Home > Research > Publications & Outputs > Data-driven prognosis method using hybrid deep ...

Electronic data

  • manuscript

    Rights statement: This is the author’s version of a work that was accepted for publication in Applied Soft Computing. 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 Applied Soft Computing, 93, 2020 DOI: 10.1016/j.asoc.2020.106351

    Accepted author manuscript, 2.69 MB, PDF document

    Available under license: CC BY-NC-ND

Links

Text available via DOI:

View graph of relations

Data-driven prognosis method using hybrid deep recurrent neural network

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Data-driven prognosis method using hybrid deep recurrent neural network. / Xia, M.; Zheng, X.; Imran, M. et al.
In: Applied Soft Computing Journal, Vol. 93, 106351, 01.08.2020.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Xia, M, Zheng, X, Imran, M & Shoaib, M 2020, 'Data-driven prognosis method using hybrid deep recurrent neural network', Applied Soft Computing Journal, vol. 93, 106351. https://doi.org/10.1016/j.asoc.2020.106351

APA

Xia, M., Zheng, X., Imran, M., & Shoaib, M. (2020). Data-driven prognosis method using hybrid deep recurrent neural network. Applied Soft Computing Journal, 93, Article 106351. https://doi.org/10.1016/j.asoc.2020.106351

Vancouver

Xia M, Zheng X, Imran M, Shoaib M. Data-driven prognosis method using hybrid deep recurrent neural network. Applied Soft Computing Journal. 2020 Aug 1;93:106351. Epub 2020 May 13. doi: 10.1016/j.asoc.2020.106351

Author

Xia, M. ; Zheng, X. ; Imran, M. et al. / Data-driven prognosis method using hybrid deep recurrent neural network. In: Applied Soft Computing Journal. 2020 ; Vol. 93.

Bibtex

@article{17dc4ca933f8475ca85638adf04896cf,
title = "Data-driven prognosis method using hybrid deep recurrent neural network",
abstract = "Prognostics and health management (PHM) has attracted increasing attention in modern manufacturing systems to achieve accurate predictive maintenance that reduces production downtime and enhances system safety. Remaining useful life (RUL) prediction plays a crucial role in PHM by providing direct evidence for a cost-effective maintenance decision. With the advances in sensing and communication technologies, data-driven approaches have achieved remarkable progress in machine prognostics. This paper develops a novel data-driven approach to precisely estimate the remaining useful life of machines using a hybrid deep recurrent neural network (RNN). The long short-term memory (LSTM) layers and classical neural networks are combined in the deep structure to capture the temporal information from the sequential data. The sequential sensory data from multiple sensors data can be fused and directly used as input of the model. The extraction of handcrafted features that relies heavily on prior knowledge and domain expertise as required by traditional approaches is avoided. The dropout technique and decaying learning rate are adopted in the training process of the hybrid deep RNN structure to increase the learning efficiency. A comprehensive experimental study on a widely used prognosis dataset is carried out to show the outstanding effectiveness and superior performance of the proposed approach in RUL prediction.",
keywords = "Long short-term memory, Prognostics, Recurrent neural network, Remaining useful life prediction, Cost effectiveness, Manufacture, Multilayer neural networks, Systems engineering, Classical neural networks, Communication technologies, Maintenance decisions, Prognostics and health managements, Recurrent neural network (RNN), Remaining useful life predictions, Remaining useful lives, Traditional approaches, Deep neural networks",
author = "M. Xia and X. Zheng and M. Imran and M. Shoaib",
note = "This is the author{\textquoteright}s version of a work that was accepted for publication in Applied Soft Computing. 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 Applied Soft Computing, 93, 2020 DOI: 10.1016/j.asoc.2020.106351",
year = "2020",
month = aug,
day = "1",
doi = "10.1016/j.asoc.2020.106351",
language = "English",
volume = "93",
journal = "Applied Soft Computing Journal",
issn = "1568-4946",
publisher = "Elsevier Science B.V.",

}

RIS

TY - JOUR

T1 - Data-driven prognosis method using hybrid deep recurrent neural network

AU - Xia, M.

AU - Zheng, X.

AU - Imran, M.

AU - Shoaib, M.

N1 - This is the author’s version of a work that was accepted for publication in Applied Soft Computing. 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 Applied Soft Computing, 93, 2020 DOI: 10.1016/j.asoc.2020.106351

PY - 2020/8/1

Y1 - 2020/8/1

N2 - Prognostics and health management (PHM) has attracted increasing attention in modern manufacturing systems to achieve accurate predictive maintenance that reduces production downtime and enhances system safety. Remaining useful life (RUL) prediction plays a crucial role in PHM by providing direct evidence for a cost-effective maintenance decision. With the advances in sensing and communication technologies, data-driven approaches have achieved remarkable progress in machine prognostics. This paper develops a novel data-driven approach to precisely estimate the remaining useful life of machines using a hybrid deep recurrent neural network (RNN). The long short-term memory (LSTM) layers and classical neural networks are combined in the deep structure to capture the temporal information from the sequential data. The sequential sensory data from multiple sensors data can be fused and directly used as input of the model. The extraction of handcrafted features that relies heavily on prior knowledge and domain expertise as required by traditional approaches is avoided. The dropout technique and decaying learning rate are adopted in the training process of the hybrid deep RNN structure to increase the learning efficiency. A comprehensive experimental study on a widely used prognosis dataset is carried out to show the outstanding effectiveness and superior performance of the proposed approach in RUL prediction.

AB - Prognostics and health management (PHM) has attracted increasing attention in modern manufacturing systems to achieve accurate predictive maintenance that reduces production downtime and enhances system safety. Remaining useful life (RUL) prediction plays a crucial role in PHM by providing direct evidence for a cost-effective maintenance decision. With the advances in sensing and communication technologies, data-driven approaches have achieved remarkable progress in machine prognostics. This paper develops a novel data-driven approach to precisely estimate the remaining useful life of machines using a hybrid deep recurrent neural network (RNN). The long short-term memory (LSTM) layers and classical neural networks are combined in the deep structure to capture the temporal information from the sequential data. The sequential sensory data from multiple sensors data can be fused and directly used as input of the model. The extraction of handcrafted features that relies heavily on prior knowledge and domain expertise as required by traditional approaches is avoided. The dropout technique and decaying learning rate are adopted in the training process of the hybrid deep RNN structure to increase the learning efficiency. A comprehensive experimental study on a widely used prognosis dataset is carried out to show the outstanding effectiveness and superior performance of the proposed approach in RUL prediction.

KW - Long short-term memory

KW - Prognostics

KW - Recurrent neural network

KW - Remaining useful life prediction

KW - Cost effectiveness

KW - Manufacture

KW - Multilayer neural networks

KW - Systems engineering

KW - Classical neural networks

KW - Communication technologies

KW - Maintenance decisions

KW - Prognostics and health managements

KW - Recurrent neural network (RNN)

KW - Remaining useful life predictions

KW - Remaining useful lives

KW - Traditional approaches

KW - Deep neural networks

U2 - 10.1016/j.asoc.2020.106351

DO - 10.1016/j.asoc.2020.106351

M3 - Journal article

VL - 93

JO - Applied Soft Computing Journal

JF - Applied Soft Computing Journal

SN - 1568-4946

M1 - 106351

ER -