Generative AI for Aviation Maintenance: Optimizing Predictive Analytics through Strategic Prompt Engineering and Hybrid Human AI Collaboration

SeyyedAbdolHojjat  MoghadasNian

ПРЕПРИНТ

Эта статья является препринтом и не была отрецензирована.
О результатах, изложенных в препринтах, не следует сообщать в СМИ как о проверенной информации.

Generative AI for Aviation Maintenance: Optimizing Predictive Analytics through Strategic Prompt Engineering and Hybrid Human AI Collaboration

S. MoghadasNian

2026-01-14

https://doi.org/10.24108/preprints-3114278

This study examines the effect of strategic prompt engineering on the diagnostic accuracy of generative AI for predictive maintenance in aviation and evaluates the performance of hybrid human AI maintenance teams. Using a mixed methods approach combining quantitative analysis of diagnostic accuracy and mean time to repair (MTTR) metrics with qualitative interviews of industry experts, results show a >11% improvement in fault prediction accuracy and a significant reduction in MTTR. Findings contribute a KPI driven framework and propose governance guidelines for ethical AI deployment in aviation.

Ссылка для цитирования:

MoghadasNian S. 2026. Generative AI for Aviation Maintenance: Optimizing Predictive Analytics through Strategic Prompt Engineering and Hybrid Human AI Collaboration. PREPRINTS.RU. https://doi.org/10.24108/preprints-3114278

Список литературы

1. Dangut, M. D., Jennions, I. K., King, S., & Skaf, Z. (2022). Application of deep reinforcement learning for extremely rare failure prediction in aircraft maintenance. Mechanical Systems and Signal Processing, 171, 108873. https://doi.org/10.1016/j.ymssp.2022.108873

2. Lee, J., & Mitici, M. (2022). Deep reinforcement learning for predictive aircraft maintenance using probabilistic Remaining-Useful-Life prognostics. Reliab. Eng. Syst. Saf., 230, 108908. https://doi.org/10.1016/j.ress.2022.108908

3. Iyer, N., Virani, N., Yang, Z., & Saxena, A. (2022). Mixed Initiative Approach for Reliable Tagging of Maintenance Records with Machine Learning. Annual Conference of the PHM Society, 14(1). https://doi.org/10.36001/phmconf.2022.v14i1.3159

4. Moghadasnian, S. (2022). Flight to Excellence: A Comprehensive Guide to Key Performance Indicators in the Airline Industry: Unlocking Success Through Data-Driven Strategies and Performance Metrics. Aviation and Tourism Research and Innovation Center (ATRIC). Digital Publication. Tehran, Iran & Milan, Italy.

5. Moghadasnian, S. (2023). Strategica Aeronautica: Mastering KPI-Driven Leadership Across the Airline and Tourism Ecosystem: A Comprehensive Guide for Executives: From Analytic Hierarchy Process to Zero-Based Budgeting, Navigate the Full Spectrum of Strategic Decision-Making Metrics. Aviation and Tourism Research and Innovation Center (ATRIC). Digital Publication. Tehran, Iran & Milan, Italy.

6. Park, D. ., An, G.- taek ., Kamyod, C. ., & Kim, C. G. . (2024). A Study on Performance Improvement of Prompt Engineering for Generative AI with a Large Language Model. Journal of Web Engineering, 22(08), 1187–1206. https://doi.org/10.13052/jwe1540-9589.2285

7. Bozkurt, A. (2024). Tell Me Your Prompts and I Will Make Them True: The Alchemy of Prompt Engineering and Generative AI. Open Praxis. https://doi.org/10.55982/openpraxis.16.2.661.

8. Chen, A., Lyu, A., & Lu, Y. (2024). Member’s performance in human–AI hybrid teams: a perspective of adaptability theory. Information Technology & People. https://doi.org/10.1108/itp-05-2023-0513.

9. Wellsandt, S., Klein, K., Hribernik, K., Lewandowski, M., Bousdekis, A., Mentzas, G., & Thoben, K. (2022). Hybrid-augmented intelligence in predictive maintenance with digital intelligent assistants. Annu. Rev. Control., 53, 382-390. https://doi.org/10.1016/j.arcontrol.2022.04.001.

10. MoghadasNian, S. (2025). AI-driven inventory optimization in airline logistics: Enhancing efficiency, sustainability, and operational. The International Conference on Artificial Intelligence in the Age of Digital Transformation, Tbilisi, Georgia.

11. MoghadasNian, S., & MahMoudy, M. (2025). Airline logistics AI performance framework: A 360-degree, multi-layered KPI approach for safety, sustainability, efficiency, and innovation. 20th Iranian International Industrial Engineering Conference, Tehran, Iran.

12. MoghadasNian, S., MahMoudy, M., (2025). Stock control in airline logistics: AI-driven inventory optimization for spare parts. International Conference on Recent Advances in Engineering, Innovation, and Technology, Brussels, Belgium.

13. Ejjami, R., & Boussalham, K. (2024). Resilient Supply Chains in Industry 5.0: Leveraging AI for Predictive Maintenance and Risk Mitigation. International Journal For Multidisciplinary Research. https://doi.org/10.36948/ijfmr.2024.v06i04.25116.

14. Khan, Z., Nasim, B., & Rasheed, Z. (2024). Generative AI based Predictive Maintenance in Aviation: A Systematic Literature Review. https://doi.org/10.21203/rs.3.rs-5277729/v1.

15. Klekowicki, M., Szymański, G. M., Waligórski, M., & Misztal, W. (2024). Application of large language models in diagnostics and maintenance of aircraft propulsion systems. Advances in Science and Technology Research Journal, 19(2), 304–320. https://doi.org/10.12913/22998624/196264

16. Agustian, E. S., & Pratama, Z. A. (2024). Artificial Intelligence Application on Aircraft Maintenance: A Systematic Literature Review. EAI Endorsed Transactions on Internet of Things, 10. https://doi.org/10.4108/eetiot.6938

17. Li, Z. (2024). AI Ethics and Transparency in Operations Management: How Governance Mechanisms Can Reduce Data Bias and Privacy Risks. Deleted Journal, 13(1), 89–93. https://doi.org/10.54254/2977-5701/13/2024130

18. Manda, V. K., Christy, V., & Jitta, M. R. (2024). Ethical AI and Decision-Making in Management Leadership. Advances in Human and Social Aspects of Technology Book Series, 197–226. https://doi.org/10.4018/979-8-3693-4147-6.ch009

19. Agharia, S., Szatkowski, J., Fraval, A., Stevens, J., & Zhou, Y. (2023). The ability of artificial intelligence tools to formulate orthopaedic clinical decisions in comparison to human clinicians: An analysis of ChatGPT 3.5, ChatGPT 4, and Bard. Journal of Orthopaedics, 50, 1–7. https://doi.org/10.1016/j.jor.2023.11.063

ПРЕПРИНТ

ИНФОРМАЦИЯ

Использование куки-файлов