Citation
Abstract
This article describes experimental results obtained when a previously described fault diagnosis system was run on-line in real time at the 34-m beam waveguide antenna at DSS 13. Experimental conditions and the quality of results are described. A neural network model and a maximum-likelihood Gaussian classifier are compared with and without a Markov component to model temporal context. At the rate of a state update every 6.4 seconds, over a period of roughly 1 hour, the neural-Markov system had zero errors (incorrect state estimates) while monitoring both faulty and normal operations. The overall results indicate that the neural-Markov combination is the most accurate model and has significant practical potential.
Details
- Volume
- 42-108
- Published
- February 15, 1992
- Pages
- 96–108
- File Size
- 502.4 KB