Abstract
Degradation assessment plays a significant role in increasing and managing the reliability and safety of mechanical systems, especially for key components. Hence, Health Index (HI) construction is a research field of interest. In conventional HI construction methods, performance features have to be selected manually based on experience and expert knowledge. This is a time-consuming procedure requiring a detailed understanding of the component. Furthermore, outliers usually exist in any HI constructed, and these can result in false alarms when HIs are subsequently used. To solve those problems, a new 'end-to-end' methodology, which combines Deep Convolutional Inner-Ensemble Learning (DCIEL) with an Outlier Removal method, is proposed for the degradation assessment of roller bearings. In the DCIEL algorithm, an inner-ensemble structure including multiple Deep Learning (DL) blocks is used to extract features directly from raw vibrational signals obtained from bearings. A novel DL block including two convolution layers and one nonlinear pooling layer is proposed. The obtained features are mapped into the HI using a Global Average layer, an Averaging layer, and a Logistic Regression layer. Finally, a novel outlier removal method, based on sliding thresholds, is proposed in order to detect and remove outliers in the constructed HIs. The effectiveness of the proposed method is verified using an open-source bearing health dataset. The proposed method demonstrates significant advantages across multiple HI assessment metrics in comparison with different DL blocks and commonly used HI construction methods.
Original language | English |
---|---|
Title of host publication | Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019 |
Editors | Chuan Li, Jose Valente de Oliveira, Ping Ding, Ping Ding, Diego Cabrera |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
Pages | 315-319 |
Number of pages | 5 |
ISBN (Electronic) | 9781728103297 |
DOIs | |
Publication status | Published - May 2019 |
Event | 2019 Prognostics and System Health Management Conference, PHM-Paris 2019 - Paris, France Duration: 2 May 2019 → 5 May 2019 |
Publication series
Name | Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019 |
---|
Conference
Conference | 2019 Prognostics and System Health Management Conference, PHM-Paris 2019 |
---|---|
Country/Territory | France |
City | Paris |
Period | 2/05/19 → 5/05/19 |
Bibliographical note
Publisher Copyright:© 2019 IEEE.
Keywords
- Bearing
- Deep learning
- Degradation assessment
- Inner ensemble structure
- Outlier removal
ASJC Scopus subject areas
- Industrial and Manufacturing Engineering
- Mechanical Engineering
- Safety, Risk, Reliability and Quality
- Statistics, Probability and Uncertainty
- Energy Engineering and Power Technology
- Nuclear Energy and Engineering
- Civil and Structural Engineering
- Electrical and Electronic Engineering