Skip to main content

Multivariate Relevance Vector Regression based Degradation Modeling and Remaining Useful Life Prediction

Wang, Xiuli, Jiang, Bin, Wu, Shaomin, Lu, Ningyun, Ding, Steven (2021) Multivariate Relevance Vector Regression based Degradation Modeling and Remaining Useful Life Prediction. IEEE Transactions on Industrial Electronics, . pp. 1-11. ISSN 0278-0046. (doi:10.1109/TIE.2021.3114724) (KAR id:91113)

PDF Author's Accepted Manuscript
Language: English
Download (1MB) Preview
[thumbnail of Kent_IEEE.pdf]
Preview
This file may not be suitable for users of assistive technology.
Request an accessible format
Official URL:
https://doi.org/10.1109/TIE.2021.3114724

Abstract

Relevance Vector Regression (RVR) is a useful tool for degradation modeling and Remaining Useful Life (RUL) prediction. However, most RVR models are for one-dimensional degradation processes and can only handle univariate observations.

This paper proposes a degradation path based RUL prediction framework using a dynamic Multivariate Relevance Vector Regression (MRVR) model. Specifically, a multi-step regression model is established for describing the degradation dynamics and extends the classical RVR into a multivariate one with consideration of the multivariate environment. The paper introduces a matrix Gaussian distribution based RVR approach and then estimates the hyperparameters with Nesterov's accelerated gradient method to avoid the exhausting re-estimation phenomenon in seeking analytical solutions. It further forecasts the degradation path for monitoring the degradation status. Based on the forecasted path, the RUL is predicted by the First Hitting Time (FHT) method. Finally, the proposed methods are illustrated by two case studies, one is presented in the paper and the other in the supplement, both of which investigate the capacitors' performance degradation in the traction systems of high-speed trains.

Item Type: Article
DOI/Identification number: 10.1109/TIE.2021.3114724
Subjects: H Social Sciences > HA Statistics > HA33 Management Science
Divisions: Divisions > Kent Business School - Division > Department of Analytics, Operations and Systems
Depositing User: Shaomin Wu
Date Deposited: 27 Oct 2021 09:59 UTC
Last Modified: 28 Oct 2021 15:25 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/91113 (The current URI for this page, for reference purposes)
Wu, Shaomin: https://orcid.org/0000-0001-9786-3213
  • Depositors only (login required):

Downloads

Downloads per month over past year