Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
7195084 | Reliability Engineering & System Safety | 2018 | 33 Pages |
Abstract
A novel framework to fuse structural health monitoring (SHM) data from different in-situ monitoring techniques is proposed aiming to develop a hyper-feature towards more effective prognostics. A state-of-the-art Non-Homogenous Hidden Semi Markov Model (NHHSMM) is utilized to model the damage accumulation of composite structures, subjected to fatigue loading, and estimate the remaining useful life (RUL) using conventional as well as fused SHM data. Acoustic Emission (AE) and Digital Image Correlation (DIC) are the selected in-situ SHM techniques. The proposed methodology is applied to open hole carbon/epoxy specimens under fatigue loading. RUL estimations utilizing features extracted from each SHM technique and after data fusion are compared, via established and newly proposed prognostic performance metrics.
Related Topics
Physical Sciences and Engineering
Engineering
Mechanical Engineering
Authors
Nick Eleftheroglou, Dimitrios Zarouchas, Theodoros Loutas, Rene Alderliesten, Rinze Benedictus,