Part of Advances in Neural Information Processing Systems 6 (NIPS 1993)
This paper describes probabilistic methods for novelty detection when using pattern recognition methods for fault monitoring of dynamic systems. The problem of novelty detection is particular(cid:173) ly acute when prior knowledge and training data only allow one to construct an incomplete classification model. Allowance must be made in model design so that the classifier will be robust to data generated by classes not included in the training phase. For diagnosis applications one practical approach is to construct both an input density model and a discriminative class model. Using Bayes' rule and prior estimates of the relative likelihood of data of known and unknown origin the resulting classification equations are straightforward. The paper describes the application of this method in the context of hidden Markov models for online fault monitoring of large ground antennas for spacecraft tracking, with particular application to the detection of transient behaviour of unknown origin.
1 PROBLEM BACKGROUND
Conventional control-theoretic models for fault detection typically rely on an accu(cid:173) rate model ofthe plant being monitored (Patton, Frank, and Clark, 1989). However, in practice it common that no such model exists for complex non-linear systems. The large ground antennas used by JPL's Deep Space Network (DSN) to track