Machinery Faults Detection and Forecasting Using Hidden Markov Models

The present work describes an automatic procedure for diagnostics and prognostic issues, and its application to the evaluation of gearboxes residual lifetime. The Hidden Markov Models — HMM — technique has been used to create quasistationary and stationary models and to take advantages of the multiple sensor data acquisition architecture. At first, Markov models for diagnostics have been defined. The main advantage of the HMMs approach is that all vibration raw data measured by a multisensor architecture can be used without any preprocessing. An effort to adapt the HMMs technique to the prognostic issue has also been carried out. To create Markov Models suitable for prognostics, the Viterbi Algorithm has been used to define the best sequence of model states and to optimize residual useful lifetime computation. Finally, experimental results are discussed, which encourage further research efforts according to the proposed approach.