Engine Health State Index (EHSI)
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Assessing the health of diesel engines is challenging due to multiple coexisting failure modes, overlapping fault signatures, and highly imbalanced operational data. This paper proposes an Engine Health State Index (EHSI), a probabilistic health metric that aggregates risk estimates from multiple failure-code–specific models.
The framework employs a collection of binary classifiers, each trained to estimate the likelihood of a specific failure code from historical telemetry and diagnostic data. At each time step, the resulting failure risk vector provides a distributed representation of latent fault exposure rather than a single dominant failure mode. EHSI maps this risk distribution to a scalar health index using normalized uncertainty measures, enabling continuous tracking of health degradation without relying on explicit fault triggers.
Experiments on real-world diesel engine datasets show that EHSI produces smooth and interpretable health trajectories that correlate with impending failures while remaining sensitive to early-stage degradation. The proposed approach is model-agnostic, extensible to additional failure modes, and suitable for large-scale fleet monitoring applications.
How to Cite
##plugins.themes.bootstrap3.article.details##
Remaining Useful Life, Prognostics, Predictive Maintenance, Engine Health Monitoring, Downtime reduction
Zhang, Y., Fang, L., Qi, Z., & Deng, H. (2023). A review of remaining useful life prediction approaches for mechanical equipment. IEEE Sensors Journal, 23(24), 29991–30006. https://doi.org/10.1109/JSEN.2023.3326487
Qiu, S., Cui, X., Ping, Z., Shan, N., Li, Z., Bao, X., & Xu, X. (2023). Deep learning techniques in intelligent fault diagnosis and prognosis for industrial systems: A review. Sensors, 23(3), 1305. https://doi.org/10.3390/s23031305
Yuan, C., & Liu, S. (2024). Multi-attribute maintenance decision making for aircraft engines based on entropy weight TOPSIS approach. In Proceedings of the 2024 Global Reliability and Prognostics and Health Management Conference (PHM-Beijing) (pp. 1–6). IEEE. https://doi.org/10.1109/PHMBeijing63284.2024.10874564
Nguyen, K. T. P., & Medjaher, K. (2021). An automated health indicator construction methodology for prognostics based on multi-criteria optimization. ISA Transactions, 113, 81–96. https://doi.org/10.1016/j.isatra.2020.03.017
Bajarunas, K., Baptista, M. L., Goebel, K., & Arias Chao, M. (2024). Health index estimation through integration of general knowledge with unsupervised learning. Reliability Engineering & System Safety, 251, 110352. https://doi.org/10.1016/j.ress.2024.110352
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. https://doi.org/10.1016/j.aei.2023.101973
Yong, B. X., & Brintrup, A. (2022). Coalitional Bayesian autoencoders: Towards explainable unsupervised deep learning with applications to condition monitoring under covariate shift. Applied Soft Computing, 123, 108912. https://doi.org/10.1016/j.asoc.2022.108912
De Giorgi, M. G., Menga, N., & Ficarella, A. (2023). Exploring prognostic and diagnostic techniques for jet engine health monitoring: A review of degradation mechanisms and advanced prediction strategies. Energies, 16(6), 2711. https://doi.org/10.3390/en16062711
Zhang, P., Cao, L., Dong, F., Gao, Z., Zou, Y., Wang, K., Zhang, Y., & Sun, P. (2022). A study of hybrid predictions based on the synthesized health indicator for marine systems and their equipment failure. Applied Sciences, 12(7), 3329. https://doi.org/10.3390/app12073329
Shcherbakov, M., & Sai, C. (2022). A hybrid deep learning framework for intelligent predictive maintenance of cyber-physical systems. ACM Transactions on Cyber-Physical Systems, 6(2), Article 17. https://doi.org/10.1145/3486252
Medjaher, K., Tobon-Mejia, D. A., & Zerhouni, N. (2012). Remaining useful life estimation of critical components with application to bearings. IEEE Transactions on Reliability, 61(2), 292–302. https://doi.org/10.1109/TR.2012.2194175
Mosallam, A., Medjaher, K., & Zerhouni, N. (2016). Data-driven prognostic method based on Bayesian approaches for direct remaining useful life prediction. Journal of Intelligent Manufacturing, 27, 1037–1048. https://doi.org/10.1007/s10845-014-0933-4
Wang, T., Yu, J., Siegel, D., & Lee, J. (2008). A similarity-based prognostics approach for remaining useful life estimation of engineered systems. In Proceedings of the International Conference on Prognostics and Health Management (pp. 1–6). IEEE. https://doi.org/10.1109/PHM.2008.4711421
Liu, B., Gao, Z., Lu, B., Dong, H., & An, Z. (2022). Deep learning-based remaining useful life estimation of bearings with time-frequency information. Sensors, 22(19), 7402. https://doi.org/10.3390/s22197402
Chen, L., Xu, G., Zhang, S., Yan, W., & Wu, Q. (2020). Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks. Journal of Manufacturing Systems, 54, 1–11. https://doi.org/10.1016/j.jmsy.2019.11.008
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. https://doi.org/10.1016/j.neucom.2018.02.083
Xu, F., Huang, Z., Yang, F., Wang, D., & Tsui, K. L. (2020). Constructing a health indicator for roller bearings by using a stacked auto-encoder with an exponential function to eliminate concussion. Applied Soft Computing, 89, 106119. https://doi.org/10.1016/j.asoc.2020.106119
Kaji, M., Parvizian, J., & van de Venn, H. W. (2020). Constructing a reliable health indicator for bearings using convolutional autoencoder and continuous wavelet transform. Applied Sciences, 10(24), 8948. https://doi.org/10.3390/app10248948.
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.