On selecting pre-processing techniques for fault classification using neural networks : a pilot study

Li, Y; Pont, MJ

Abstract

This paper introduces a measure for selecting an appropriate pre-processing strategy for use in neural network-based condition monitoring and fault diagnosis (CMFD) applications. The proposed selection measure is derived from a non-parametric separability matrix: no knowledge of the underlying distribution of the data is required. The effectiveness of this measure is explored on a problem of engine misfire detection.

Citation

Li, Y., & Pont, M. (2002). On selecting pre-processing techniques for fault classification using neural networks : a pilot study. International Journal of Knowledge-Based and Intelligent Engineering Systems, 6(2), 80-87

• Journal Article Type: Article
• Publication Date: Jan 1, 2002
• Deposit Date: Jul 31, 2015
• Journal: International Journal of Knowledge-Based Intelligent Engineering Systems
• Print ISSN: 1327-2314
• Electronic ISSN: 1875-8827
• Publisher: IOS Press
• Peer Reviewed: Peer Reviewed
• Volume: 6
• Issue: 2
• Pages: 80-87
• Publisher URL: http://www.kesinternational.org/journal/