Climb Performance Prediction in High Drag Configuration Middle-Class Transportation Aircraft: An Ensemble Learning Approach

Year 2024, , 235 - 242, 22.10.2024

Hamdi Ercan , Mustafa Akın , Bayram Taşdelen

https://doi.org/10.30518/jav.1515233

Abstract

This study addresses the application of machine learning and artificial neural network models for predicting the climb speed of the C-130H military transport aircraft. Random Forest, Neural Network, and Ensemble models were developed to overcome limitations of traditional chart reading and interpolation methods. Models were trained on flight manual data, considering factors such as gross weight, pressure altitude, drag index, temperature deviation, and engine efficiency. Comparative analysis revealed the Ensemble approach, combining Random Forest and Neural Network techniques, provided the highest accuracy (R² ≈ 0.4532), followed by Random Forest (R² ≈ 0.4303) and Neural Network (R² ≈ 0.3765) models. All significantly outperformed the traditional Young Method (R² = -1.2673). Feature importance analysis identified pressure altitude, gross weight, and engine efficiency as critical factors influencing climb speed. The ensemble approach demonstrated more reliable and accurate results in predicting C-130H climb rates, reducing risks associated with single-model reliance. This research highlights the potential of machine learning in aircraft performance prediction, offering possibilities for improving pre-flight preparation, reducing workload, and enhancing flight safety. Implications for the aviation industry and future research directions are discussed, emphasizing the role of advanced predictive models in shaping future flight operations and aircraft performance management.

Keywords

C-130H Aircraft, Flight Performance, Performance Optimization, Climb Speed Prediction, Artificial Neural Network, Machine Learning

References

• Altuntaş, Y. (2007). Uçak Kara Kutusundan Alınan Kayıtların Yapay Sinir Ağları İle İncelenmesi [Analysis of Aircraft Black Box Records With Artificial Neural Networks], Haliç University, Institute of Science, Master's Thesis, İstanbul. 83s.
• Arık, S. (2014). Yapay Sinir Ağları Kullanılarak Hava Veri Bilgisayarı Parametrelerinin Hesaplanması [The Calculations of Air Data Parameters Using Artificial Neural Networks], Erciyes University, Institute of Science, Master's Thesis, Kayseri, 86 s.
• Aslantaş, V. and Kemal, G., (2002). Yapay Sinir Ağlarının C-130 Uçaklarının Sürat Hesaplarına Uygulanması [Application of Artificial Neural Networks to Speed Calculations of C-130 Aircraft]. 4th Aviation Symposium, Kayseri, 310-315.
• Baklacıoğlu, T. (2010). Uçak Performans Modellemesi [Aircraft performance modelling], Anadolu University Graduate School of Natural and Applied Science, Doctoral Dissertation, Eskişehir. 142s.
• Batchelor, G. K. (1967). An Introduction to Fluid Dynamics, Cambridge Univ. Press, Cambridge, 1-536.
• Boztepe, A. B., Çelik, B., Bahtışen, Ü., Tombul, F., Kınacı, İ. (2001). 030 Uçuş Performansı ve Planlama-II [030 Flight Performance and Planning-II], Türk Hava Kurumu (Turkish Aeronautical Association), Ankara, 1-249
• Cutler, A., Cutler, D. R., & Stevens, J. R. (2012). Random Forests. Ensemble Machine Learning: Methods and Applications, 157-175.
• Dong, X., Yu, Z., Cao, W., Shi, Y., and Ma, Q. (2020) A Survey On Ensemble Learning. Frontiers of Computer Science, 14(2), 241-258.
• Eken, A. (2009). Uçak Performans Hesaplamalarına Yönelik Yazılım Geliştirilmesi [Development of Software for Aircraft Performance Calculations], Istanbul Technical University, Institute of Science, Master Thesis, İstanbul. 91s.
• Erdmański, M. and Szymaniec, K. (2010). Performance Characteristic of C-130E Hercules Aircraft Engine Under
• Variable Work Conditions. Combustion Engines, 142(3), 41-47.
• Fenar, S., Ercan, H., and Tekin, S. A., (2014). Icing Prediction Model Using Artificial Neural Network For Aircraft Modernization. The First International Symposium on Industrial Design Engineering (ISIDE14), 189-192.
• Filippone, A., (2008). Comprehensive Analysis of Transport Aircraft Flight Performance. Progress in Aerospace Sciences, 44(3), 192-236.
• Güleç, K. (2002). C-130 Uçaklarının Performans Hesaplamalarında Yapay Sinir Ağının Kullanılması [Using Artificial Neural Network in Performance Calculations of C-130 Aircraft], Erciyes University, Institute of Science, Master's Thesis, Kayseri. 68s.
• Guzel, K., Bilgin, G., (2019). Derin Ögrenilen Özellikler Toplulugu Kullanarak Kolon Kanser Görüntülerinde Çekirdeklerin Sınıflandırılması [Classification of Nuclei in Colon Cancer Images using Ensemble of Deep Learned Features]. Tıp Teknolojileri Kongresi (Medical Technologies Congress - TIPTEKNO 2019), Aydın, 181-184.
• Ilbas, M. and Turkmen, M. (2012). Turbofan Motorlarda Egzoz Gaz Sıcaklığının Yapay Sinir Ağları ile Tahmin Edilmesi [Prediction of Exhaust Gas Temperature in Turbofan Engines with Artificial Neural Networks]. Isı Bilimi ve Tekniği Dergisi (Journal of Thermal Science and Technology), 32(2), 11-18.
• Konar, M., Oktay, T., Şahin, H., (2020). Döner Kanatlı Hava Araçlarının Uçuş Performans Optimizasyonu [Flight Performance Optimization of Rotary Wing Aircraft]. International 5th January Congress of Applied Sciences, Adana, 11-15.
• Matloob, F., Ghazal, T. M., Taleb, N., Aftab, S., Ahmad, M., Khan, M. A., Abbas, S., and Soomro, T. R. (2021) Software Defect Prediction Using Ensemble Learning: A Systematic Literature Review. IEEE Access. 9, 98754-98771.
• Oktay, T. and Özgür, B., (2022). Turboprop Motorlu Askeri Uçaklarda Uçuş Performansının İrdelenmesi ve İyileştirilmesi [Investigation and Improvement of Flight Performance of Military Aircraft with Turboprop Engines]. Ankara 7th International Scientific Research Congress, Ankara, 1629-1634.
• Pooley Dorothy, S. and Robson, D. (2010) The Air Pilot's Manual 3: Air Navigation. 6(3), Pooley's Air Pilot Publishing, West Sussex, 1-363.
• Sağiroğlu, Ş., Erler, M. & Beşdok, E. (2003). Mühendislikte Yapay Zeka Uygulamaları-I: Yapay Sinir Ağları [Artificial Intelligence Applications in Engineering-I: Artificial Neural Networks]. Kayseri: Ufuk Kitabevi2003, pp.410
• Temel, R. (2017). Uçak Kara Kutusundan Alınan Veriler Kullanılarak Hücum Açısı ve Mach Sayısının YSA ve ANFIS İle Tahmini [Prediction of Angle of Attack and Mach Number with ANN and ANFIS Using Data from Aircraft Black Box], Erciyes University, Institute of Science, Master's Thesis, Kayseri, 90 s.
• Türkmen, İ. and Arik, S., (2017). A New Alternative Air Data Computation Method Based on Artifıcial Neural Networks. Journal of Aeronautics and Space Technologies, 10(1), 21-29.
• Türkmen, İ. and Temel, R., (2022). Uçak Kara Kutusundan Alınan Veriler Kullanılarak Uçuş Parametrelerinin Yapay Sinir Ağı ile Analizi ve Tahmini [Artificial Neural Network Analysis and Prediction of Flight Parameters Using Data from Aircraft Black Box]. 7th International Congress on Engineering and Technology Management, 1, 750-757.
• United States Air Forces (USAF) Series, (2002). C-130 Aircraft Flight Manual Performance Data, T.O. 1C-130H-1-1, USAF Technical Order, USA, 1-856.
• Yildirim Dalkiran, F. and Toraman, M., (2021). Predicting Thrust of Aircraft Using Artificial Neural Networks. Aircraft Engineering and Aerospace Technology, 93(1), 35-41.
• Yildirim, M. T. and Kurt, B., (2017). Investigation of Low-Pressure Turbine and Aircraft Performance Parameters Through Multiple Regression Analysis. Journal of Aeronautics and Space Technologies, 10(2), 31-36.
• Young, A. (2019). Analysis of Best Climb Speed in High Drag C-130Variants, https://breezymint.com/img/FourEngine/Four_Engine_Climb-3.pdf