Uncertainty-aware Deep Learning: A Promising Tool for Trustworthy Fault Diagnosis

doi:10.1109/JAS.2024.124290

CASIA OpenIR > 学术期刊 > IEEE/CAA Journal of Automatica Sinica

	Uncertainty-aware Deep Learning: A Promising Tool for Trustworthy Fault Diagnosis
	Jiaxin Ren; Jingcheng Wen; Zhibin Zhao; Ruqiang Yan; Xuefeng Chen; Asoke K. Nandi
发表期刊	IEEE/CAA Journal of Automatica Sinica
ISSN	2329-9266
	2024
卷号	11 期号:6 页码:1317-1330
摘要	Recently, intelligent fault diagnosis based on deep learning has been extensively investigated, exhibiting state-of-the-art performance. However, the deep learning model is often not truly trusted by users due to the lack of interpretability of “black box”, which limits its deployment in safety-critical applications. A trusted fault diagnosis system requires that the faults can be accurately diagnosed in most cases, and the human in the decision-making loop can be found to deal with the abnormal situation when the models fail. In this paper, we explore a simplified method for quantifying both aleatoric and epistemic uncertainty in deterministic networks, called SAEU. In SAEU, Multivariate Gaussian distribution is employed in the deep architecture to compensate for the shortcomings of complexity and applicability of Bayesian neural networks. Based on the SAEU, we propose a unified uncertainty-aware deep learning framework (UU-DLF) to realize the grand vision of trustworthy fault diagnosis. Moreover, our UU-DLF effectively embodies the idea of “humans in the loop”, which not only allows for manual intervention in abnormal situations of diagnostic models, but also makes corresponding improvements on existing models based on traceability analysis. Finally, two experiments conducted on the gearbox and aero-engine bevel gears are used to demonstrate the effectiveness of UU-DLF and explore the effective reasons behind.
关键词	Out-of-distribution detection traceability analysis trustworthy fault diagnosis uncertainty quantification
DOI	10.1109/JAS.2024.124290
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/56451
专题	学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式 GB/T 7714	Jiaxin Ren,Jingcheng Wen,Zhibin Zhao,et al. Uncertainty-aware Deep Learning: A Promising Tool for Trustworthy Fault Diagnosis[J]. IEEE/CAA Journal of Automatica Sinica,2024,11(6):1317-1330.
APA	Jiaxin Ren,Jingcheng Wen,Zhibin Zhao,Ruqiang Yan,Xuefeng Chen,&Asoke K. Nandi.(2024).Uncertainty-aware Deep Learning: A Promising Tool for Trustworthy Fault Diagnosis.IEEE/CAA Journal of Automatica Sinica,11(6),1317-1330.
MLA	Jiaxin Ren,et al."Uncertainty-aware Deep Learning: A Promising Tool for Trustworthy Fault Diagnosis".IEEE/CAA Journal of Automatica Sinica 11.6(2024):1317-1330.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
JAS-2023-1373.pdf（16165KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载