Manufacturing Quality–Informed Prognostics: A Novel Approach to Past Uncertainty Management
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
https://orcid.org/0009-0007-6522-8662
Julie Teuwen
Nick Eleftheroglou
Abstract
The future behavior of a system is largely determined by its manufacturing process, as variations in production quality can lead to different performance outcomes over time. In the context of prognostics, all sources of uncertainty that exist prior to the system’s commencement of operation are collectively referred to as past uncertainty, yet its role is rarely recognised in the prognostics and health management (PHM) community. Most existing approaches to uncertainty and its management focus only on model parameters, leaving the management of past uncertainty largely unexplored. This work introduces a framework to explicitly manage this source by incorporating manufacturing quality control (MQC) data into hidden semi‑Markov model (HSMM) prognostics. The method creates quality‑specific HSMMs, each tailored to a particular manufacturing quality (MQ) type, and combines them during inference using MQC‑informed Bayesian model averaging.
The framework is validated on composite specimens with pristine, oil‑induced, and Teflon‑induced defects. Ultrasonic scans provide MQC inputs, while strain data describes degradation. Results show that accounting for MQ reduces uncertainty in RUL predictions and highlights the importance of correctly identifying the MQ type for effective uncertainty management in prognostics.
How to Cite
##plugins.themes.bootstrap3.article.details##
Prognostics, Uncertainty management
Eleftheroglou, N. (2020). Adaptive prognostics for remaining useful life of composite structures [Doctoral dissertation, Delft University of Technology]. doi: 10.4233/uuid:538558fb-ac9a-414d-8a59-4b523d8ff74c
Eleftheroglou, N., Galanopoulos, G., & Loutas, T. (2024). Similarity learning hidden semi-Markov model for adaptive prognostics of composite structures. Reliability Engineering & System Safety, 243, 109808. doi: 10.1016/j.ress.2023.109808
Eleftheroglou, N., Zarouchas, D., & Benedictus, R. (2020). An adaptive probabilistic data-driven methodology for prognosis of the fatigue life of composite structures. Composite Structures, 245, 112386. doi: 10.1016/j.compstruct.2020.112386
Endrerud, J. O. (2014). NDT for non-experts. Reinforced Plastics, 58, 44–46. doi: 10.1016/S0034-3617(14)70184-5
Goli, M., Ghodrati, B., & Eleftheroglou, N. (2025). A literature review-based evaluation framework for maintenance strategy selection in heavy vehicles. Results in Engineering, 28, 107109. doi: 10.1016/j.rineng.2025.107109
Kim, S., Choi, J.-H., & Kim, N. H. (2022). Inspection schedule for prognostics with uncertainty management. Reliability Engineering & System Safety, 222, 108391. doi: 10.1016/j.ress.2022.108391
Kontogiannis, T., Salinas-Camus, M., & Eleftheroglou, N. (2025). Hidden Markov model applications. In Stochastic modeling and statistical methods (pp. 191–213). Elsevier. doi: 10.1016/B978-0-44-331694-4.00015-3
Leinarts, D. R. (2025). Uncertainty management for past state prognostic uncertainties in aerospace structures [Master’s thesis, TU Delft].
Orchard, M., Kacprzynski, G., Goebel, K., Saha, B., & Vachtsevanos, G. (2008). Advances in uncertainty representation and management for particle filtering applied to prognostics. In 2008 International Conference on Prognostics and Health Management (pp. 1–6). IEEE. doi: 10.1109/PHM.2008.4711433
Saha, B., & Goebel, K. (2008). Uncertainty management for diagnostics and prognostics of batteries using Bayesian techniques. In 2008 IEEE Aerospace Conference (pp. 1–8). IEEE. doi: 10.1109/AERO.2008.4526631
Salinas-Camus, M., & Eleftheroglou, N. (2024). Uncertainty in aircraft turbofan engine prognostics on the C-MAPSS dataset. PHM Society European Conference, 8, 10. doi: 10.36001/phme.2024.v8i1.4007
Salinas-Camus, M., Goebel, K., & Eleftheroglou, N. (2025). A comprehensive review and evaluation framework for data-driven prognostics: Uncertainty, robustness, interpretability, and feasibility. Mechanical Systems and Signal Processing, 237, 113015. doi: 10.1016/j.ymssp.2025.113015
Sankararaman, S. (2015). Significance, interpretation, and quantification of uncertainty in prognostics and remaining useful life prediction. Mechanical Systems and Signal Processing, 52–53, 228–247. doi: 10.1016/j.ymssp.2014.05.029
Sankararaman, S., & Goebel, K. (2013). Why is the remaining useful life prediction uncertain? Annual Conference of the PHM Society, 5. doi: 10.36001/phmconf.2013.v5i1.2263
Syriopoulos, P. K., Kalampalikis, N. G., Kotsiantis, S. B., & Vrahatis, M. N. (2025). KNN classification: A review. Annals of Mathematics and Artificial Intelligence, 93, 43–75. doi: 10.1007/s10472-023-09882-x
Tang, L., Kacprzynski, G. J., Goebel, K., & Vachtsevanos, G. (2009). Methodologies for uncertainty management in prognostics. In 2009 IEEE Aerospace Conference (pp. 1–12). IEEE. doi: 10.1109/AERO.2009.4839668
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.