fault prognostics using dynamic wavelet neural networks


PENG  WANG a1 and GEORGE  VACHTSEVANOS a1c1
a1 School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332-0250, USA

Abstract

Modern industry is concerned about extending the lifetime of its critical processes and maintaining them only when required. Significant aspects of these trends include the ability to diagnose impending failures, prognosticate the remaining useful lifetime of the process and schedule maintenance operations so that uptime is maximized. Prognosis is probably the most difficult of the three issues leading to condition-based maintenance (CBM). This paper attempts to address this challenging problem with intelligence-oriented techniques, specifically dynamic wavelet neural networks (DWNNs). DWNNs incorporate temporal information and storage capacity into their functionality so that they can predict into the future, carrying out fault prognostic tasks. Such fundamental issues as the network structure, learning algorithms, stability analysis, uncertainty management, and performance assessment are studied in a theoretical framework. An example is presented in which a trained DWNN successfully prognoses a defective bearing with a crack in its inner race.

(Received October 27 2000)
(Accepted November 27 2000)


Key Words: Condition-Based Maintenance; Fault Diagnosis; Fault Prognosis; Neural Networks; Wavelets.

Correspondence:
c1 Reprint requests to: George Vachtsevanos, School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332-0250, USA. E-mail: gjv@ece.gatech.edu


0Comments