Remaining Useful Life Prediction of Rolling Bearings Using PSR, JADE, and Extreme Learning Machine

Yongbin Liu, Bing He, Fang Liu, Siliang Lu, Yilei Zhao and Jiwen Zhao

Mathematical Problems in Engineering, 2016, vol. 2016, 1-13

Abstract:

Rolling bearings play a pivotal role in rotating machinery. The degradation assessment and remaining useful life (RUL) prediction of bearings are critical to condition-based maintenance. However, sensitive feature extraction still remains a formidable challenge. In this paper, a novel feature extraction method is introduced to obtain the sensitive features through phase space reconstitution (PSR) and joint with approximate diagonalization of Eigen-matrices (JADE). Firstly, the original features are extracted from bearing vibration signals in time and frequency domain. Secondly, the PSR is applied to embed the original features into high dimensional phase space. The between-class and within-class scatter ( ) are calculated to evaluate the feature sensitivity through the phase point distribution of different degradation stages and then different weights are assigned to the corresponding features based on the calculated . Thirdly, the JADE is employed to fuse the weighted features to obtain the advanced features which can better reflect the bearing degradation process. Finally, the advanced features are input into the extreme learning machine (ELM) to train the RUL prediction model. A set of experimental case studies are carried out to verify the effectiveness of the proposed method. The results show that the extracted advanced features can better reflect the degradation process compared to traditional features and could effectively predict the RUL of bearing.

Date: 2016
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://downloads.hindawi.com/journals/MPE/2016/8623530.pdf (application/pdf)
http://downloads.hindawi.com/journals/MPE/2016/8623530.xml (text/xml)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hin:jnlmpe:8623530

DOI: 10.1155/2016/8623530

Access Statistics for this article

More articles in Mathematical Problems in Engineering from Hindawi
Bibliographic data for series maintained by Mohamed Abdelhakeem ().