Please choose your delivery country and your customer group
Hidden Markov Model (HMM) has been actively studied in speech recognition since 1960s and increasingly used in many other fields. However, its application to machine condition monitoring has been very limited. HMM is not only very accurate and robust in analyzing signals but also can be a very powerful method in predicting a trend hidden in the signal. In this paper, the general idea of HMM is described and algorithm of continuous HMM (CHMM) has been tuned to be used in mechanical signal analysis and applied to ball bearing condition monitoring. The results show CHMM's big potential as an intelligent condition monitoring tool based on its accuracy, robustness. The increasing popularity of HMM is based on two facts; rich mathematical structure and proven accuracy on critical applications. It has a doubly embedded stochastic process with an underlying stochastic process that can be observed through another set of stochastic processes. This structure of HMM is useful for modeling a sequence that does not look like a stochastic process. Although it has become popular in various areas like bioscience and image processing, its use in mechanical engineering field has been very limited and rare in condition monitoring.