A Reliability Digital Twin Architecture for Real-Time Fleet Monitoring and Predictive Maintenance of Hydrostatic Transmission Components
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
As Digital Twins (DTs) are increasingly developed for Prognostics and Health Management (PHM), many published works remain conceptual, or rely solely on Data-Driven (DD) algorithms, that are difficult to deploy under fleet or industrial constraints. This paper proposes a reliability-centered DT architecture, specifically designed for fleet-level deployment with limited sensing, rare failures, and strong legacy knowledge.
The contribution lies in structuring and integrating heterogeneous estimation mechanisms, relying on physics-based lifetime models, Bayesian techniques for risk control of model updates, soft sensing, and with the adjunction of unsupervised anomaly indicators. The goal here is to have a coherent, explainable, and industrially deployable DT pipeline. Central to the framework is a two-level fusion strategy: (i) a centralized reliability fusion operating on cumulative damage, accelerated life testing (ALT) models and sparse failures, and (ii) decentralized embedded diagnostics, providing complementary health indicators under operational variability.
The architecture is demonstrated on hydrostatic transmission components using test-to-failure databases (DBs), accelerated life models, temperature soft sensing through Extended Kalman Filter (EKF) and neural networks (NN), and vibration-based anomaly detection/degradation quantifier via SOM–MQE. The paper explicitly addresses scalability, explainability, and statistical risk control, which remain open challenges in DT deployments for PHM. The proposed framework targets practitioners seeking DT implementations compatible with ISO‑13374 logic, uncertainty guarantees, and industrial or fleet asset management constraints.
How to Cite
##plugins.themes.bootstrap3.article.details##
PHM Digital Twin, Architecture, Real-Time Monitoring, Hydrostatic Components
Penteado, G. U. S., Michalski, M. A. C., & de Souza, G. F. M. (2025). Digital twins in asset prognosis and health management: Definitions, applications, state of the art, and future trends. In Industrial Engineering and Operations Management: Springer Proceedings in Mathematics & Statistics (Vol. 483). doi: 10.1007/978-3-031-80785-5_12
Grieves, M., & Vickers, J. (2017). Digital twin: Mitigating unpredictable, undesirable emergent behavior in complex systems. In Transdisciplinary Perspectives on Complex Systems (pp. 85–113). Springer.
Tao, F., Zhang, M., Liu, Y., & Nee, A. Y. C. (2018). Digital twin-driven prognostics and health management for complex equipment. CIRP Annals: Manufacturing Technology, 67(1), 169–172. doi: 10.1016/j.cirp.2018.04.055
Lu, Y., Liu, C., Wang, I., Huang, H., & Xu, X. (2020). Digital twin-driven smart manufacturing: Connotation, reference model, applications and research issues. Robotics and Computer-Integrated Manufacturing, 61, 101837. doi: 10.1016/j.rcim.2019.101837
Jiao, J., Zhao, M., Lin, J., & Liang, K. (2020). A comprehensive review on convolutional neural networks in machine fault diagnosis. Neurocomputing, 417, 36–63. doi: 10.1016/j.neucom.2020.07.088
Zio, E. (2022). Prognostics and health management (PHM): Where are we and where do we need to go in theory and practice? Reliability Engineering & System Safety, 218, 108119. doi: 10.1016/j.ress.2021.108119
Meeker, W. Q., & Escobar, L. A. (1998). Statistical methods for reliability data. Wiley.
Nelson, W. (2004). Accelerated testing: Statistical models, test plans, and data analysis. Wiley-Interscience.
Abernethy, R. B. (2006). The new Weibull handbook: Reliability and statistical analysis for predicting life, safety, risk, support costs, failures, and forecasting warranty claims (5th ed.). North Palm Beach, FL, USA.
Fink, O., Nejjar, I., Sharma, V., Niresi, K. F., Sun, H., Dong, H., Xu, C., Wei, A., Bizzi, A., Theiler, R., Tian, Y., Von Krannichfeldt, L., Ma, Z., Garmaev, S., Zhang, Z., & Zhao, M. (2025). From physics to machine learning and back: Learning and observational bias in PHM. arXiv. doi: 10.48550/arXiv.2509.21207
Kohonen, T. (2001). Self-organizing maps (3rd ed.). Springer Series in Information Sciences, 30. Springer.
Vogl, G. W., Weiss, B. A., & Donmez, M. A. (2014). Standards for prognostics and health management (PHM) techniques within manufacturing operations. In Proceedings of the Annual Conference of the PHM Society. Fort Worth, TX, USA. National Institute of Standards and Technology (NIST).
Dowling, N. E. (2012). Mechanical behavior of materials: Engineering methods for deformation, fracture, and fatigue (4th ed.). Pearson Education.
Niggel, C., Ozouf, V., Padois, F., Serment, C., Chardaire, D., Berthier, D., Dandine, B., Castanier, B., Regis, B., Cherfi, Z., & Laronde, R. (2025). Handbook for automotive reliability: Assessment and validation. Société des Ingénieurs de l’Automobile.
Liu, Y., & Abeyratne, A. I. (2019). Practical applications of Bayesian reliability. Wiley.
Kruschke, J. (2014). Doing Bayesian data analysis: A tutorial introduction with R. Academic Press.
Choi, J. H., Jang, S. K., Cho, W. H., Moon, S., & Kim, H. (2024). Motor PHM on edge computing with anomaly detection and fault severity estimation through compressed data using PCA and autoencoder. Machine Learning and Knowledge Extraction, 6(3), 1466–1483. doi: 10.3390/make6030069
Bublil, T., Taal, C., Maljaars, B., Klein, R., & Bortman, J. (2024). Labeling algorithm for outer-race faults in bearings based on load signal. PHM Society European Conference, 8(1), 7. doi: 10.36001
Huang, Y., & Guehmann, C. (2014). Estimation of the temperatures in an asynchronous machine using extended Kalman filter. In IEEE Energy Conversion Congress and Exposition (ECCE). doi: 10.1109/ISFEE.2014.7050598
Radicioni, L., Bono, F. M., & Cinquemani, S. (2025). Vibration-based anomaly detection in industrial machines: A comparison of autoencoders and latent spaces. Machines, 13, 139. doi: 10.3390/machines13020139
Park, K., & Lee, Y. (2024). An experiment on anomaly detection for fault vibration signals using autoencoder-based N-segmentation algorithm. Proceedings of the European Conference of the PHM Society, 8(1). doi: 10.36001
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.