Citation

Abstract

This article describes initial results obtained from an investigation of using pattern recognition techniques for identifying fault modes in the Deep Space Network (DSN) 70-m antenna control assembly. It describes the overall background to the problem, outlining the motivation and potential benefits of this approach. In particular, it describes an experiment in which fault modes were introduced into a state-space simulation of the antenna control loops. By training a multilayer feed95 percent were achieved with a false alarm rate of zero on unseen test data. It concludes that although the neural classifier has certain practical limitations at present, it also has considerable potential for problems of this nature.

Details

Volume
42-101
Published
May 15, 1990
Pages
136–151
File Size
681.1 KB