Share Email Print

Proceedings Paper

Comparison of neural network and cluster analysis techniques for the reliability of high-speed machinery
Author(s): Colin P. Matthews; J. Y. Clark; Paul M. Sharkey; K. Warwick
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper presents a comparison of three differing methods applied to the analysis of control data from a high speed machinery application. The source data and the pre-processing applied to improve the suitability of the data to the analysis techniques is discussed. The methods compared are cluster analysis, multi-layer perceptron neural networks and self organizing feature maps. The aim of the work is to determine the merits of the techniques in separating normal running operation from faulty operation. The methodology used with each technique is explained and results are computed so as to give the fairest comparison of their respective abilities. Additionally, the ways in which such techniques would be integrated into a final system for the analysis, diagnosis, and control of a high speed machine to give improved reliability are discussed.

Paper Details

Date Published: 22 December 1995
PDF: 9 pages
Proc. SPIE 2595, Machine Tool, In-Line, and Robot Sensors and Controls, (22 December 1995); doi: 10.1117/12.228853
Show Author Affiliations
Colin P. Matthews, Univ. of Reading (United Kingdom)
J. Y. Clark, Univ. of Reading (United Kingdom)
Paul M. Sharkey, Univ. of Reading (United Kingdom)
K. Warwick, Univ. of Reading (United Kingdom)

Published in SPIE Proceedings Vol. 2595:
Machine Tool, In-Line, and Robot Sensors and Controls
George D. Foret; Kam C. Lau; Bartholomew O. Nnaji, Editor(s)

© SPIE. Terms of Use
Back to Top