Reliable machine prognostic health management in the presence of missing data

Huang, Yu; Tang, Yufei; VanZwieten, James H.; Liu, Jianxun

doi:10.1002/cpe.5762

Reliable machine prognostic health management in the presence of missing data

Journal Article · Wed Apr 22 00:00:00 EDT 2020 · Concurrency and Computation. Practice and Experience

DOI:https://doi.org/10.1002/cpe.5762· OSTI ID:1986605

Huang, Yu ^[1]; ^[2]; VanZwieten, James H. ^[2]; Liu, Jianxun ^[3]

Florida Atlantic Univ., Boca Raton, FL (United States); Florida Atlantic University
Florida Atlantic Univ., Boca Raton, FL (United States)
Hunan University of Science and Technology (China)

Prognostics and health management enables the prediction of future degradation and remaining useful life (RUL) for in-service systems based on historical and contemporary data, showing promise for many practical applications. One major challenge for prognostics is the common occurrence of missing values in time-series data, often caused by disruptions in sensor communication or hardware/software failures. Another major concern is that the sufficient prior knowledge of critical component degradation with a clear failure threshold is often not readily available in practice. These issues can significantly hinder the application of advanced signal and data analysis methods and consequently degrade the health management performance. In this article, we propose a novel data-driven framework that is capable of providing accurate and reliable predictions of degradation and RUL. In this approach, one-hot health state indicators are appended to the historical time series so that the model learns end-of-life automatically. A modified gate recurrent unit based variational autoencoder is employed in generative adversarial networks to model the temporal irregularity of the incomplete time series. Furthermore, experiments on multivariate time-series datasets collected from real-world aeroengines verify that significant performance improvement can be achieved using the proposed model for robust long-term prognostics.

View Accepted Manuscript (DOE)

Research Organization:: Florida Atlantic Univ., Boca Raton, FL (United States)

Sponsoring Organization:: Key Research and Development Project of Hunan Province, China; National Science Foundation (NSF); USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Water Power Technologies Office

Grant/Contract Number:: EE0004200

OSTI ID:: 1986605

Journal Information:: Concurrency and Computation. Practice and Experience, Journal Name: Concurrency and Computation. Practice and Experience Journal Issue: 12 Vol. 34; ISSN 1532-0626

Publisher:: WileyCopyright Statement

Country of Publication:: United States

Language:: English

References (24)

Bayesian estimation and prediction for the transformed gamma degradation process Giorgio, Massimiliano; Guida, Maurizio; Postiglione, Fabio Quality and Reliability Engineering International, Vol. 34, Issue 7 https://doi.org/10.1002/qre.2329	journal	June 2018
Multiple imputation using chained equations: Issues and guidance for practice White, Ian R.; Royston, Patrick; Wood, Angela M. Statistics in Medicine, Vol. 30, Issue 4 https://doi.org/10.1002/sim.4067	journal	November 2010
Battery capacity degradation prediction using similarity recognition based on modified dynamic time warping Tao, Laifa; Lu, Chen; Yang, Chao Structural Control and Health Monitoring, Vol. 25, Issue 1 https://doi.org/10.1002/stc.2024	journal	May 2017
Missing value imputation: a review and analysis of the literature (2006–2017) Lin, Wei-Chao; Tsai, Chih-Fong Artificial Intelligence Review, Vol. 53, Issue 2 https://doi.org/10.1007/s10462-019-09709-4	journal	April 2019
An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring Tian, Zhigang Journal of Intelligent Manufacturing, Vol. 23, Issue 2 https://doi.org/10.1007/s10845-009-0356-9	journal	November 2009
Probabilistic neural network based categorical data imputation Nishanth, Kancherla Jonah; Ravi, Vadlamani Neurocomputing, Vol. 218 https://doi.org/10.1016/j.neucom.2016.08.044	journal	December 2016
A recurrent neural network based health indicator for remaining useful life prediction of bearings Guo, Liang; Li, Naipeng; Jia, Feng Neurocomputing, Vol. 240 https://doi.org/10.1016/j.neucom.2017.02.045	journal	May 2017
Remaining useful life estimation of engineered systems using vanilla LSTM neural networks Wu, Yuting; Yuan, Mei; Dong, Shaopeng Neurocomputing, Vol. 275 https://doi.org/10.1016/j.neucom.2017.05.063	journal	January 2018
Bidirectional handshaking LSTM for remaining useful life prediction Elsheikh, Ahmed; Yacout, Soumaya; Ouali, Mohamed-Salah Neurocomputing, Vol. 323 https://doi.org/10.1016/j.neucom.2018.09.076	journal	January 2019
Imputations of missing values using a tracking-removed autoencoder trained with incomplete data Lai, Xiaochen; Wu, Xia; Zhang, Liyong Neurocomputing, Vol. 366 https://doi.org/10.1016/j.neucom.2019.07.066	journal	November 2019
Remaining useful life estimation in prognostics using deep convolution neural networks Li, Xiang; Ding, Qian; Sun, Jian-Qiao Reliability Engineering & System Safety, Vol. 172 https://doi.org/10.1016/j.ress.2017.11.021	journal	April 2018
Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction Li, Xiang; Zhang, Wei; Ding, Qian Reliability Engineering & System Safety, Vol. 182 https://doi.org/10.1016/j.ress.2018.11.011	journal	February 2019
Nearest neighbor imputation of species-level, plot-scale forest structure attributes from LiDAR data Hudak, Andrew T.; Crookston, Nicholas L.; Evans, Jeffrey S. Remote Sensing of Environment, Vol. 112, Issue 5 https://doi.org/10.1016/j.rse.2007.10.009	journal	May 2008
An Adversarial Learning Approach for Machine Prognostic Health Management Huang, Yu; Tang, Yufei; VanZwieten, James 2019 International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS) https://doi.org/10.1109/HPBDIS.2019.8735480	conference	May 2019
Remaining Useful Life Estimation of Hydrokinetic Turbine Blades Using Power Signal Huang, Yu; Tang, Yufei; VanZwieten, James 2019 IEEE Power & Energy Society General Meeting (PESGM) https://doi.org/10.1109/PESGM40551.2019.8973840	conference	August 2019
Recurrent neural networks for remaining useful life estimation Heimes, Felix O. 2008 International Conference on Prognostics and Health Management https://doi.org/10.1109/PHM.2008.4711422	conference	October 2008
A Novel Framework for Gear Safety Factor Prediction Li, Jie; Liu, Song; He, Haibo IEEE Transactions on Industrial Informatics, Vol. 15, Issue 4 https://doi.org/10.1109/TII.2018.2868359	journal	April 2019
Diagnosing Rotating Machines With Weakly Supervised Data Using Deep Transfer Learning Li, Xiang; Zhang, Wei; Ding, Qian IEEE Transactions on Industrial Informatics, Vol. 16, Issue 3 https://doi.org/10.1109/TII.2019.2927590	journal	March 2020
Representation Learning: A Review and New Perspectives Bengio, Y.; Courville, A.; Vincent, P. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, Issue 8 https://doi.org/10.1109/TPAMI.2013.50	journal	August 2013
A fabrication history based strain-fatigue model for prediction of crack initiation in a radial loading wheel Zhao, Y.; Ma, M.; Qin, R. Fatigue & Fracture of Engineering Materials & Structures, Vol. 40, Issue 11 https://doi.org/10.1111/ffe.12607	journal	March 2017
Extracting and composing robust features with denoising autoencoders Vincent, Pascal; Larochelle, Hugo; Bengio, Yoshua Proceedings of the 25th international conference on Machine learning - ICML '08 https://doi.org/10.1145/1390156.1390294	conference	January 2008
Missing Data Analysis: Making It Work in the Real World Graham, John W. Annual Review of Psychology, Vol. 60, Issue 1 https://doi.org/10.1146/annurev.psych.58.110405.085530	journal	January 2009
SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient Yu, Lantao; Zhang, Weinan; Wang, Jun Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31, Issue 1 https://doi.org/10.1609/aaai.v31i1.10804	journal	February 2017
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches Cho, Kyunghyun; van Merrienboer, Bart; Bahdanau, Dzmitry Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation https://doi.org/10.3115/v1/W14-4012	conference	January 2014

Similar Records

Development and Validation of a Lifecycle-based Prognostics Architecture with Test Bed Validation

Technical Report · Wed Nov 05 23:00:00 EST 2014 · OSTI ID:1183744

A Prognostics and Health Management Framework for Wind

Conference · Mon Nov 04 23:00:00 EST 2019 · OSTI ID:1580483

Diagnostics and Prognostics Tools for Assessing Remaining Useful Life of Nuclear Power Plant Materials

Conference · Wed Nov 30 23:00:00 EST 2011 · OSTI ID:1113623

Related Subjects

96 KNOWLEDGE MANAGEMENT AND PRESERVATION
generative adversarial networks
missing data imputation
prognostics and health management
remaining useful life prediction

Reliable machine prognostic health management in the presence of missing data

Citation Formats

References (24)

Similar Records

Related Subjects