Skip to the content

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

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

[img] PDF
Restricted to Repository staff only

Download (166kB) | Request a copy

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.

Item Type: Article
Schools: Schools > School of Computing, Science and Engineering
Journal or Publication Title: International Journal of Knowledge-Based Intelligent Engineering Systems
Publisher: IOS Press
Refereed: Yes
ISSN: 1327-2314
Funders: Non funded research
Depositing User: Yuhua Li
Date Deposited: 31 Jul 2015 17:15
Last Modified: 05 Apr 2016 19:31
URI: http://usir.salford.ac.uk/id/eprint/35997

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)

Downloads

Downloads per month over past year