EconPapers    
Economics at your fingertips  
 

Trustworthy Bayesian deep learning framework for uncertainty quantification and confidence calibration: Application in machinery fault diagnosis

Hao Li, Jinyang Jiao, Zongyang Liu, Jing Lin, Tian Zhang and Hanyang Liu

Reliability Engineering and System Safety, 2025, vol. 255, issue C

Abstract: Reliable and accurate machinery fault diagnosis is crucial for ensuring operational safety and reducing downtime in industrial settings. Traditional intelligent diagnosis methods only focus on improving the accuracy of in-distribution samples, but neglect the trustworthiness evaluation of diagnosis results. To address these issues, this paper developed a novel trustworthy machinery fault diagnosis (TMFD) method, which integrates Bayesian deep learning techniques with model calibration strategies. Specifically, TMFD regards a Bayesian convolutional neural network framework as the backbone. Then, we introduce α-divergence to facilitate the decomposition and quantification of epistemic uncertainty and aleatoric uncertainty, ultimately achieving out-of-distribution sample detection through epistemic uncertainty. Then, the ante-calibration loss constraint and the compositional post-calibration operation are jointly applied to promote data-efficient and high expressive calibration for in-distribution sample diagnosis confidence. Finally, TMFD is validated using three experimental datasets, demonstrating its effectiveness and robustness in machinery fault diagnosis.

Keywords: Trustworthy; Bayesian deep learning; Uncertainty quantification; Model calibration; Machinery fault diagnosis (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0951832024007282
Full text for ScienceDirect subscribers only

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:eee:reensy:v:255:y:2025:i:c:s0951832024007282

DOI: 10.1016/j.ress.2024.110657

Access Statistics for this article

Reliability Engineering and System Safety is currently edited by Carlos Guedes Soares

More articles in Reliability Engineering and System Safety from Elsevier
Bibliographic data for series maintained by Catherine Liu ().

 
Page updated 2025-05-25
Handle: RePEc:eee:reensy:v:255:y:2025:i:c:s0951832024007282