Share Email Print

Proceedings Paper

Reduction of thermal data using neural networks
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A scanned thermal line source is a rapid and efficient technique for detection of corrosion in aircraft components. Reconstruction of the back surface profile from the data obtained with this technique requires a nonlinear mapping. Neural networks are an effective method for performing nonlinear mappings of one parameter space to another. This paper discusses the application of neural networks to the reconstruction of back surface profiles from the data obtained from a thermal line scan. The neural network is found to be a very effective method of reconstructing arbitrary surface profiles. The network is trained on simulations of the thermal line scan technique. The trained network is then applied to both simulated and experimentally obtained data. The reconstructed profiles are in good agreement with independent characterizations of the profiles. Limitations of the reconstruction technique are illustrated by presenting results for several different configurations.

Paper Details

Date Published: 30 March 2000
PDF: 9 pages
Proc. SPIE 4020, Thermosense XXII, (30 March 2000); doi: 10.1117/12.381542
Show Author Affiliations
William P. Winfree, NASA Langley Research Ctr. (United States)
K. Elliott Cramer, NASA Langley Research Ctr. (United States)

Published in SPIE Proceedings Vol. 4020:
Thermosense XXII
Ralph B. Dinwiddie; Dennis H. LeMieux, Editor(s)

© SPIE. Terms of Use
Back to Top