A deep learning-based approach for electrical equipment remaining useful life prediction
Tóm tắt
Electrical equipment maintenance is of vital importance to management companies. Efficient maintenance can significantly reduce business costs and avoid safety accidents caused by catastrophic equipment failures. In the current context, predictive maintenance (PdM) is becoming increasingly popular based on machine learning approaches, while its research on electrical equipment such as low-voltage contactors is in its infancy. The failure modes are mainly fusion welding and explosion, and a few are unable to switch on. In this study, a data-driven approach is proposed to predict the remaining useful life (RUL) of the low-voltage contactor. Firstly, the three-phase alternating voltage and current records the life of electrical equipment by tracking the number of times it has been operated. Secondly, the failure-relevant features are extracted by using the time domain, frequency domain, and wavelet methods. Then, a CNN-LSTM network is designed and used to train an electrical equipment RUL prediction model based on the extracted features. An experimental study based on ten datasets collected from low-voltage AC contactors reveals that the proposed method shows merits in comparison with the prevailing deep learning algorithms in terms of MAE and RMSE.
Tài liệu tham khảo
citation_journal_title=Comput. Ind. Eng.; citation_title=An overview of time-based and condition-based maintenance in industrial application; citation_author=R. Ahmad, S. Kamaruddin; citation_volume=63; citation_issue=1; citation_publication_date=2012; citation_pages=135-149; citation_doi=10.1016/j.cie.2012.02.002; citation_id=CR1
P. Andersson, L.-G. Mattsson, Service innovations enabled by the “internet of things”. IMP J. (2015)
citation_journal_title=Mech. Syst. Signal Process.; citation_title=Machinery health prognostics: a systematic review from data acquisition to RUL prediction; citation_author=Y. Lei, N. Li, L. Guo, N. Li, T. Yan, J. Lin; citation_volume=104; citation_publication_date=2018; citation_pages=799-834; citation_doi=10.1016/j.ymssp.2017.11.016; citation_id=CR3
M. Haarman, M. Mulders, C. Vassiliadis, Predictive maintenance 4.0: predict the unpredictable. PwC and Mainnovation 4 (2017)
C. Chen, Y. Liu, X. Sun, S. Wang, C.D. Cairano-Gilfedder, S. Titmus, A.A. Syntetos, Reliability analysis using deep learning, in ASME IDETC-CIE (ASME, Quebec, Canada)
citation_title=Predictive maintenance of photovoltaic panels via deep learning; citation_inbook_title=IEEE Data Science Workshop (DSW); citation_publication_date=2018; citation_id=CR6; citation_author=T. Huuhtanen; citation_author=A. Jung
citation_journal_title=IEEE Access; citation_title=Remaining useful life estimation of BLDC motor considering voltage degradation and attention-based neural network; citation_author=T.A. Shifat, H. Jang-Wook; citation_volume=8; citation_publication_date=2020; citation_pages=168414-168428; citation_doi=10.1109/ACCESS.2020.3023335; citation_id=CR7
citation_journal_title=Measurement; citation_title=Transfer learning for remaining useful life prediction of multi-conditions bearings based on bidirectional-GRU network; citation_author=Y. Cao, M. Jia, P. Ding, Y. Ding; citation_volume=178; citation_publication_date=2021; citation_doi=10.1016/j.measurement.2021.109287; citation_id=CR8
citation_journal_title=Intell. Auton. Syst.; citation_title=An attention enhanced dilated CNN approach for cross-axis industrial robotics fault diagnosis; citation_author=Y. Liu, C. Chen, T. Wang, L. Cheng; citation_volume=2; citation_issue=1; citation_publication_date=2022; citation_pages=1-11; citation_doi=10.1007/s43684-022-00030-6; citation_id=CR9
citation_journal_title=J. Adv. Res.; citation_title=A review on modern defect detection models using DCNNs–deep convolutional neural networks; citation_author=A.-A. Tulbure, A.-A. Tulbure, E.-H. Dulf; citation_volume=35; citation_publication_date=2022; citation_pages=33-48; citation_doi=10.1016/j.jare.2021.03.015; citation_id=CR10
citation_journal_title=IEEE/ASME Trans. Mechatron.; citation_title=A deep learning-based remaining useful life prediction approach for bearings; citation_author=C. Cheng, G. Ma, Y. Zhang, M. Sun, F. Teng, H. Ding, Y. Yuan; citation_volume=25; citation_issue=3; citation_publication_date=2020; citation_pages=1243-1254; citation_doi=10.1109/TMECH.2020.2971503; citation_id=CR11
citation_journal_title=Electronics; citation_title=A state-of-the-art survey on deep learning theory and architectures; citation_author=M.Z. Alom, T.M. Taha, C. Yakopcic, S. Westberg, P. Sidike, M.S. Nasrin, M. Hasan, B.C. Essen, A.A. Awwal, V.K. Asari; citation_volume=8; citation_issue=3; citation_publication_date=2019; citation_pages=292; citation_doi=10.3390/electronics8030292; citation_id=CR12
citation_journal_title=IEEE Access; citation_title=Industrial big data analysis in smart factory: current status and research strategies; citation_author=X. Xu, Q. Hua; citation_volume=5; citation_publication_date=2017; citation_pages=17543-17551; citation_doi=10.1109/ACCESS.2017.2741105; citation_id=CR13
citation_journal_title=NTUEE, Taiwan; citation_title=A tutorial of the wavelet transform; citation_author=L. Chun-Lin; citation_volume=21; citation_publication_date=2010; citation_pages=22; citation_id=CR14
citation_journal_title=Proc. Inst. Mech. Eng., B J. Eng. Manuf.; citation_title=Predictive maintenance, its implementation and latest trends; citation_author=S. Selcuk; citation_volume=231; citation_issue=9; citation_publication_date=2017; citation_pages=1670-1679; citation_doi=10.1177/0954405415601640; citation_id=CR15
citation_journal_title=IEEE Access; citation_title=Remaining useful life prediction for lithium-ion battery: a deep learning approach; citation_author=L. Ren, L. Zhao, S. Hong, S. Zhao, H. Wang, L. Zhang; citation_volume=6; citation_publication_date=2018; citation_pages=50587-50598; citation_doi=10.1109/ACCESS.2018.2858856; citation_id=CR16
citation_journal_title=IEEE Trans. Reliab.; citation_title=An enhanced deep learning-based fusion prognostic method for RUL prediction; citation_author=C.-G. Huang, X. Yin, H.-Z. Huang, Y.-F. Li; citation_volume=69; citation_issue=3; citation_publication_date=2019; citation_pages=1097-1109; citation_doi=10.1109/TR.2019.2948705; citation_id=CR17
citation_title=Forecasting faults of industrial equipment using machine learning classifiers; citation_inbook_title=Innovations in Intelligent Systems and Applications (INISTA); citation_publication_date=2018; citation_id=CR18; citation_author=N. Kolokas; citation_author=T. Vafeiadis; citation_author=D. Ioannidis; citation_author=D. Tzovaras
citation_journal_title=Eur. J. Ind. Eng.; citation_title=Improving reliability of repairable systems using preventive maintenance and time-between-failures monitoring; citation_author=I. Alsyouf, M. Shamsuzzaman, G. Abdelrahman, M. Al-Taha; citation_volume=10; citation_issue=5; citation_publication_date=2016; citation_pages=596-617; citation_doi=10.1504/EJIE.2016.078798; citation_id=CR19
citation_journal_title=J. Qual. Maint. Eng.; citation_title=Maintenance management: literature review and directions; citation_author=A. Garg, S. Deshmukh; citation_volume=12; citation_issue=3; citation_publication_date=2006; citation_pages=205-238; citation_doi=10.1108/13552510610685075; citation_id=CR20
citation_journal_title=IEEE Trans. Instrum. Meas.; citation_title=Prognosis of defect propagation based on recurrent neural networks; citation_author=A. Malhi, R. Yan, R.X. Gao; citation_volume=60; citation_issue=3; citation_publication_date=2011; citation_pages=703-711; citation_doi=10.1109/TIM.2010.2078296; citation_id=CR21
citation_title=A generic indirect deep learning approach for multisensor degradation modeling; citation_inbook_title=IEEE Transactions on Automation Science and Engineering; citation_publication_date=2021; citation_id=CR22; citation_author=D. Wang; citation_author=K. Liu; citation_author=X. Zhang
citation_journal_title=IEEE Access; citation_title=A novel predictive maintenance method based on deep adversarial learning in the intelligent manufacturing system; citation_author=C. Liu, D. Tang, H. Zhu, Q. Nie; citation_volume=9; citation_publication_date=2021; citation_pages=49557-49575; citation_doi=10.1109/ACCESS.2021.3069256; citation_id=CR23
citation_journal_title=IEEE Access; citation_title=A review on deep learning applications in prognostics and health management; citation_author=L. Zhang, J. Lin, B. Liu, Z. Zhang, X. Yan, M. Wei; citation_volume=7; citation_publication_date=2019; citation_pages=162415-162438; citation_doi=10.1109/ACCESS.2019.2950985; citation_id=CR24
citation_journal_title=Reliab. Eng. Syst. Saf.; citation_title=Fault prediction of bearings based on LSTM and statistical process analysis; citation_author=J. Liu, C. Pan, F. Lei, D. Hu, H. Zuo; citation_volume=214; citation_publication_date=2021; citation_doi=10.1016/j.ress.2021.107646; citation_id=CR25
citation_journal_title=Reliab. Eng. Syst. Saf.; citation_title=An integrated deep learning-based approach for automobile maintenance prediction with GIS data; citation_author=C. Chen, Y. Liu, X. Sun, C. Cairano-Gilfedder, S. Titmus; citation_volume=216; citation_publication_date=2021; citation_doi=10.1016/j.ress.2021.107919; citation_id=CR26
citation_journal_title=IEEE Trans. Instrum. Meas.; citation_title=State-of-the-art predictive maintenance techniques; citation_author=H.M. Hashemian; citation_volume=60; citation_issue=1; citation_publication_date=2010; citation_pages=226-236; citation_doi=10.1109/TIM.2010.2047662; citation_id=CR27
citation_journal_title=Measurement; citation_title=A robust construction of normalized CNN for online intelligent condition monitoring of rolling bearings considering variable working conditions and sources; citation_author=B. Zhao, X. Zhang, Z. Zhan, Q. Wu; citation_volume=174; citation_publication_date=2021; citation_doi=10.1016/j.measurement.2021.108973; citation_id=CR28
citation_journal_title=Reliab. Eng. Syst. Saf.; citation_title=Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction; citation_author=X. Li, W. Zhang, Q. Ding; citation_volume=182; citation_publication_date=2019; citation_pages=208-218; citation_doi=10.1016/j.ress.2018.11.011; citation_id=CR29
citation_journal_title=Mech. Syst. Signal Process.; citation_title=Deep separable convolutional network for remaining useful life prediction of machinery; citation_author=B. Wang, Y. Lei, N. Li, T. Yan; citation_volume=134; citation_publication_date=2019; citation_doi=10.1016/j.ymssp.2019.106330; citation_id=CR30
citation_title=Deep learning approaches to remaining useful life prediction: a survey; citation_inbook_title=IEEE Symposium Series on Computational Intelligence (SSCI); citation_publication_date=2021; citation_id=CR31; citation_author=L. Cummins; citation_author=B. Killen; citation_author=K. Thomas; citation_author=P. Barrett; citation_author=S. Rahimi; citation_author=M. Seale
citation_journal_title=J. Power Sources; citation_title=A novel health indicator for on-line lithium-ion batteries remaining useful life prediction; citation_author=Y. Zhou, M. Huang, Y. Chen, Y. Tao; citation_volume=321; citation_publication_date=2016; citation_pages=1-10; citation_doi=10.1016/j.jpowsour.2016.04.119; citation_id=CR32
citation_journal_title=IEEE Trans. Veh. Technol.; citation_title=Long short-term memory recurrent neural network for remaining useful life prediction of lithium-ion batteries; citation_author=Y. Zhang, R. Xiong, H. He, M.G. Pecht; citation_volume=67; citation_issue=7; citation_publication_date=2018; citation_pages=5695-5705; citation_doi=10.1109/TVT.2018.2805189; citation_id=CR33
citation_journal_title=IEEE Access; citation_title=Industrial big data analytics for prediction of remaining useful life based on deep learning; citation_author=H. Yan, J. Wan, C. Zhang, S. Tang, Q. Hua, Z. Wang; citation_volume=6; citation_publication_date=2018; citation_pages=17190-17197; citation_doi=10.1109/ACCESS.2018.2809681; citation_id=CR34
citation_journal_title=Comput. Netw.; citation_title=Towards smart factory for industry 4.0: a self-organized multi-agent system with big data based feedback and coordination; citation_author=S. Wang, J. Wan, D. Zhang, D. Li, C. Zhang; citation_volume=101; citation_publication_date=2016; citation_pages=158-168; citation_doi=10.1016/j.comnet.2015.12.017; citation_id=CR35