Home > Research > Publications & Outputs > A Two-Stage Approach for the Remaining Useful L...

Research

Associated organisational units

Links

Text available via DOI:

Keywords

View graph of relations

A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks. / Xia, Min; Li, Teng; Shu, Tongxin et al.
In: IEEE Transactions on Industrial Informatics, Vol. 15, No. 6, 8454498, 01.06.2019, p. 3703-3711.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Xia, M, Li, T, Shu, T, Wan, J, De Silva, CW & Wang, Z 2019, 'A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks', IEEE Transactions on Industrial Informatics, vol. 15, no. 6, 8454498, pp. 3703-3711. https://doi.org/10.1109/TII.2018.2868687

APA

Xia, M., Li, T., Shu, T., Wan, J., De Silva, C. W., & Wang, Z. (2019). A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks. IEEE Transactions on Industrial Informatics, 15(6), 3703-3711. Article 8454498. https://doi.org/10.1109/TII.2018.2868687

Vancouver

Xia M, Li T, Shu T, Wan J, De Silva CW, Wang Z. A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks. IEEE Transactions on Industrial Informatics. 2019 Jun 1;15(6):3703-3711. 8454498. Epub 2018 Sept 4. doi: 10.1109/TII.2018.2868687

Author

Xia, Min ; Li, Teng ; Shu, Tongxin et al. / A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks. In: IEEE Transactions on Industrial Informatics. 2019 ; Vol. 15, No. 6. pp. 3703-3711.

Bibtex

@article{40ef5e53e8fb49008c73ff7adc4ea9b2,
title = "A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks",
abstract = "The degradation of bearings plays a key role in the failures of industrial machinery. Prognosis of bearings is critical in adopting an optimal maintenance strategy to reduce the overall cost and to avoid unwanted downtime or even casualties by estimating the remaining useful life (RUL) of the bearings. Traditional data-driven approaches of RUL prediction rely heavily on manual feature extraction and selection using human expertise. This paper presents an innovative two-stage automated approach to estimate the RUL of bearings using deep neural networks (DNNs). A denoising autoencoder-based DNN is used to classify the acquired signals of the monitored bearings into different degradation stages. Representative features are extracted directly from the raw signal by training the DNN. Then, regression models based on shallow neural networks are constructed for each health stage. The final RUL result is obtained by smoothing the regression results from different models. The proposed approach has achieved satisfactory prediction performance for a real bearing degradation dataset with different working conditions.",
keywords = "Bearings, deep neural networks (DNNs), prognosis, remaining useful life (RUL) prediction",
author = "Min Xia and Teng Li and Tongxin Shu and Jiafu Wan and {De Silva}, {Clarence W.} and Zhongren Wang",
year = "2019",
month = jun,
day = "1",
doi = "10.1109/TII.2018.2868687",
language = "English",
volume = "15",
pages = "3703--3711",
journal = "IEEE Transactions on Industrial Informatics",
issn = "1551-3203",
publisher = "IEEE Computer Society",
number = "6",

}

RIS

TY - JOUR

T1 - A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks

AU - Xia, Min

AU - Li, Teng

AU - Shu, Tongxin

AU - Wan, Jiafu

AU - De Silva, Clarence W.

AU - Wang, Zhongren

PY - 2019/6/1

Y1 - 2019/6/1

N2 - The degradation of bearings plays a key role in the failures of industrial machinery. Prognosis of bearings is critical in adopting an optimal maintenance strategy to reduce the overall cost and to avoid unwanted downtime or even casualties by estimating the remaining useful life (RUL) of the bearings. Traditional data-driven approaches of RUL prediction rely heavily on manual feature extraction and selection using human expertise. This paper presents an innovative two-stage automated approach to estimate the RUL of bearings using deep neural networks (DNNs). A denoising autoencoder-based DNN is used to classify the acquired signals of the monitored bearings into different degradation stages. Representative features are extracted directly from the raw signal by training the DNN. Then, regression models based on shallow neural networks are constructed for each health stage. The final RUL result is obtained by smoothing the regression results from different models. The proposed approach has achieved satisfactory prediction performance for a real bearing degradation dataset with different working conditions.

AB - The degradation of bearings plays a key role in the failures of industrial machinery. Prognosis of bearings is critical in adopting an optimal maintenance strategy to reduce the overall cost and to avoid unwanted downtime or even casualties by estimating the remaining useful life (RUL) of the bearings. Traditional data-driven approaches of RUL prediction rely heavily on manual feature extraction and selection using human expertise. This paper presents an innovative two-stage automated approach to estimate the RUL of bearings using deep neural networks (DNNs). A denoising autoencoder-based DNN is used to classify the acquired signals of the monitored bearings into different degradation stages. Representative features are extracted directly from the raw signal by training the DNN. Then, regression models based on shallow neural networks are constructed for each health stage. The final RUL result is obtained by smoothing the regression results from different models. The proposed approach has achieved satisfactory prediction performance for a real bearing degradation dataset with different working conditions.

KW - Bearings

KW - deep neural networks (DNNs)

KW - prognosis

KW - remaining useful life (RUL) prediction

U2 - 10.1109/TII.2018.2868687

DO - 10.1109/TII.2018.2868687

M3 - Journal article

AN - SCOPUS:85052869973

VL - 15

SP - 3703

EP - 3711

JO - IEEE Transactions on Industrial Informatics

JF - IEEE Transactions on Industrial Informatics

SN - 1551-3203

IS - 6

M1 - 8454498

ER -