Hidden Markov models and neural networks for fault detection in dynamic systems

It is shown how both pattern recognition methods (in the form of neural networks) and hidden Markov models (HMMs) can be used to automatically monitor online data for fault detection purposes. Monitoring for anomalies or faults poses some technical problems which are not normally encountered in typical HMM applications such as speed recognition. In particular, the ability to detect data from previously unseen classes and the use of prior knowledge in constructing the Markov model are both essential in applications of this nature. Recent progress on these and related topics in the context of fault detection is discussed. An application of these methods to the problem of online health monitoring of an antenna pointing system is described