Home > Research > Publications & Outputs > Trustworthy and intelligent fault diagnosis wit...

Links

Text available via DOI:

View graph of relations

Trustworthy and intelligent fault diagnosis with effective denoising and evidential stacked GRU neural network

Research output: Contribution to Journal/MagazineJournal articlepeer-review

E-pub ahead of print

Standard

Trustworthy and intelligent fault diagnosis with effective denoising and evidential stacked GRU neural network. / Zhou, Hanting; Chen, Wenhe; Liu, Jing et al.
In: Journal of Intelligent Manufacturing, Vol. 35, No. 7, 12.10.2023, p. 3523-3542.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Zhou H, Chen W, Liu J, Cheng L, Xia M. Trustworthy and intelligent fault diagnosis with effective denoising and evidential stacked GRU neural network. Journal of Intelligent Manufacturing. 2023 Oct 12;35(7):3523-3542. Epub 2023 Oct 12. doi: 10.1007/s10845-023-02221-1

Author

Zhou, Hanting ; Chen, Wenhe ; Liu, Jing et al. / Trustworthy and intelligent fault diagnosis with effective denoising and evidential stacked GRU neural network. In: Journal of Intelligent Manufacturing. 2023 ; Vol. 35, No. 7. pp. 3523-3542.

Bibtex

@article{6ede525606a545a3ab3ea16887a91172,
title = "Trustworthy and intelligent fault diagnosis with effective denoising and evidential stacked GRU neural network",
abstract = "With the advances in Internet-of-Things and data mining technologies, deep learning-based approaches have been widely used for intelligent fault diagnosis of manufacturing assets. However, uncertainty caused by the non-stationary process data such as vibration signal and noise interference in practical working environments will greatly affect the performance and reliability of predictions. The present paper develops a trustworthy and intelligent fault diagnosis framework based on a two-stage joint denoising method and evidential neural networks. The proposed denoising method integrating the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and the independent component analysis (ICA) method can effectively reduce data uncertainty caused by noise interference. The stacked gated recurrent unit (SGRU) model has been incorporated into the evidential neural networks as a deep classifier. The proposed evidential SGRU (ESGRU) method can quantify the prediction uncertainty, which estimates the prediction trustworthiness. Predictive entropy and reliability diagrams are used as calibration methods to validate the effectiveness of uncertainty estimation. The proposed framework is validated by two case studies of rolling bearing fault diagnosis in variable noise conditions. Experimental results demonstrate that the proposed method can achieve a high denoising effect and provide reliable uncertainty prediction results which are significant for practical applications.",
keywords = "Evidence theory, Intelligent fault diagnosis, Joint denoising method, Stacked gated recurrent unit (SGRU) neural networks, Uncertainty estimation",
author = "Hanting Zhou and Wenhe Chen and Jing Liu and Longsheng Cheng and Min Xia",
year = "2023",
month = oct,
day = "12",
doi = "10.1007/s10845-023-02221-1",
language = "English",
volume = "35",
pages = "3523--3542",
journal = "Journal of Intelligent Manufacturing",
issn = "0956-5515",
publisher = "Springer",
number = "7",

}

RIS

TY - JOUR

T1 - Trustworthy and intelligent fault diagnosis with effective denoising and evidential stacked GRU neural network

AU - Zhou, Hanting

AU - Chen, Wenhe

AU - Liu, Jing

AU - Cheng, Longsheng

AU - Xia, Min

PY - 2023/10/12

Y1 - 2023/10/12

N2 - With the advances in Internet-of-Things and data mining technologies, deep learning-based approaches have been widely used for intelligent fault diagnosis of manufacturing assets. However, uncertainty caused by the non-stationary process data such as vibration signal and noise interference in practical working environments will greatly affect the performance and reliability of predictions. The present paper develops a trustworthy and intelligent fault diagnosis framework based on a two-stage joint denoising method and evidential neural networks. The proposed denoising method integrating the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and the independent component analysis (ICA) method can effectively reduce data uncertainty caused by noise interference. The stacked gated recurrent unit (SGRU) model has been incorporated into the evidential neural networks as a deep classifier. The proposed evidential SGRU (ESGRU) method can quantify the prediction uncertainty, which estimates the prediction trustworthiness. Predictive entropy and reliability diagrams are used as calibration methods to validate the effectiveness of uncertainty estimation. The proposed framework is validated by two case studies of rolling bearing fault diagnosis in variable noise conditions. Experimental results demonstrate that the proposed method can achieve a high denoising effect and provide reliable uncertainty prediction results which are significant for practical applications.

AB - With the advances in Internet-of-Things and data mining technologies, deep learning-based approaches have been widely used for intelligent fault diagnosis of manufacturing assets. However, uncertainty caused by the non-stationary process data such as vibration signal and noise interference in practical working environments will greatly affect the performance and reliability of predictions. The present paper develops a trustworthy and intelligent fault diagnosis framework based on a two-stage joint denoising method and evidential neural networks. The proposed denoising method integrating the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and the independent component analysis (ICA) method can effectively reduce data uncertainty caused by noise interference. The stacked gated recurrent unit (SGRU) model has been incorporated into the evidential neural networks as a deep classifier. The proposed evidential SGRU (ESGRU) method can quantify the prediction uncertainty, which estimates the prediction trustworthiness. Predictive entropy and reliability diagrams are used as calibration methods to validate the effectiveness of uncertainty estimation. The proposed framework is validated by two case studies of rolling bearing fault diagnosis in variable noise conditions. Experimental results demonstrate that the proposed method can achieve a high denoising effect and provide reliable uncertainty prediction results which are significant for practical applications.

KW - Evidence theory

KW - Intelligent fault diagnosis

KW - Joint denoising method

KW - Stacked gated recurrent unit (SGRU) neural networks

KW - Uncertainty estimation

U2 - 10.1007/s10845-023-02221-1

DO - 10.1007/s10845-023-02221-1

M3 - Journal article

VL - 35

SP - 3523

EP - 3542

JO - Journal of Intelligent Manufacturing

JF - Journal of Intelligent Manufacturing

SN - 0956-5515

IS - 7

ER -