This paper presents an analytical model of an intelligent diagnostic system designed for early fault detection in aircraft radio-electronic (avionic) devices. Traditional threshold-based methods are limited by low sensitivity and inability to model nonlinear dependencies among system parameters. The proposed AI-based model, calibrated on vibration, temperature, and pressure data from the FADEC (Full Authority Digital Engine Control) of a Pratt & Whitney PW127M engine (ATR-72 aircraft), applies a nonlinear mapping evaluated using a binary cross-entropy metric. Uncertainty quantification is introduced using a Beta distribution, enabling calculation of a 95 % confidence interval for diagnostic reliability. Experimental validation shows a diagnostic accuracy of 93 ± 2 % and false-alarm rate below 8 %, demonstrating promising predictive performance under simulated operating conditions. The system ensures real-time data fusion between onboard and ground maintenance units, providing a foundation for predictive and sustainable aviation maintenance. The proposed framework provides probabilistic, confidence-aware diagnostics suitable for real-time deployment and supports risk-informed maintenance decisions aligned with modern aviation certification and Maintenance 4.0 requirements.
J. Lee, B. Bagheri, and H.-A. Kao, “A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems,” Manufacturing Letters, 2014.
Y. Lei, N. Li, L. Guo, N. Li, T. Yan, and J. Lin, “Machinery health prognostics: A systematic review from data acquisition to RUL prediction,” Mechanical Systems and Signal Processing, vol. 104, pp. 799-834, May 2018, [Online]. Available: https://doi.org/10.1016/j.ymssp.2017.11.016.
R. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang, and R. X. Gao, “Deep learning and its applications to machine health monitoring,” Mechanical Systems and Signal Processing, vol. 115, pp. 213-237, 2019, [Online]. Available: https://doi.org/10.1016/j.ymssp.2018.05.050.
J. Lee, H.-A. Kao, and S. Yang, “Service innovation and smart analytics for Industry 4.0 and big data environment,” Procedia CIRP, vol. 16, pp. 3-8, 2014, [Online]. Available: https://doi.org/10.1016/j.procir.2014.02.001.
A. Abdukayumov and I. S. Maturazov, “Improvement of radio electronic equipment diagnostic systems,” AIP Conference Proceedings, vol. 2432, Art. no. 030044, Jun. 2022, [Online]. Available: https://doi.org/10.1063/5.0090223.
E. S. Agustian and Z. A. Pratama, “Artificial intelligence application on aircraft maintenance: A systematic literature review,” EAI Endorsed Transactions on Internet of Things, vol. 10, 2024, [Online]. Available: https://doi.org/10.4108/eetiot.6938.
A. Bentaleb, K. Toumlal, and J. Abouchabaka, “Predicting aircraft engine failures using artificial intelligence,” International Journal of Advanced Computer Science and Applications, vol. 15, 2024, [Online]. Available: https://doi.org/10.14569/IJACSA.2024.0150295.
Y. Gal and Z. Ghahramani, “Dropout as a Bayesian approximation: Representing model uncertainty in deep learning,” in Proc. 33rd Int. Conf. Machine Learning (ICML), New York, NY, USA, 2016, pp. 1050-1059.
A. Kendall and Y. Gal, “What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?,” 2017, [Online]. Available: https://doi.org/10.48550/arXiv.1703.04977.
A. Saxena and K. Goebel, “Turbofan Engine Degradation Simulation Dataset,” NASA PHM Repository.
F. Tao et al., “Digital twin-driven product lifecycle management,” IEEE Access, 2019.
K. R. Patibandla, “Predictive maintenance in aviation using artificial intelligence,” Journal of Artificial Intelligence General Science, vol. 4, no. 1, pp. 325-333, 2024, [Online]. Available: https://doi.org/10.60087/jaigs.v4i1.214.
P. Nunes, J. Santos, and E. Rocha, “Challenges in predictive maintenance - A review,” CIRP Journal of Manufacturing Science and Technology, vol. 40, pp. 53-67, 2023, [Online]. Available: https://doi.org/10.1016/j.cirpj.2022.11.004.
