Journal article
HMM-Based Joint Modeling of Condition Monitoring Signals and Failure Event Data for Prognosis
IEEE transactions on reliability, Vol.72(3), pp.878-888
09/2023
DOI: 10.1109/TR.2022.3193353
Abstract
Accurate estimation of remaining useful life (RUL) of a unit is critical to fulfill reliability commitments. In the presence of hard failures (i.e., absence of a predefined failure threshold), accurate prognosis of RUL using condition monitoring (CM) signals becomes challenging. To tackle this problem, we present a prognostic framework by jointly modeling CM signals and failure event data. Development of the presented method depends on the idea that while the unit operates, it continually degrades through a series of hidden states and the CM signals are functionally related to this hidden failure process. The unit fails once the hidden failure process reaches a dead state. Through this modeling, requirement of a failure threshold on CM signals is eliminated. We provide a modified expectation-maximization procedure to estimate parameters, and through a comprehensive set of numerical as well as real-world experiments, we demonstrate superior prognosis performance against some benchmark methods.
Details
- Title: Subtitle
- HMM-Based Joint Modeling of Condition Monitoring Signals and Failure Event Data for Prognosis
- Creators
- Akash Deep - University of Wisconsin–MadisonShiyu Zhou - University of Wisconsin–MadisonDharmaraj Veeramani - University of Wisconsin–MadisonYong Chen - University of Iowa
- Resource Type
- Journal article
- Publication Details
- IEEE transactions on reliability, Vol.72(3), pp.878-888
- Publisher
- IEEE
- DOI
- 10.1109/TR.2022.3193353
- ISSN
- 0018-9529
- eISSN
- 1558-1721
- Language
- English
- Electronic publication date
- 08/05/2022
- Date published
- 09/2023
- Academic Unit
- Industrial and Systems Engineering
- Record Identifier
- 9984281629302771
Metrics
5 Record Views