PROSPECTS FOR USING AI METHODS TO PREDICT THE GLACIATION OF UAV BEARING SURFACES
Abstract
Icing of aircraft lifting surfaces is a safety risk factor in both civil and military aviation. Ice accretion on lifting surfaces leads to degradation of the aerodynamic characteristics of the aircraft, reducing the maximum lift coefficient by 20–80% and increasing the drag coefficient by 50–100%. The problem is particularly acute for small unmanned aerial vehicles (UAV), which operate at low Reynolds numbers and cannot utilize traditional anti-icing systems due to weight, size, and power constraints. This study aims to comprehensively analyze current research on aircraft component icing processes and evaluate prospects for applying machine learning methods to predict ice accretion. The research presents a systematic review of physical mechanisms governing rime, glaze, and mixed ice formation, experimental testing methods in icing wind tunnels, and contemporary CFD tools (LEWICE, FENSAP-ICE, GlennICE). The study substantiates the feasibility of hybrid CFD–ML approaches where traditional numerical simulations generate training datasets for constructing fast surrogate models. Using 3,200 icing simulations on the symmetric NACA0012 airfoil across wide ranges of six governing parameters (velocity, angle of attack, temperature, LWC, MVD, exposure time), a multilayer perceptron was developed to predict iced profile contour coordinates. The model demonstrates mean absolute error of 0.741 cm (1.5% chord) on the test set, with highest accuracy for rime ice (0.11 cm) and acceptable results for more complex glaze and mixed ice morphologies. Results confirm the neural network approach effectiveness as a rapid engineering analysis tool and establish foundations for integrating such models into automated design systems and adaptive ice protection systems for UAV. The developed methodology enables real-time ice shape prediction without computational overhead of full CFD simulations, facilitating development of intelligent anti-icing systems.
Downloads
References
Mclean, Jr., J. (1986). Determining the effects of weather in aircraft accident investiga-tions. У 24th aerospace sciences meeting. Amer-ican Institute of Aeronautics and Astro-nautics. https://doi.org/10.2514/6.1986-323
Li, S., & Paoli, R. (2022). Aircraft icing severity evaluation. Encyclopedia, 2(1), 56–69. https://doi.org/10.3390/encyclope-dia2010005
Li, S., Qin, J., He, M., & Paoli, R. (2020). Fast evaluation of aircraft icing severity using machine learning based on xgboost. Aero-space, 7(4), 36. https://doi.org/10.3390/aero-space7040036
Cao, Y., Tan, W., & Wu, Z. (2018). Air-craft icing: An ongoing threat to aviation safety. Aerospace Science and Technology, 75, 353–385. https://doi.org/10.1016/j.ast.2017.12.028
Løw-Hansen, B., Hann, R., Stov-ner, B. N., & Johansen, T. A. (2023). UAV ic-ing: A survey of recent developments in ice de-tection methods. IFAC-PapersOnLine, 56(2), 10727-10739. https://doi.org/10.1016/j.ifacol.2023.10.733
Cui, Y., Chen, W., Dai, N., & Han, C. (2024). Integrated technologies for anti-deicing functions and structures of aircraft: Current sta-tus and development trends. Aerospace, 11(10), 821. https://doi.org/10.3390/aero-space11100821
Hann, R. (2018). UAV icing: Compari-son of LEWICE and FENSAP-ICE for ice ac-cretion and performance degradation. У 2018 at-mospheric and space environments conference. American Institute of Aeronautics and Astro-nautics. https://doi.org/10.2514/6.2018-2861
Botura, G., & Fahrner, A. (2003). Icing detection system - conception, development, testing and applicability to uavs. У 2nd AIAA "unmanned unlimited" conf. and workshop & exhibit. American Institute of Aeronautics and Astronautics. https://doi.org/10.2514/6.2003-6637
Abdelghany, E. S., Farghaly, M. B., Almalki, M. M., Sarhan, H. H., & Essa, M. E.-S. M. (2023). Machine learning and iot trends for intelligent prediction of aircraft wing anti-ic-ing system temperature. Aerospace, 10(8), 676. https://doi.org/10.3390/aero-space10080676
Alekseyenko, S., & Yushkevich, О. (2019). The development of a three-dimensional model of the ice growth process on aerodynamic surfaces. Technology Audit and Production Re-serves, 4(1(48)), 11–18. https://doi.org/10.15587/2312-8372.2019.145296
Prikhod’ko, A. A., Alekseenko, S. V., & Chmovzh, V. V. (2019). Experimental investiga-tion of the influence of the shape of ice out-growths on the aerodynamic characteristics of the wing. Journal of Engineering Physics and Thermophysics, 92(2), 486–492. https://doi.org/10.1007/s10891-019-01955-1
Prykhodko, A. A., Alekseyenko, S. V., & Prikhodko, V. V. (2019). Numerical investi-gation of the influence of horn ice formation on airfoils aerodynamic performances. Interna-tional Journal of Fluid Mechanics Re-search, 46(6), 499–508. https://doi.org/10.1615/interjfluidme-chres.2019026024
Arizmendi, B., Bellosta, T., del Val, A. I., Gori, G., Prazeres, M. O., & Reis, J. (2019). On real-time management of on-board ice protection systems by means of machine learning. У AIAA aviation 2019 forum. Ameri-can Institute of Aeronautics and Astro-nautics. https://doi.org/10.2514/6.2019-3464
Li, S., Qin, J., & Paoli, R. (2021). Data-Driven machine learning model for aircraft icing severity evaluation. Journal of Aerospace Infor-mation Systems, 1–5. https://doi.org/10.2514/1.i010978
El-Sayed, A. F. (2022). Numerical stud-ies for the interaction of solid and liquid debris with aircraft modules. У Foreign object debris and damage in aviation (с. 447–508). CRC Press. https://doi.org/10.1201/9781003133087-10
Potapczuk, M. G. (2013). Aircraft icing research at NASA glenn research center. Journal of Aerospace Engineering, 26(2), 260–276. https://doi.org/10.1061/(asce)as.1943-5525.0000322
Anderson, D. (1994). Rime-, mixed- and glaze-ice evaluations of three scaling laws. У 32nd aerospace sciences meeting and exhibit. American Institute of Aeronautics and Astro-nautics. https://doi.org/10.2514/6.1994-718
Wright, W. B., Gent, R. W., & Guffond, D. (1997, May 1). DRA/NASA/ONERA Collabora-tion on Icing Research: Prediction of Airfoil ICE Accretion - Part 2. NASA Technical Reports Server (NTRS). https://ntrs.nasa.gov/cita-tions/19970023937
Britton, R., & Bond, T. (1991). A review of ice accretion data from a model rotor icing test and comparison with theory. У 29th aero-space sciences meeting. American Institute of Aeronautics and Astro-nautics. https://doi.org/10.2514/6.1991-661
Dai, H., Zhu, C., Zhao, H., & Liu, S. (2021). A new ice accretion model for aircraft icing based on phase-field method. Applied Sci-ences, 11(12), 5693. https://doi.org/10.3390/app11125693
Alekseyenko, S., Sinapius, M., Schulz, M., & Prykhodko, O. (2015). Interac-tion of supercooled large droplets with aerody-namic profile. У SAE 2015 international confer-ence on icing of aircraft, engines, and structures. SAE Interna-tional. https://doi.org/10.4271/2015-01-2118
Hansman, R., Jr, Breuer, K., Hazan, D., Reehorst, A., & Vargas, M. (1993). Close-up analysis of aircraft ice accretion. 31st Aerospace Sciences Meeting. https://doi.org/10.2514/6.1993-29
Janjua, Z. A., Turnbull, B., Hibberd, S., & Choi, K. (2018). Mixed ice accretion on air-craft wings. Physics of Fluids, 30(2). https://doi.org/10.1063/1.5007301
Bragg, M., Broeren, A., Addy, H., Potapczuk, M., Guffond, D., & Montreuil, E. (2007). Airfoil Ice-Accretion Aerodynamic Sim-ulation. 45th AIAA Aerospace Sciences Meeting and Exhibit. https://doi.org/10.2514/6.2007-85
Muddisetty, H., Karanam, S. a. K., Vasquez, R. M. H., Effendy, F., Muthu, G., Dixit, C. K., & Subramanian, S. (2024). Air craft aer-odynamics and ice accretion effects. AIP Con-ference Proceedings, 3029, 020041. https://doi.org/10.1063/5.0218223
Hedde, T., & Guffond, D. (1995). ON-ERA three-dimensional icing model. AIAA Journal, 33(6), 1038–1045. https://doi.org/10.2514/3.12795
Broeren, A. P., Lee, S., & Clark, C. (2015). Aerodynamic effects of Anti-Icing fluids on a thin High-Performance wing section. Jour-nal of Aircraft, 53(2), 451–462. https://doi.org/10.2514/1.c033384
Szilder, K., & Yuan, W. (2017). In-flight icing on unmanned aerial vehicle and its aerody-namic penalties. Progress in Flight Physics, 173–188. https://doi.org/10.1051/eu-cass/2016090173
Muhammed, M., & Virk, M. S. (2022). ICE accretion on Fixed-Wing Unmanned Aerial Vehicle—A review study. Drones, 6(4), 86. https://doi.org/10.3390/drones6040086
Ruff, G. A., & Berkowitz, B. M. (1990, May 1). Users Manual for the NASA Lewis ICE Accretion Prediction Code (LEWICE). NASA Technical Reports Server (NTRS). https://ntrs.nasa.gov/citations/19900011627
Glenn Icing Computational Environment (GLeNNICE)(LEW-20155-1) | NASA Software Catalog. (n.d.). https://software.nasa.gov/software/LEW-20155-1
Morency, F., Beaugendre, H., Baruzzi, G., & Habashi, W. (2001). FENSAP-ICE - A comprehensive 3D simulation system for in-flight icing. У 15th AIAA computational fluid dynamics conference. American Institute of Aeronautics and Astro-nautics. https://doi.org/10.2514/6.2001-2566
Li, S., & Paoli, R. (2019). Modeling of Ice Accretion over Aircraft Wings Using a Com-pressible OpenFOAM Solver. International Journal of Aerospace Engineering, 2019, 1–11. https://doi.org/10.1155/2019/4864927
Du, J., Guo, Q., Yue, Y., Ma, Y., & Cheng, H. (2025). Rapid prediction of ice accre-tion on swept wings based on proper orthogonal decomposition and surrogate modelling. Journal of Applied Fluid Mechanics, 18(8). https://doi.org/10.47176/jafm.18.8.3278
Johnson, M., & Rokhsaz, K. (2000). Us-ing Artificial Neural Networks and self-organiz-ing maps for detection of airframe icing. Atmos-pheric Flight Mechanics Conference. https://doi.org/10.2514/6.2000-4099
Aykan, R., Hajiyev, C., & Çalişkan, F. (2005). Kalman filter and neural network‐based icing identification applied to A340 aircraft dy-namics. Aircraft Engineering and Aerospace Technology, 77(1), 23–33. https://doi.org/10.1108/00022660510576019
Ding, D., Qian, W. Q., & Wang, Q. (2020). Aircraft inflight icing detection based on statistical decision theory. IOP Conference Se-ries Materials Science and Engineering, 751(1), 012054. https://doi.org/10.1088/1757-899x/751/1/012054
Ding, D., Qian, W. Q., & Wang, Q. (2021). Aircraft Wing ICE Online Detection and Fault-Tolerant Control Law design. 2021 China Automation Congress (CAC), 2520–2525. https://doi.org/10.1109/cac53003.2021.9728535
Melody, J. W., Hillbrand, T., Başar, T., & Perkins, W. R. (2001). H∞ parameter identifica-tion for inflight detection of aircraft icing: the time-varying case. Control Engineering Prac-tice, 9(12), 1327–1335. https://doi.org/10.1016/s0967-0661(01)00081-8
Ying, S., Ge, T., & Ai, J. (2013). H ∞ pa-rameter identification and H 2 feedback control synthesizing for inflight aircraft icing. Journal of Shanghai Jiaotong University (Science), 18(3), 317–325. https://doi.org/10.1007/s12204-013-1401-6
Dong, Y. (2018). An application of Deep Neural Networks to the in-flight parameter iden-tification for detection and characterization of aircraft icing. Aerospace Science and Technol-ogy, 77, 34–49. https://doi.org/10.1016/j.ast.2018.02.026
Chen, T., & Guestrin, C. (2016). XGBOOST: a scalable tree boosting System. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1603.02754
Li, S., Qin, J., He, M., & Paoli, R. (2020). Fast evaluation of aircraft icing severity using machine learning based on XGBOOST. Aerospace, 7(4), 36. https://doi.org/10.3390/aer-ospace7040036
Martin, J. D., & Simpson, T. W. (2005). Use of kriging models to approximate determin-istic computer models. AIAA Journal, 43(4), 853–863. https://doi.org/10.2514/1.8650
Shon, S., Kang, Y., Hong, Y., Yee, K., & Myong, R. S. (2021). Design of hybrid airfoils for icing tunnel tests based on Reduced-Order modeling methods. Journal of Aircraft, 59(4), 847–860. https://doi.org/10.2514/1.c036435
Broeren, A. P., Addy, H. E., Jr, Bragg, M. B., Busch, G. T., & Montreuil, E. (2011, June 1). Aerodynamic Simulation of Ice Accretion on Airfoils. NASA Technical Reports Server (NTRS). https://ntrs.nasa.gov/cita-tions/2011001336
Copyright (c) 2025 Володимир Стрембовський, Артур Круглий (Автор)
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in the journal Journal of Rocket-Space Technology are licensed under the Creative Commons Attribution 4.0 International (CC BY) license. This means that you are free to:
- Share, copy, and redistribute the article in any medium or format
- Adapt, remix, transform, and build upon the article
as long as you provide appropriate credit to the original work, include the authors' names, article title, journal name, and indicate that the work is licensed under CC BY. Any use of the material should not imply endorsement by the authors or the journal.
