Machine Learning–Aided Synthetic Air Data System for Commercial Aircraft
Publication: Journal of Aerospace Engineering
Volume 37, Issue 6
Abstract
Air data inertial reference system (ADIRS) parameters are very important for the safe flight of an aircraft. The ADIRS consists of air data inertial reference units (ADIRUs) and the air data reference (ADR) part of the ADIRU, which provides the air data [altitude (ALT), angle of attack (AOA), airspeed, and temperature information] examined in this study. ADR is essential to continuously ensure accurate and precise information to the flight management guidance computers (FMGCs), electronic flight instruments system (EFIS), and other systems on the aircraft for reliable and safe flight operation. This study estimated the ADR parameters (altitude, angle of attack, airspeed, and temperature) to obtain a synthetic air data system for data continuity in the event of any sensor failure on the aircraft using correlated data. According to correlation analysis, the angle of attack, computed airspeed (CAS), and static air temperature (SAT) data have the highest correlation with the stabilizer position (STAB), whereas the altitude data have the highest correlation with the low-pressure engine spool rotational speed (N1). The AOA, CAS, SAT, and ALT parameters were estimated by decision tree, support vector machine, and Gaussian process regression models using real flight data collected from a local airline. The Gaussian process regression model was better at generalizing the data set for data estimation than were the other machine learning methods used in this study. MATLAB version R2023a software was used in all operations.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This study is supported by TUBITAK with project number 124E220.
References
AAIB (Air Accidents Investigation Branch). 2006. Bulletin: 6/2006, I-BIKE EW/C2005/06/03. Aldershot, UK: AAIB.
AAIB (Air Accidents Investigation Branch). 2019. AAIB investigation to Boeing 737-8AS, EI-GJT. Aldershot, UK: AAIB.
Airbus. 2002. Flight crew operating manual–Navigation: ADIRS. Leiden, Netherlands: Airbus.
Amini, M. A., and M. Ayati. 2019. “Performance of low-cost air-data sensors for airspeed and angle of attack measurements in a flapping-wing robot.” J. Aerosp. Eng. 32 (3): 04019018. https://doi.org/10.1061/(ASCE)AS.1943-5525.0000997.
ATSB (Australian Transport Safety Bureau). 2008. Transport safety report, aviation occurrence investigation. AO-2008-070, Interim Factual. Canberra, ACT, Australia: ATSB.
ATSB (Australian Transport Safety Bureau). 2009. “Qantas Airbus A330 incident.” Accessed September 14, 2023. http://www.atsb.gov.au/newsroom/2009/release/2009_01.aspx.
Balaban, M. E., and E. Kartal. 2019. Veri Madenciliği ve Makine Öğrenmesi. İstanbul, Turkey: Çağlayan Kitabevi.
Barthe, J. 2007. “Unreliable speed.” Safety first. Accessed September 5, 2007. https://safetyfirst.airbus.com/app/themes/mh_newsdesk/documents/archives/unreliable-speed.pdf.
Bilgin, M. 2020. Makine Öğrenmesi. İstanbul, Turkey: Papatya Yayınları.
Boeing. 1997. 737-600/-700/-800/-900 operations manual. Arlington County, VA: Boeing.
Calia, A., E. Denti, R. Galatolo, and F. Schettini. 2008. “Air data computation using neural networks.” J. Aircr. 45 (6): 2078–2083. https://doi.org/10.2514/1.37334.
Collinson, R. P. 2023. Introduction to avionics systems. New York: Springer.
Coyne, J. 2000. AD/INST/45 Honeywell air data inertial reference units 6/2000 DM. Canberra, Australia: Civil Aviation Safety Authority, Commonwealth of Australia.
EASA (European Aviation Safety Agency). 2023. EASA artificial intelligence roadmap 2.0: A human-centric approach to AI in aviation. Cologne, Germany: EASA.
FAA (Federal Aviation Administration). 2005. Airworthiness directives; Boeing model 777 Airplanes: 14 CFR Part 39. Washington, DC: FAA.
FAA (Federal Aviation Administration). 2012. Flight-critical systems design assurance. Washington, DC: FAA.
Gao, Z., Z. Xiang, M. Xia, and H. Wang. 2022. “Adaptive air-data estimation in wind disturbance based on flight data.” J. Aerosp. Eng. 35 (2): 04021126. https://doi.org/10.1061/(ASCE)AS.1943-5525.0001379.
Garcia, A. B., R. F. Babiceanu, and R. Seker. 2021. “Artificial intelligence and machine learning approaches for aviation cybersecurity: An overview.” In Proc., IEEE Integrated Communications Navigation and Surveillance Conf. (ICNS), 1–8. New York: IEEE. https://doi.org/10.1109/ICNS52807.2021.9441594.
Gauber, J. 2016. Currently developing and future communications and technology impact on AMDAR instruments and observing methods. Geneva: World Meteorological Organization.
Hradecky, S. 2009. “Crash: Air France A332 over Atlantic on Jun 1st 2009, aircraft impacted ocean.” Accessed September 14, 2023. http://avherald.com/h?article=41a81ef1/0004&opt=0.
Kumar, M., M. Hanumanthappa, and T. V. S. Kumar. 2012. “Intrusion Detection System using decision tree algorithm.” In Proc., 2012 IEEE 14th Int. Conf. on Communication Technology 629–634. New York: IEEE.
Lerro, A., P. Gili, M. L. Fravolini, and M. Napolitano. 2021. “Experimental analysis of neural approaches for synthetic angle-of-attack estimation.” Int. J. Aerosp. Eng. 2021 (Mar): 1. https://doi.org/10.1155/2021/9982722.
Li, R., C. Lu, J. Liu, and T. Lei. 2018. “Air data estimation algorithm under unknown wind based on information fusion.” J. Aerosp. Eng. 31 (5): 04018072. https://doi.org/10.1061/(ASCE)AS.1943-5525.0000889.
Lie, F. A. P., and D. Gebre-Egziabher. 2013. “Synthetic air data system.” J. Aircr. 50 (4): 1234–1249. https://doi.org/10.2514/1.C032177.
Lim, H., H. Ryu, M. B. Rhudy, D. Lee, D. Jang, C. Lee, Y. Park, W. Youn, and H. Myung. 2022. “Deep learning–aided synthetic airspeed estimation of UAVs for analytical redundancy with a temporal convolutional network.” IEEE Rob. Autom. Lett. 7 (1): 17–24. https://doi.org/10.1109/LRA.2021.3117021.
NTSB (National Transportation Safety Board). 2009. “NTSB investigating two recent incidents involving possible A-330 speed and altitude indication anomalies.” Accessed September 14, 2023. https://www.ntsb.gov/Pages/home.aspx.
Roman, I., R. Santana, A. Mendiburu, and J. A. Lozano. 2019. “Evolving Gaussian Process kernels from elementary mathematical expressions.” Preprint, submitted April 23, 2018. https://arxiv.org/abs/1910.05173.
Ryu, H., C. Lee, Y. Park, M. B. Rhudy, D. Lee, D. Jang, and W. Youn. 2022. “In-flight estimation of drag parameters and air data for unmanned aircraft.” J. Aerosp. Inf. Syst. 19 (3): 166–178. https://doi.org/10.2514/1.I010967.
SAE. 2001. “ARINC 738-3rd·738-3 air data and inertial reference system (ADIRS).” Accessed September 9, 2023. https://aviation-ia.sae-itc.com/standards/arinc738-3-738-3-air-data-inertial-reference-system-adirs.
Shmelova, T., A. Sterenharz, and S. Dolgikh. 2020. “Artificial intelligence in aviation industries: Methodologies, education, applications, and opportunities.” In Handbook of research on artificial intelligence applications in the aviation and aerospace industries, 1–35. Hershey, PA: IGI Global.
Tiassou, K., K. Kanoun, M. Ka, C. Seguin, and C. Papadopoulos. 2011. “Modeling aircraft operational reliability.” In Proc., Computer Safety, Reliability, and Security, 157–170. New York: Springer.
Turkmen, I., and S. Arik. 2017. “A new alternative air data computation method based on artificial neural networks.” J. Aeronaut. Space Technol. 10 (1): 21–29.
Yang, J., Z. Wu, K. Peng, P. N. Okolo, W. Zhang, H. Zhao, and J. Sun. 2021. “Parameter selection of Gaussian kernel SVM based on local density of training set.” Inverse Probl. Sci. Eng. 29 (4): 536–548. https://doi.org/10.1080/17415977.2020.1797716.
Youn, W., H. Lim, H. S. Choi, M. B. Rhudy, H. Ryu, S. Kim, and H. Myung. 2021. “State estimation for HALE UAVs with deep-learning-aided virtual AOA/SSA sensors for analytical redundancy.” IEEE Rob. Autom. Lett. 6 (3): 5276–5283. https://doi.org/10.1109/LRA.2021.3074084.
Information & Authors
Information
Published In
Journal of Aerospace Engineering
Volume 37 • Issue 6 • November 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Sep 21, 2023
Accepted: Apr 17, 2024
Published online: Jul 27, 2024
Published in print: Nov 1, 2024
Discussion open until: Dec 27, 2024
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.