论文信息 - Initial results on fault diagnosis of DSN antenna control assemblies using pattern recognition techniques

Initial results on fault diagnosis of DSN antenna control assemblies using pattern recognition techniques

Initial results obtained from an investigation using pattern recognition techniques for identifying fault modes in the Deep Space Network (DSN) 70 m antenna control loops are described. The overall background to the problem is described, the motivation and potential benefits of this approach are outlined. In particular, an experiment is described in which fault modes were introduced into a state-space simulation of the antenna control loops. By training a multilayer feed-forward neural network on the simulated sensor output, classification rates of over 95 percent were achieved with a false alarm rate of zero on unseen tests data. It concludes that although the neural classifier has certain practical limitations at present, it also has considerable potential for problems of this nature.

Padhraic Smyth | Jeff Mellstrom

[1] Sholom M. Weiss,et al. An Empirical Comparison of Pattern Recognition, Neural Nets, and Machine Learning Classification Methods , 1989, IJCAI.

[2] Padhraic Smyth,et al. Automated monitor and control for deep space network subsystems , 1989 .

[3] M. J. D. Powell,et al. Restart procedures for the conjugate gradient method , 1977, Math. Program..

[4] R. E. Hill. Dynamic models for simulation of the 70-M antenna axis servos , 1988 .

[5] Ronald A. Cole,et al. A neural-net training program based on conjugate-radient optimization , 1989 .

[6] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[7] Richard Lippmann,et al. Practical Characteristics of Neural Network and Conventional Pattern Classifiers on Artificial and Speech Problems , 1989, NIPS.