Towards bearing failure prognostics: a practical comparison between data-driven methods for industrial applications
- PDF / 1,833,196 Bytes
- 12 Pages / 595.22 x 842 pts (A4) Page_size
- 72 Downloads / 171 Views
DOI 10.1007/s12206-020-0908-7
Journal of Mechanical Science and Technology 34 (10) 2020 Original Article DOI 10.1007/s12206-020-0908-7 Keywords: · Bearing failure prognostics · Deep belief networks · Gaussian process regression · Health indicator construction · Monotonicity
Correspondence to: Jang-Wook Hur [email protected]
Citation: Akpudo, U. E., Hur, J.-W. (2020). Towards bearing failure prognostics: a practical comparison between data-driven methods for industrial applications. Journal of Mechanical Science and Technology 34 (10) (2020) ?~?. http://doi.org/10.1007/s12206-020-0908-7
Received March 20th, 2020 Revised
June 8th, 2020
Accepted July 21st, 2020 † Recommended by Editor Chongdu Cho
Towards bearing failure prognostics: a practical comparison between datadriven methods for industrial applications Ugochukwu Ejike Akpudo and Jang-Wook Hur Department of Mechanical Systems Engineering, Kumoh National Institute of Technology, 61 Daehak-ro (yangho-dong), Gumi, Gyeongbuk 39177, Korea
Abstract
Research studies on data-driven approaches to rotating components and rolling element bearing (REB) prognostics have recently witnessed a rapid increase. These datadriven methods rely on sensor data for condition monitoring and degradation assessments; however, the problem of mining features from these sophisticated data using appropriate intelligent methods and choosing a practically reliable predictive model(s) has become a global concern. Vibration monitoring for REBs have over the years shown great effectiveness. Although monotonic statistical features serve as reliable health indicators (HIs), relying on a single feature for optimal bearing degradation assessment is inefficient. By fusing highly monotonic features using appropriate methods, a more reliable HI can be constructed and from this, various degradation states/stages and time to start prediction (TSP) can be identified by mapping known failure modes/degradation states to cluster points from clustering algorithms. Emphatically, the choice of regression algorithms for prognostics poses more concern as engineers and data scientists are faced with choosing between Bayessian machine learning (ML) and deep learning (DL) methods. This study presents a methodology for constructing a reliable HI for bearing prognostics, choosing a reliable TSP, and provides a comparison between ML and DL methods for bearing prognostics. As representatives of both domains, the Gaussian process regression (GPR) and the deep belief network (DBN) are introduced and compared. The results provide a reliable paradigm for prognosible feature representation for REBs and for choosing between both domains while considering their dependencies, efficiencies, and deficiencies.
1. Introduction
© The Korean Society of Mechanical Engineers and Springer-Verlag GmbH Germany, part of Springer Nature 2020
The problem of predicting/extending the useful life of systems has become pertinent in many areas of science and engineering. As a result, adequate predictive maintenance practices for ensuri
Data Loading...
