Share Email Print

Proceedings Paper

Classification of thermally condition-monitored components using statistical and neural network techniques
Author(s): Nathan T. Moja; Andrew J. Willis
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A popular approach to the qualitative analysis of thermal patterns has been to identify anomalies through comparison of thermal images against a single baseline or reference image. However, this approach represents an oversimplification as significant variations of thermal patterns due to change in measurement position, changing equipment loading, environmental conditions and varying mechanisms of equipment deterioration are not catered for. To overcome these limitations, the use of neural net and statistically based classifiers has been investigated, in the latter case for both parametric and non parametric designs. An experimental thermal image database characterizing normal and abnormal load tap-changer operation of a 63 MVA, 22kV transformer provided the training data. The images were captured at different times, different locations and under varying loads.

Paper Details

Date Published: 30 October 1997
PDF: 9 pages
Proc. SPIE 3164, Applications of Digital Image Processing XX, (30 October 1997); doi: 10.1117/12.279582
Show Author Affiliations
Nathan T. Moja, Eskom Technology Research and Investigations (South Africa)
Andrew J. Willis, Univ. of the Witwatersrand (South Africa)

Published in SPIE Proceedings Vol. 3164:
Applications of Digital Image Processing XX
Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?