Prognosis based on Multi-branch Hidden semi-Markov Models: A case study
Résumé
This paper proposes a multi-branch model to deal with Remaining Useful Life(RUL) estimation problem in the case where several deterioration modes co-exist within a singlecomponent. By basing on Hidden semi-Markov Models (HsMM), the component is supposed topass through some discrete and unobservable health states until it fails. The rate and the mannerof these state transitions, however, depend on the mode of deterioration that is actually active.We show that by taking into account the co-existence of dierent deterioration modes, the multi-branch model can help to improve prognosis results, which is essential for the implementationof a predictive maintenance. A practical case study is investigated to evaluate the advantagesof the proposed model.Furthermore, the comparison shows that the condition-based inspection maintenance is better than theperiodic inspection maintenance.