Diagnosing and correcting system anomalies with a robust classifier

Abstract
If a robust statistical model has been developed to classify the "health" of a system, a well-known Taylor series approximation technique forms the basis of a diagnostic/recovery procedure that can be initiated when the system's health degrades or fails altogether. This procedure determines a ranked set of probable causes for the degraded health state, which can be used as a prioritized checklist for isolating system anomalies and quantifying corrective action. The diagnostic/recovery procedure is applicable to any classifier known to be robust; it can be applied to both neural network and traditional parametric pattern classifiers generated by a supervised learning procedure in which an empirical risk/benefit measure is optimized. We describe the procedure mathematically and demonstrate its ability to detect and diagnose the cause(s) of faults in NASA's Deep Space Communications Complex at Goldstone, California.

This publication has 3 references indexed in Scilit: