Towards a Hybrid Framework for Prognostics with Limited Run-to-Failure Data

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jun 27, 2024
Luc S. Keizers
Richard Loendersloot
Tiedo Tinga

Abstract

The introduction of cyber-physical systems with increased availability of sensor data creates a lot of research interest in prognostic algorithms for predictive maintenance. Although a lot of algorithms are successfully applied to benchmark case studies based on simulated data and experimental set-ups, deployment
in industry lags behind. From a comparison between three benchmark case studies with two real-world case studies based on prognostic metrics (monotonicity, prognosability and trendability), two main issues are observed: 1) the lack of run-to-failures and 2) low prognostic metrics due to a low signal-to-noise ratio of degradation trends, as a result of unexplained physical phenomena. To make prognostics feasible, a hybrid framework is proposed that focuses on improving system knowledge. The framework consists of a quantitative diagnostic assessments, guided by (modular) system models in which damage is induced. This quantitative damage assessment provides input for prognostics based on Bayesian filtering, enabling prognostics for assets in varying operational conditions. Implementation and validation of the framework requires investments, but modularity within the framework can accelerate development for new systems.

How to Cite

Keizers, L., Loendersloot, R., & Tinga, T. (2024). Towards a Hybrid Framework for Prognostics with Limited Run-to-Failure Data. PHM Society European Conference, 8(1), 12. https://doi.org/10.36001/phme.2024.v8i1.4017
Abstract 181 | PDF Downloads 103

##plugins.themes.bootstrap3.article.details##

Keywords

Prognostics, Hybrid Framework, Prognostic Metrics, Physics-of-Failure, Data Availability

References
Agogino, A., & Goebel, K. (2007). Milling data set. Retrieved from https://data.nasa.gov/Raw-Data/Milling-Wear/vjv9-9f3x/data

Alomari, Y., And´o, M., & Baptista, M. (2023). Advancing aircraft engine rul predictions: an interpretable integrated approach of feature engineering and aggregated feature importance. Scientific Reports, 13(1), 13:13466. doi: https://doi.org/10.1038/s41598-023-40315-1

Archard, J. (1953). Contact and rubbing of flat surfaces. Journal of Applied Physics, 24(8), 981 - 988. doi: https://doi.org/10.1063/1.1721448

Baral, T., Saraygord Afshari, S., & Liang, X. (2023). Residual life prediction of aluminum alloy plates under cyclic loading using an integrated prognosis method. Transactions of the Canadian Society for Mechanical Engineering, 47(5), 1-12. doi: https://doi.org/10.1139/tcsme-2023-0010

Borutzky, W. (2020, Jan). A hybrid bond graph model-based - data driven method for failure prognostic. Procedia Manufacturing, 42, 188-196. (International Conference on
Industry 4.0 and Smart Manufacturing (ISM 2019)) doi:https://doi.org/10.1016/j.promfg.2020.02.069

Bär, J. (2020). Crack detection and crack length measurement with the dc potential drop method–possibilities, challenges and new developments. Applied Sciences, 10(23), 8559. doi: https://doi.org/10.3390/app10238559

Calabrese, F., Regattieri, A., Bortolini, M., Gamberi, M., & Pilati, F. (2021). Predictive maintenance: A novel framework for a data-driven, semi-supervised, and partially online
prognostic health management application in industries. Applied Sciences, 11(8), 3380. doi: https://doi.org/10.3390/app11083380

Chao, M. A., Kulkarni, C., Goebel, K., & Fink, O. (2021). Aircraft engine run-to-failure dataset under real flight conditions for prognostics and diagnostics. Data, 6(1), 5. doi:
https://doi.org/10.3390/data6010005

Chao, M. A., Kulkarni, C., Goebel, K., & Fink, O. (2022, Jan). Fusing physics-based and deep learning models for prognostics. Reliability Engineering & System Safety, 217,
107961. doi: https://doi.org/10.1016/j.ress.2021.107961

Christ, M., Braun, N., Neuffer, J., & Kempa-Liehr, A. W. (2018, Sept). Time series feature extraction on basis of scalable hypothesis tests (tsfresh – a python package). Neurocomputing, 307, 72-77. doi: https://doi.org/10.1016/j.neucom.2018.03.067

Coble, J. B. (2010). Merging data sources to predict remaining useful life – an automated method to identify prognostic parameters (Unpublished doctoral dissertation). University of Tennessee.

Coelho, L. B., Zhang, D., Ingelgem, Y. V., Steckelmacher, D., Nowé, A., & Terryn, H. (2022, Jan). Reviewing machine learning of corrosion prediction in a data-oriented perspective. Materials Degradation, 6, 8. doi: https://doi.org/10.1038/s41529-022-00218-4

de Pater, I., Reijns, A., & Mitici, M. (2022, May). Alarm-based predictive maintenance scheduling for aircraft engines with imperfect remaining useful life prognostics. Reliability Engineering & System Safety, 221, 108341. doi:https://doi.org/10.1016/j.ress.2022.108341

Eker, C. F., O.F., & Jennions, I. (2012). Major challenges in prognostics: Study on benchmarking prognostics datasets. In Proceedings of the european conference of the phm society 2012 (Vol. 1, p. 1-8). doi: https://doi.org/10.36001/phme.2012.v1i1.1409

Elattar, H., Elminir, H., & Riad, A. e.-d. (2016, June). Prognostics: a literature review. Complex Intelligent Systems, 2, 125-154. Fernandes, M., Chorchaco, J. M., & Marreiros, G. (2022, Mar).

Machine learning techniques applied to mechanical fault diagnosis and fault prognosis in the context of real industrial manufacturing use-cases: a systematic literature
review. Applied Intelligence, 52, 14246-14280. doi: https://doi.org/10.1007/s10489-022-03344-3

Ferreira, C., & Gonc¸alves, G. (2022, April). Remaining useful life prediction and challenges: A literature review on the use of machine learning methods. Journal of Manufacturing Systems, 63, 550-562. doi: https://doi.org/10.1016/j.jmsy.2022.05.010

Guo, J., Li, Z., & Li, M. (2020). A review on prognostics methods for engineering systems. IEEE Transactions on Reliability, 69(3), 1110-1129. doi: https://doi.org/10.1109/
TR.2019.2957965

Gálvez, A., Diez-Olivan, A., Seneviratne, D., & Galar, D. (2021). Fault detection and rul estimation for railway hvac systems using a hybrid model-based approach. Sustainability, 13(12), 6828. doi: https://doi.org/10.3390/su13126828

Gülich, J. F. (2020). Centrifugal pumps. Springer.

Heek, D. (2021). A data-driven condition monitoring approach for the main bearings of a marine diesel engine. https://research.tue.nl/en/studentTheses/a-data-driven-condition-monitoring-approach-for-the-main-bearings. (MSc thesis, Eindhoven University of Technology)

Homborg, A., Leon Morales, C., Tinga, T., de Wit, J., & Mol, J. (2014, Aug). Detection of microbiologically influenced corrosion by electrochemical noise transients. Electrochimica Acta, 136, 223-232. doi:https://doi.org/10.1016/j.electacta.2014.05.102

Jouin, M., Gouriveau, R., Hissel, D., P´era, M.-C., & Zerhouni, N. (2016, May).

Particle filter-based prognostics: Review, discussion and perspectives. Mechanical Systems and Signal Processing, 72-73, 2-31. doi: https://doi.org/10.1016/j.ymssp.2015.11.008

Keizers, L. S., Loendersloot, R., & Tinga, T. (2021). Unscented kalman filtering for prognostics under varying operational and environmental conditions. International Journal of Prognostics and Health Management, 12(2), 1-20. doi:https://doi.org/10.36001/ijphm.2021.v12i2.2943

Keizers, L. S., Loendersloot, R., & Tinga, T. (2022). Atmospheric corrosion prognostics using a particle filter. In Book of extended abstracts for the 32nd european safety
and reliability conference. doi: https://doi.org/10.3850/978-981-18-5183-4 r22-08-170-cd

Kumar, S., Kolekar, T., Kotecha, K., Patil, S., & Bongale, A. (2022, Jan). Performance evaluation for tool wear prediction based on bi-directional, encoder–decoder and hybrid long short-term memory models. International Journal of Quality Reliability Management, ahead-of-print, 1551-1576. doi: https://doi.org/10.1108/IJQRM-08-2021-0291

Li, Y., Jiang, W., Zhang, G., & Shu, L. (2021, June). Wind turbine fault diagnosis based on transfer learning and convolutional autoencoder with small-scale data. Renewable
Energy, 171, 103-115. doi: https://doi.org/10.1016/j.renene.2021.01.143

Lu, S., Zhu, Y., Liu, S., & She, J. (2022). A tool wear prediction model based on attention mechanism and indrnn. In 2022 international joint conference on neural networks
(ijcnn) (p. 1-7). doi: https://doi.org/10.1109/IJCNN55064.2022.9889794

Lukens, S., Rousis, D., Baer, T., Lujan, M., & Smith, M. (2022). Data quality scorecard for assessing the suitability of asset condition data for prognostics modeling. In Proceedings of the annual conference of the phm society (Vol. 14, p. 1-15). doi: https://doi.org/10.36001/phmconf.2022.v14i1.3188

Medjaher, K., & Zerhouni, N. (2013, Jan). Framework for a hybrid prognostics. In (Vol. 33, p. 91-96). doi: https://doi.org/10.3303/CET1333016

Mkadara, G., Mar´e, J.-C., & Paulmann, G. (2021). Methodology for model architecting and failure simulation supported by bond-graphs—application to helicopter axial piston pump. Sustainability, 13(4), 1863. doi: https://doi.org/10.3390/su13041863

Mulders, M., & Haarman, M. (2017). Predictive maintenance 4.0 predict the unpredictable (Tech. Rep.). https://www.pwc.nl/nl/assets/documents/pwc-predictive-maintenance-4-0.pdf. (Retrieved on 21-02-2024)

Nakhaeinejad, M., & Bryant, M. (2011). Dynamic modeling of rolling element bearings with surface contact defects using bond graphs. Journal of Tribology, 133(1), 011102.
doi: https://doi.org/10.1115/1.4003088

Peng, D., Liu, C., & Gryllias, K. (2022). A transfer learning-based rolling bearing fault diagnosis across machines. In Annual conference of the phm society (Vol. 14, p. 1-9). doi:https://doi.org/10.36001/phmconf.2022.v14i1.3257

Pinciroli, L., Baraldi, P., & Zio, E. (2023, June). Maintenance optimization in industry 4.0. Reliability Engineering & System Safety, 234, 109204. doi: https://doi.org/10.1016/
j.ress.2023.109204

Pugalenthi, K., Park, H., Hussain, S., & Raghavan, N. (2021, sept). Hybrid particle filter trained neural network for prognosis of lithium-ion batteries. IEEE Access,
9, 135132-135143. doi: https://doi.org/10.1109/ACCESS.2021.3116264


Ramasso, E., & Saxena, A. (2014). Performance benchmarking and analysis of prognostic methods for cmapss datasets. International Journal of Prognostics and Health
Management, 5(2), 1-15. doi: https://doi.org/10.36001/ijphm.2014.v5i2.2236

Sawalhi, N., & Randall, R. (2008). Simulating gear and bearing interactions in the presence of faults: Part i. the combined gear bearing dynamic model and the simulation
of localised bearing faults. Mechanical Systems and Signal Processing, 22(8), 1924-1951. doi: https://doi.org/10.1016/j.ymssp.2007.12.001

Saxena, A., & Goebel, K. (2008). C-mapss data set.

Sheng, R., & Zhu, X. (2020, Dec). Tool wear assessment approach based on the neighborhood rough set model and nearest neighbor model. Shock and Vibration, 2020, 1-15. doi: https://doi.org/10.1155/2020/8876187

Sun, J., Zuo, H., Wang, W., & Pecht, M. G. (2014). Prognostics uncertainty reduction by fusing on-line monitoring data based on a state-space-based degradation model. Mechanical Systems and Signal Processing, 45(2), 396-407. doi: https://doi.org/10.1016/j.ymssp.2013.08.022

Sundararajan, G. (1991). A comprehensive model for the solid particle erosion of ductile materials. Wear, 149(1), 111-127. doi: https://doi.org/10.1016/0043-1648(91)90368-5

Tiddens, W., Braaksma, J., & Tinga, T. (2023). Decision framework for predictive maintenance method selection. Applied Sciences, 13(3), 2021. doi: https://doi.org/10.3390/
app13032021

Tinga, T. (2013a, July). Predictive maintenance of military systems based on physical failure models. Chemical engineering transactions, 33, 295-300. doi: https://doi.org/
10.3303/CET1333050

Tinga, T. (2013b). Principles of loads and failure mechanisms. applications in maintenance, reliability and design. Springer.

Tinga, T., Wubben, F., Tiddens, W. W., Wortmann, H., & Gaalman, G. (2021). Dynamic maintenance based on functional usage profiles. , 27(1), 21-42. doi: https://doi.org/
10.1108/JQME-01-2019-0002

van der Velde, R., Moerkerken, A., Hofstraat, K., Rosier, M., Haarman, M., de Klerk, P., Nedelcheva, Y. (2023). Digital trends in maintenance (Tech. Rep.). https://www.pwc.nl/en/evenementen/digital-trends-in-maintenance.html. (Retrieved on 01-03-2024)

Virkler, D., Hillberry, B., & Goel, P. (1979). The statistical nature of fatigue crack propagation. Journal of Engineering Materials and Technology, 101(2), 148-153.

Vos, P. (2019). Engine condition trend monitoring for apache turboshaft engines (Tech. Rep.). NLR. (Classified)

Wang, J., Wang, P., & Gao, R. (2015, July). Particle filter for tool wear prediction. Journal of Manufacturing Systems, 36, 35-45. doi: https://doi.org/10.1016/j.jmsy.2015.03.005

Wang, P., & Gao, R. (2016). Stochastic tool wear prediction for sustainable manufacturing. Procedia CIRP, 48, 236-241. doi: https://doi.org/10.1016/j.procir.2016.03.101

Yan, J., Meng, Y., Lu, L., & Guo, C. (2017). Big-data-driven based intelligent prognostics scheme in industry 4.0 environment. In 2017 prognostics and system health management conference (phm-harbin) (p. 1-5). doi: https://doi.org/10.1109/PHM.2017.8079310

Zhou, Y., & Sun, W. (2020, May). Tool wear condition monitoring in milling process based on current sensors. IEEE Access, 8, 95491-95502. doi: https://doi.org/10.1109/
ACCESS.2020.2995586

Zio, E., & Peloni, G. (2011). Particle filtering prognostic estimation of the remaining useful life of nonlinear components. Reliability Engineering & System Safety, 96(3),
403-409. doi: https://doi.org/10.1016/j.ress.2010.08.009
Section
Technical Papers