Collaborative Online RUL Prediction of Multiple Assets With Analytically Recursive Bayesian Inference

By using in situ health information, many existing studies for online remaining useful life (RUL) prediction adopt a stochastic process-based degradation model and a computation-intensive parameter estimation method for RUL prediction of a single operating asset. Nevertheless, it is common that ther...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on reliability Vol. 73; no. 1; pp. 506 - 520
Main Authors: Peng, Weiwen, Chen, Yuan, Xu, Ancha, Ye, Zhi-Sheng
Format: Journal Article
Language:English
Published: New York IEEE 01.03.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Bayes methods
Bayesian analysis
Bayesian method
Collaboration
collaborative learning
Computational modeling
Data models
Degradation
Federated learning
Mathematical models
online inference
Parameter estimation
Predictive models
remaining useful life (RUL)
Statistical inference
Stochastic processes
Wiener process
ISSN:0018-9529, 1558-1721
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:By using in situ health information, many existing studies for online remaining useful life (RUL) prediction adopt a stochastic process-based degradation model and a computation-intensive parameter estimation method for RUL prediction of a single operating asset. Nevertheless, it is common that there are multiple assets under operation, and it would be more statistically efficient to jointly update their RULs by allowing information sharing among them for model parameter estimation. To this end, we propose a collaborative RUL prediction framework with closed-form online update. The framework is a hybrid algorithm that combines the conjugate prior for part of the model parameters and a stochastic approximation to the rest parameters. With this framework, a recursive online Bayesian algorithm is developed to jointly update the model parameters and RUL prediction using data from multiple operating assets. The effectiveness of the proposed method is demonstrated through a simulation study and two real cases.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9529
1558-1721
DOI:10.1109/TR.2023.3295943