Feature Extraction for Bearing Prognostics Based on Continuous Hidden Markov Model

Many research papers implemented fault diagnosis and prognosis when there are many history data. However, for some capital and high reliability equipment, it is very difficult to acquire some run-to-failure data. In this case, the fault diagnosis and prognosis become very hard. In order to address this issue, continuous hidden Markov model (CHMM) is used to track the degradation process in this paper. With the degradation, the log-likelihood which is the output of CHMM will decrease gradually. Therefore, this indicator can be used to evaluate the health condition of monitored equipment. Finally, bearing run-to-failure data sets are used to validate the model’s effectiveness