Home > Research > Publications & Outputs > Intelligent fault diagnosis of machinery using ...

Associated organisational unit

Electronic data

  • Manuscript Single-column

    Rights statement: This is the author’s version of a work that was accepted for publication in Reliability Engineering & System Safety. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Reliability Engineering & System Safety, 215, 2021 DOI: 10.1016/j.ress.2021.107938

    Accepted author manuscript, 1.21 MB, PDF document

    Available under license: CC BY-NC-ND

Links

Text available via DOI:

View graph of relations

Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning. / Xia, M.; Shao, H.; Williams, D. et al.

In: Reliability Engineering and System Safety, Vol. 215, 107938, 30.11.2021.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Xia, M, Shao, H, Williams, D, Lu, S, Shu, L & de Silva, CW 2021, 'Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning', Reliability Engineering and System Safety, vol. 215, 107938. https://doi.org/10.1016/j.ress.2021.107938

APA

Xia, M., Shao, H., Williams, D., Lu, S., Shu, L., & de Silva, C. W. (2021). Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning. Reliability Engineering and System Safety, 215, [107938]. https://doi.org/10.1016/j.ress.2021.107938

Vancouver

Xia M, Shao H, Williams D, Lu S, Shu L, de Silva CW. Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning. Reliability Engineering and System Safety. 2021 Nov 30;215:107938. Epub 2021 Jul 24. doi: 10.1016/j.ress.2021.107938

Author

Xia, M. ; Shao, H. ; Williams, D. et al. / Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning. In: Reliability Engineering and System Safety. 2021 ; Vol. 215.

Bibtex

@article{3042637f1d6545dcaccec6ddb19d1342,
title = "Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning",
abstract = "Digital twin (DT) is emerging as a key technology for smart manufacturing. The high fidelity DT model of the physical assets can produce system performance data that is close to reality, which provides remarkable opportunities for machine fault diagnosis when the measured fault condition data are insufficient. This paper presents an intelligent fault diagnosis framework for machinery based on DT and deep transfer learning. First, the DT model of the machine is built by establishing the simulation model and with further updating through continuously measured data from the physical asset. Second, all important machine conditions can be simulated from the built DT. Third, a new-type deep structure based on novel sparse de-noising auto-encoder (NSDAE) is developed and pre-trained with condition data from the source domain, as generated from the DT. Then, to achieve accurate machine fault diagnosis with possible variations in working conditions and system characteristics, the pre-trained NSDAE is fine-tuned using parameter transfer with only one sample from the target domain. The presented method is validated through a case study of triplex pump fault diagnosis. The experimental results demonstrate that the proposed method achieves intelligent fault diagnosis with a limited amount of measured data and outperforms other state-of-the-art data-driven methods. ",
keywords = "Deep transfer learning, Digital twin, Fault diagnosis, Novel sparse de-noising auto-encoder, Deep learning, E-learning, Fault detection, Machinery, Signal encoding, Autoencoders, Condition, De-noising, Faults diagnosis, Intelligent fault diagnosis, Machine fault diagnosis, Physical assets, Transfer learning, Failure analysis",
author = "M. Xia and H. Shao and D. Williams and S. Lu and L. Shu and {de Silva}, C.W.",
note = "This is the author{\textquoteright}s version of a work that was accepted for publication in Reliability Engineering & System Safety. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Reliability Engineering & System Safety, 215, 2021 DOI: 10.1016/j.ress.2021.107938",
year = "2021",
month = nov,
day = "30",
doi = "10.1016/j.ress.2021.107938",
language = "English",
volume = "215",
journal = "Reliability Engineering and System Safety",
issn = "0951-8320",
publisher = "Elsevier Limited",

}

RIS

TY - JOUR

T1 - Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning

AU - Xia, M.

AU - Shao, H.

AU - Williams, D.

AU - Lu, S.

AU - Shu, L.

AU - de Silva, C.W.

N1 - This is the author’s version of a work that was accepted for publication in Reliability Engineering & System Safety. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Reliability Engineering & System Safety, 215, 2021 DOI: 10.1016/j.ress.2021.107938

PY - 2021/11/30

Y1 - 2021/11/30

N2 - Digital twin (DT) is emerging as a key technology for smart manufacturing. The high fidelity DT model of the physical assets can produce system performance data that is close to reality, which provides remarkable opportunities for machine fault diagnosis when the measured fault condition data are insufficient. This paper presents an intelligent fault diagnosis framework for machinery based on DT and deep transfer learning. First, the DT model of the machine is built by establishing the simulation model and with further updating through continuously measured data from the physical asset. Second, all important machine conditions can be simulated from the built DT. Third, a new-type deep structure based on novel sparse de-noising auto-encoder (NSDAE) is developed and pre-trained with condition data from the source domain, as generated from the DT. Then, to achieve accurate machine fault diagnosis with possible variations in working conditions and system characteristics, the pre-trained NSDAE is fine-tuned using parameter transfer with only one sample from the target domain. The presented method is validated through a case study of triplex pump fault diagnosis. The experimental results demonstrate that the proposed method achieves intelligent fault diagnosis with a limited amount of measured data and outperforms other state-of-the-art data-driven methods.

AB - Digital twin (DT) is emerging as a key technology for smart manufacturing. The high fidelity DT model of the physical assets can produce system performance data that is close to reality, which provides remarkable opportunities for machine fault diagnosis when the measured fault condition data are insufficient. This paper presents an intelligent fault diagnosis framework for machinery based on DT and deep transfer learning. First, the DT model of the machine is built by establishing the simulation model and with further updating through continuously measured data from the physical asset. Second, all important machine conditions can be simulated from the built DT. Third, a new-type deep structure based on novel sparse de-noising auto-encoder (NSDAE) is developed and pre-trained with condition data from the source domain, as generated from the DT. Then, to achieve accurate machine fault diagnosis with possible variations in working conditions and system characteristics, the pre-trained NSDAE is fine-tuned using parameter transfer with only one sample from the target domain. The presented method is validated through a case study of triplex pump fault diagnosis. The experimental results demonstrate that the proposed method achieves intelligent fault diagnosis with a limited amount of measured data and outperforms other state-of-the-art data-driven methods.

KW - Deep transfer learning

KW - Digital twin

KW - Fault diagnosis

KW - Novel sparse de-noising auto-encoder

KW - Deep learning

KW - E-learning

KW - Fault detection

KW - Machinery

KW - Signal encoding

KW - Autoencoders

KW - Condition

KW - De-noising

KW - Faults diagnosis

KW - Intelligent fault diagnosis

KW - Machine fault diagnosis

KW - Physical assets

KW - Transfer learning

KW - Failure analysis

U2 - 10.1016/j.ress.2021.107938

DO - 10.1016/j.ress.2021.107938

M3 - Journal article

VL - 215

JO - Reliability Engineering and System Safety

JF - Reliability Engineering and System Safety

SN - 0951-8320

M1 - 107938

ER -