Deterministic Maintenance in Safety-Critical Aerospace Systems: A Certifiable AI/ML Framework for Root Cause Determinism, Closed-Loop Learning, and Reliability-Centric Avionics Design
Keywords:
Avionics Reliability, Certifiable Artificial Intelligence, Deterministic Maintenance, Digital Twin Validation, DO-178C Traceability, Root Cause IntelligenceAbstract
Aerospace maintenance operations face a persistent tension between the operational demands of high-dispatch-rate fleets and the stringent airworthiness requirements that govern safety-critical avionics. Existing maintenance paradigms, whether corrective, preventive, or predictive, fail to provide guaranteed diagnostic consistency, leaving technicians exposed to variable root cause interpretations and elevated no-fault-found rates that waste resources and erode airworthiness confidence. This article introduces the Deterministic Maintenance Framework (DMF), a new architecture where each observed fault signature corresponds to a unique, reproducible root cause and corrective action pair through the function f(O) = (RC, A, C). Here, the observation set O includes fault features, thermal signatures, system state, event logs, and historical records, and the output triple provides the root cause, corrective action, and a confidence explanation that meets regulatory traceability requirements. The DMF is structured across ten functional layers extending from raw data acquisition through digital twin validation to reliability growth feedback. A central component, the Root Cause Intelligence Engine (RCIE), constrains probabilistic artificial intelligence and machine learning inference within deterministic output rules to ensure that the same fault always yields the same diagnosis. Validated against representative avionics scenarios, including a Controller Pilot Data Link Communications timeout case, the DMF reduces mean time to repair by 57 percent, lowers no-fault-found incidence by 74 percent, and achieves diagnostic consistency exceeding 99 percent. The framework is architected for alignment with DO-178C software certification traceability principles and the regulatory guidance articulated in the European Union Aviation Safety Agency Artificial Intelligence Roadmap 2.0 and the Federal Aviation Administration AI Safety Assurance Roadmap.
Downloads
References
R. K. Mobley, An Introduction to Predictive Maintenance. Elsevier, 2002. Available: https://books.google.com/books?id=SjqXzxpAzSQC
A. K. S. Jardine, D. Lin, and D. Banjevic, "A review on machinery diagnostics and prognostics implementing condition based maintenance," Mechanical Systems and Signal Processing, vol. 20, no. 7, pp. 1483-1510, 2006. Available: https://doi.org/10.1016/j.ymssp.2005.09.012
J. Lee, B. Bagheri, and H.-A. Kao, "A cyber-physical systems architecture for industry 4.0-based manufacturing systems," Manufacturing Letters, vol. 3, pp. 18-23, 2015. Available: https://doi.org/10.1016/j.mfglet.2014.12.001
K. P. Murphy, Machine Learning: A Probabilistic Perspective. MIT Press, 2012. Available: https://www.cs.ubc.ca/~murphyk/MLbook/
J. Pearl, Probabilistic Reasoning in Intelligent Systems. Elsevier, 2014. Available: https://dl.acm.org/doi/book/10.5555/534975
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.
F. Tao et al., "Data-driven smart manufacturing," Journal of Manufacturing Systems, vol. 48, pp. 157-169, 2018. Available: https://doi.org/10.1016/j.jmsy.2018.01.006
S. M. Lundberg and S.-I. Lee, "A unified approach to interpreting model predictions," Advances in Neural Information Processing Systems, vol. 30, 2017. Available: https://proceedings.neurips.cc/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf
M. Chen, R. Qu, and W. Fang, "Case-based reasoning system for fault diagnosis of aero-engines," Expert Systems with Applications, vol. 202, p. 117350, 2022. Available: https://doi.org/10.1016/j.eswa.2022.117350
Z. She et al., "Ontology-based root cause fault diagnostic reasoning for airborne systems," Aerospace, vol. 13, no. 2, p. 167, 2026. Available: https://doi.org/10.3390/aerospace13020167
S. Sutthithatip, S. Perinpanayagam, and S. Aslam, "(Explainable) artificial intelligence in aerospace safety critical systems," in Proc. IEEE Aerospace Conference, 2022, pp. 1-12. Available: https://doi.org/10.1109/AERO53065.2022.9843612
EASA, Artificial Intelligence Roadmap 2.0, May 2023. Available: https://www.easa.europa.eu/en/document-library/general-publications/easa-artificial-intelligence-roadmap-20
FAA, Roadmap for Artificial Intelligence Safety Assurance, Version I, Jul. 2024. Available: https://www.faa.gov/aircraft/air_cert/step/roadmap_for_AI_safety_assurance
W. K. Youn et al., "Software certification of safety critical avionic systems: DO-178C and its impacts," IEEE Aerospace and Electronic Systems Magazine, vol. 30, no. 4, pp. 4-13, 2015. Available: https://doi.org/10.1109/MAES.2014.140109
M. J. Scott et al., "A systematic literature review of predictive maintenance for defence fixed-wing aircraft sustainment and operations," Sensors, vol. 22, no. 18, p. 7070, 2022. Available: https://doi.org/10.3390/s22187070
J. Lee and M. Mitici, "Deep reinforcement learning for predictive aircraft maintenance using probabilistic remaining-useful life prognostics," Reliability Engineering and System Safety, vol. 230, p. 108908, 2023. Available: https://doi.org/10.1016/j.ress.2022.108908
L. Li et al., "Digital twin in aerospace industry: A gentle introduction," IEEE Access, vol. 10, pp. 9543-9562, 2021. Available: https://doi.org/10.1109/ACCESS.2021.3136458
G. M. Bisanti et al., "Digital twins for aircraft maintenance and operation," Internet of Things, vol. 24, p. 100991, 2023. Available: https://doi.org/10.1016/j.iot.2023.100991
I. Kabashkin and V. Perekrestov, "Ecosystem of aviation maintenance," Applied Sciences, vol. 14, no. 11, p. 4394, 2024. Available: https://doi.org/10.3390/app14114394
F. S. Cetin et al., "Data-driven predictive maintenance for aircraft components through sparse event logs," Aerospace, vol. 13, no. 1, p. 110, 2026. Available: https://doi.org/10.3390/aerospace13010110
J. Li, S. King, and I. Jennions, "Intelligent fault diagnosis of an aircraft fuel system using machine learning," Machines, vol. 11, no. 4, p. 481, 2023. Available: https://doi.org/10.3390/machines11040481
P. Andrade et al., "Aircraft maintenance check scheduling using reinforcement learning," Aerospace, vol. 8, no. 4, p. 113, 2021. Available: https://www.mdpi.com/2226-4310/8/4/113
C. Silva et al., "Adaptive reinforcement learning for task scheduling in aircraft maintenance," Scientific Reports, vol. 13, no. 1, p. 16605, 2023. Available: https://www.nature.com/articles/s41598-023-41169-3
A. Zaoui et al., "Impact of artificial intelligence on aeronautics: An industry-wide review," Journal of Engineering and Technology Management, vol. 71, p. 101800, 2024. Available: https://doi.org/10.1016/j.jengtecman.2024.101800
M. Baptista et al., "Forecasting fault events for predictive maintenance using data-driven techniques and ARMA modeling," Computers and Industrial Engineering, vol. 115, pp. 41-53, 2018. Available: https://doi.org/10.1016/j.cie.2017.10.033
R. Meissner et al., "Developing prescriptive maintenance strategies in the aviation industry based on a discrete-event simulation framework for post-prognostics decision making," Reliability Engineering & System Safety, vol. 214, pp. 107812, 2021. Available: https://doi.org/10.1016/j.ress.2021.107812
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Shyamala Bai Kotin
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
