Unsupervised Physics-Informed Health Indicator Estimation for Complex Systems

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

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

Published Oct 26, 2023
Kristupas Bajarunas Marcia Baptista Kai Goebel Manuel Arias Chao

Abstract

Developing Health Indicators (HI) is a crucial aspect of prognostics and health management of complex systems. Previous research has demonstrated the benefits of accurately determining the HI, which can lead to better performance of prognostic models. However, the existing methodologies for determining HI in complex systems are mostly semi-supervised and rely on assumptions that may not hold in real-world scenarios. The existing methods usually involve using a reference set of healthy sensor readings or run-to-failure data to infer HI. But the unsupervised inference of HI from sensor readings, which is challenging in scenarios where diverse operating conditions can mask the effect of degradation on sensor readings, has not been extensively researched. In this paper, we propose a novel physics-informed unsupervised model for determining HI. Unlike previous methods, constrained by assumptions, the proposed method uses prior general knowledge about degradation to infer HI, thereby eliminating the need for a reference set of healthy sensor readings. The proposed unsupervised model is an Autoencoder that incorporates constraints on its latent space to ensure consistency with knowledge about degradation. We assess the efficacy of the proposed model by analyzing a prevalent prognostic case study, specifically the turbofan engine dataset (N-CMAPSS). Our analysis considers the model's sensitivity to data availability and the resulting Health Index's quality, including trendability and monotonicity. Additionally, we investigate the impact of incorporating the Health Index in predicting Remaining Useful Life (RUL). We demonstrate that our proposed method generates a Health Index that exhibits greater monotonicity and trendability than the current state-of-the-art semi-supervised approach. Moreover, our approach for identifying the Health Index leads to enhanced prognostic performance compared to the existing semi-supervised approach.

How to Cite

Bajarunas, K., Baptista, M., Goebel, K., & Chao, M. A. (2023). Unsupervised Physics-Informed Health Indicator Estimation for Complex Systems. Annual Conference of the PHM Society, 15(1). https://doi.org/10.36001/phmconf.2023.v15i1.3477
Abstract 583 | PDF Downloads 286

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

Keywords

Prognostics, Health Index, Unsupervised Learning

References
Arias Chao, M., 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.

Arias Chao, M., Kulkarni, C., Goebel, K., & Fink, O. (2022). Fusing physics-based and deep learning models for prognostics. Reliability Engineering & System Safety, 217, 107961.

Chalapathy, R., & Chawla, S. (2019). Deep learning for anomaly detection: A survey. arXiv preprint arXiv:1901.03407.
Coble, J. B. (2010). Merging data sources to predict remaining useful life–an automated method to identify prognostic parameters.

Cofre-Martel, S., Lopez Droguett, E., & Modarres, M.(2021). Remaining useful life estimation through deep learning partial differential equation models: A framework for degradation dynamics interpretation using latent variables. Shock and Vibration, 2021, 1–15.

de Beaulieu, M. H., Jha, M. S., Garnier, H., & Cerbah, F.(2022). Unsupervised remaining useful life prediction through long-range health index estimation based on encoders-decoders. IFAC-PapersOnLine, 55(6), 718–723.

de Pater, I., & Mitici, M. (2023). Developing health indicators and rul prognostics for systems with few failure instances and varying operating conditions using a lstm autoencoder. Engineering Applications of Artificial Intelligence, 117, 105582.

Fu, S., Zhong, S., Lin, L., & Zhao, M. (2021). A novel time-series memory auto-encoder with sequentially updated reconstructions for remaining useful life prediction.IEEE Transactions on Neural Networks and Learning Systems, 33(12), 7114–7125.

Guo, L., Lei, Y., Li, N., Yan, T., & Li, N. (2018). Machinery health indicator construction based on convolutional neural networks considering trend burr. Neurocomputing, 292, 142–150.

Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021). Physics-informed machine learning. Nature Reviews Physics, 3(6), 422-440.

Koutroulis, G., Mutlu, B., & Kern, R. (2022). Constructing robust health indicators from complex engineered systems via anticausal learning. Engineering Applications of Artificial Intelligence, 113, 104926.

Lee, H., Lim, H. J., & Chattopadhyay, A. (2021). Data-driven system health monitoring technique using autoencoder for the safety management of commercial aircraft. Neural Computing and Applications, 33, 3235–3250.

Liu, K., & Huang, S. (2014). Integration of data fusion methodology and degradation modeling process to improve prognostics. IEEE Transactions on AutomationScience and Engineering, 13(1), 344–354.

Lovberg, A. (2021). Remaining useful life prediction of aircraft engines with variable length input sequences. In Annual conference of the phm society (Vol. 13).

Magad ́an, L., Su ́arez, F. J., Granda, J. C., delaCalle, F. J., & Garc ́ıa, D. F. (2023). A robust health prognostic technique for failure diagnosis and the remaining useful lifetime predictions of bearings in electric motors. Applied Sciences, 13(4), 2220.

Nejjar, I., Geissmann, F., Zhao, M., Taal, C., & Fink, O.(2023). Domain adaptation via alignment of operation profile for remaining useful lifetime prediction. arXiv preprint arXiv:2302.01704.

Nguyen, K. T., & Medjaher, K. (2021). An automated health indicator construction methodology for prognostics based on multi-criteria optimization. ISA transactions, 113, 81–96.

Pearl, J., et al. (2000). Models, reasoning and inference.Cambridge, UK: CambridgeUniversityPress, 19(2).

Qin, Y., Yang, J., Zhou, J., Pu, H., & Mao, Y.(2023). A new supervised multi-head self-attention autoencoder for health indicator construction and similarity-based machinery rul prediction. Advanced Engineering Informatics, 56, 101973. doi: https://doi.org/10.1016/j.aei.2023.101973

Wang, T., Yu, J., Siegel, D., & Lee, J. (2008). A similarity-based prognostics approach for remaining useful life estimation of engineered systems. In 2008 international conference on prognostics and health management (pp. 1–6).

Yang, F., Habibullah, M. S., Zhang, T., Xu, Z., Lim, P., & Nadarajan, S. (2016). Health index-based prognostics for remaining useful life predictions in electrical machines. IEEE Transactions on Industrial Electronics, 63(4), 2633–2644.

Ye, Z., & Yu, J. (2021). Health condition monitoring of machines based on long short-term memory convolutional autoencoder. Applied Soft Computing, 107, 107379.

Zgraggen, J., Pizza, G., & Huber, L. G. (2022). Uncertainty informed anomaly scores with deep learning: Robust fault detection with limited data. In Phm society european conference (Vol. 7, pp. 530–540).

Zhai, S., Gehring, B., & Reinhart, G. (2021). Enabling predictive maintenance integrated production scheduling by operation-specific health prognostics with generative deep learning. Journal of Manufacturing Systems, 61, 830–855.

Zhou, H., Huang, X., Wen, G., Lei, Z., Dong, S., Zhang, P., & Chen, X. (2022). Construction of health indicators for condition monitoring of rotating machinery: A review of the research. Expert Systems with Applications, 203,117297.
Section
Technical Research Papers

Most read articles by the same author(s)

1 2 3 4 5 > >>