RUL Prediction for Individual Units Based on Condition Monitoring Signals With a Change Point

In this article, we propose a method to predict the remaining useful life (RUL) for individual units based on condition monitoring signals with a change point. In this work, we assume the units are subject to hard failure. The existence of a sudden change point in the condition monitoring signal ind...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on reliability Vol. 64; no. 1; pp. 182 - 196
Main Authors Junbo Son, Yilu Zhang, Sankavaram, Chaitanya, Shiyu Zhou
Format Journal Article
LanguageEnglish
Published IEEE 01.03.2015
Subjects
Batteries
Change point
Condition monitoring
Data models
hard failure
Hazards
joint prognostic model
Joints
Prognostics and health management
remaining useful life prediction
Vectors
Online AccessGet full text

Cover

More Information
Summary:In this article, we propose a method to predict the remaining useful life (RUL) for individual units based on condition monitoring signals with a change point. In this work, we assume the units are subject to hard failure. The existence of a sudden change point in the condition monitoring signal indicates an increase of the probability of system failure. Therefore, this information should be considered in the RUL prediction. In the proposed method, an extended form of the joint prognostic model (JPM) considering a change point (JPM-C) is proposed, and the change point is detected according to the concordance correlation coefficient (CCC). The advantageous features of the proposed method have been shown through a numerical simulation, and a case study of the battery useful life prediction.
ISSN:0018-9529
1558-1721
DOI:10.1109/TR.2014.2355531