Araştırma Makalesi
BibTex RIS Kaynak Göster

Kalkış safhasında uçak motorlarından kaynaklanan görsel duman yoğunluğunun yapay sinir ağları ile tahmin edilmesi

Yıl 2025, Cilt: 8 Sayı: 2, 147 - 157, 25.10.2025
https://doi.org/10.51513/jitsa.1692078

Öz

Uçak motorlarından kaynaklanan emisyonların azaltılmasına yönelik çalışmalar, yüksek teknoloji ve önemli maliyetler gerektiren süreçleri içermektedir. Bu çalışmada, kalkış safhasındaki uçak motorlarından yayılan görsel duman yoğunluğunu tahmin etmek amacıyla yenilikçi bir yapay sinir ağı (YSA) modeli geliştirilmiştir. Modellemede, Uluslararası Sivil Havacılık Örgütü’nün (ICAO) Aircraft Engine Emissions Databank (EEDB) veri seti kullanılmış ve tahmin doğruluğunu artırmak için çeşitli eğitim algoritmaları değerlendirilmiştir. Çalışmada, YSA’nın doğrusal ve doğrusal olmayan ilişkileri öğrenme kapasitesinden yararlanılmış ve en başarılı tahminleme yöntemi olarak Levenberg-Marquardt (trainlm) algoritması belirlenmiştir. Modelin performans değerlendirmesinde ortalama karesel hata, ortalama mutlak hata ve korelasyon katsayısı hesaplanmıştır. Sonuçlar, trainlm algoritmasıyla eğitilen YSA modelinin en düşük hata oranlarıyla en yüksek doğruluk seviyesine ulaştığını göstermektedir. Geliştirilen YSA modeli, uçak motorlarından kaynaklanan zararlı emisyonların azaltılmasına yönelik yeni bir bakış açısı sunarak sürdürülebilir havacılık uygulamalarına katkı sağlamaktadır. Ayrıca, modelin havaalanı çevresindeki hava kalitesinin iyileştirilmesi ve emisyon yönetiminin optimize edilmesi açısından önemli bir potansiyele sahip olduğu değerlendirilmektedir. Bu bağlamda çalışma havacılık sektörünün sürdürülebilirlik hedeflerine ulaşmasına destek sağlayacak ileri düzey bir tahminleme yaklaşımı ortaya koymaktadır.

Kaynakça

  • Agarwal, A., Speth, R. L., Fritz, T. M., Jacob, S. D., Rindlisbacher, T., Iovinelli, R., & Barrett, S. R. (2019). SCOPE11 method for estimating aircraft black carbon mass and particle number emissions. Environmental Science & Technology, 53(3), 1364–1373. https://doi.org/10.1021/acs.est.8b04060
  • Ateş, K. T. (2022). Investigation of factors affecting compressive strength of cement and concrete with prediction methods used in artificial intelligence algorithms. International Journal of Advances in Engineering and Pure Sciences, 34(2), 242–261. https://doi.org/10.7240/jeps.1013130
  • Brink, L. F. J. (2020). Modeling the impact of fuel composition on aircraft engine NOx, CO and soot emissions. (Doctoral dissertation, Massachusetts Institute of Technology). Retrieved from https://dspace.mit.edu/handle/1721.1/129181
  • Christie, S., Lobo, P., Lee, D., & Raper, D. (2017). Gas turbine engine nonvolatile particulate matter mass emissions: correlation with smoke number for conventional and alternative fuel blends. Environmental Science & Technology, 51(2), 988-996. https://doi.org/10.1021/acs.est.6b03766
  • Deng L, Chen Q, He Y, Sui X, Wang Q. (2021), Detection of smoke from infrared image frames in the aircraft cargoes. International Journal of Distributed Sensor Networks, 17(4). https://doi.org/10.1177/15501477211009808
  • Ge, F., Yu, Z., Li, Y., Zhu, M., Zhang, B., Zhang, Q., & Chen, L. (2022). Predicting aviation non-volatile particulate matter emissions at cruise via convolutional neural network. Science of The Total Environment, 850, 158089. https://doi.org/10.1016/j.scitotenv.2022.158089
  • International Civil Aviation Organization. (2020). Airport air quality manual (Doc 9889). Erişim: 03 Nisan, 2025, https://www.icao.int/publications/documents/9889_cons_en.pdf
  • International Civil Aviation Organization. (2024). ICAO Aircraft Engine Emissions Databank. Erişim: 01 Kasım, 2024, https://www.easa.europa.eu/en/domains/environment/icao-aircraft-engine-emissions-databank
  • Jagtap, S. S., Childs, P. R., & Stettler, M. E. (2024). Conceptual design-optimisation of a future hydrogen-powered ultrahigh bypass ratio geared turbofan engine. International Journal of Hydrogen Energy, 95, 317-328. https://doi.org/10.1016/j.ijhydene.2024.10.329
  • Kılıç, İ., Aydın, M., & Şahin, H. (2024). Predicting battery capacity with artificial neural networks. Akıllı Ulaşım Sistemleri ve Uygulamaları Dergisi, 7(2), 99-112. https://doi.org/10.51513/jitsa.1380584
  • Kodak, G. (2024). An Investigation on the use of air quality models in ship emission forecasts. Akıllı Ulaşım Sistemleri ve Uygulamaları Dergisi, 7(1), 15-30. https://doi.org/10.51513/jitsa.1425614
  • Kurt, B. (2024a). Prediction of performance degradation in aircraft engines with fuel flow parameter. Neural Computing and Applications, 36(6), 2973-2982. https://doi.org/10.1007/s00521-023-09174-9
  • Kurt, B. (2024b). Evaluation of aircraft engine performance during takeoff phase with machine learning methods. Neural Computing and Applications, 36(30), 19173-19190. https://doi.org/10.1007/s00521-024-10220-3
  • Ma, S., Lin, S., Han, B., Zhang, C., Wei, Z., Xue, L., & Hopke, P. K. (2025). Revealing considerable emissions reduction potential in flight operations: A real-time emission perspective. Transportation Research Part D: Transport and Environment, 143, 104745. https://doi.org/10.1016/j.trd.2025.104745
  • Martini, B. (2008). Development and assessment of a soot emissions model for aircraft gas turbine engines. (Doctoral dissertation, Massachusetts Institute of Technology). Retrieved from https://dspace.mit.edu/handle/1721.1/45256
  • Mumcu, B., & Meşhur, H. F. A. (2025). Yapay Zekâ ve Yeşil Ulaşım Birlikteliğinin Kente Etkileri. Akıllı Ulaşım Sistemleri ve Uygulamaları Dergisi, 8(1), 66-89. https://doi.org/10.51513/jitsa.1529225
  • Oruc, R. (2025). Prediction of emission and exergy parameters of commercial high by-pass turbofan engines based on CSA-SVR model. Journal of Thermal Analysis and Calorimetry, 1-13. https://doi.org/10.1007/s10973-025-14403-5
  • Qasem, M. A. A., Al-Mutairi, E. M., & Jameel, A. G. A. (2023). Smoke point prediction of oxygenated fuels using neural networks. Fuel, 332, 126026. https://doi.org/10.1016/j.fuel.2022.126026
  • Stettler, M. E., Swanson, J. J., Barrett, S. R., & Boies, A. M. (2013). Updated correlation between aircraft smoke number and black carbon concentration. Aerosol Science and Technology, 47(11), 1205-1214. https://doi.org/10.1080/02786826.2013.829908
  • Taşar, B., Üneş, F., Demirci, M., & Kaya, Y. Z. (2018). Yapay sinir ağları yöntemi kullanılarak buharlaşma miktarı tahmini. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 9(1), 543-551.
  • Trivanovic, U., & Pratsinis, S. E. (2023). Opinion: Eliminating aircraft soot emissions. Aerosol Research Discussions, 2023, 1-17. https://doi.org/10.5194/ar-2-207-2024
  • Wayson, R. L., Fleming, G. G., & Iovinelli, R. (2009). Methodology to estimate particulate matter emissions from certified commercial aircraft engines. Journal of the Air & Waste Management Association, 59(1), 91-100. https://doi.org/10.3155/1047-3289.59.1.91
  • Yavuz, S., & Deveci, M. (2012). İstatiksel normalizasyon tekniklerinin yapay sinir ağin performansina etkisi. Erciyes Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, (40), 167-187.
  • Zou, R., Wang, B., Wang, K., Shang, W. L., Xue, D., & Ochieng, W. Y. (2025). A pathway to sustainable aviation: Modeling aircraft takeoff mass for precise fuel consumption and aircraft emission calculations. Energy, 319, 135074. https://doi.org/10.1016/j.energy.2025.135074

Prediction of the smoke number from aircraft engines during the takeoff phase using artificial neural networks

Yıl 2025, Cilt: 8 Sayı: 2, 147 - 157, 25.10.2025
https://doi.org/10.51513/jitsa.1692078

Öz

Studies aimed at reducing emissions from aircraft engines involve processes that require high technology and significant costs. In this study, an innovative artificial neural network (ANN) model was developed to predict the number of smoke emissions from aircraft engines during the takeoff phase. The modeling process utilized the International Civil Aviation Organization’s (ICAO) Aircraft Engine Emissions Databank (EEDB) dataset, and various training algorithms were evaluated to enhance prediction accuracy. The study leveraged the ANN’s ability to learn both linear and nonlinear relationships, identifying the Levenberg-Marquardt (trainlm) algorithm as the most effective prediction method. For the model's performance evaluation, mean squared error, mean absolute error , and the correlation coefficient were calculated. The results demonstrated that the ANN model trained with the trainlm algorithm achieved the highest accuracy with the lowest error rates. The developed ANN model offers a new perspective for reducing harmful emissions from aircraft engines, contributing to sustainable aviation practices. Furthermore, the model is considered to have significant potential in improving air quality around airports and optimizing emissions management. In this context, the study presents an advanced prediction approach that supports the aviation sector’s sustainability goals.

Kaynakça

  • Agarwal, A., Speth, R. L., Fritz, T. M., Jacob, S. D., Rindlisbacher, T., Iovinelli, R., & Barrett, S. R. (2019). SCOPE11 method for estimating aircraft black carbon mass and particle number emissions. Environmental Science & Technology, 53(3), 1364–1373. https://doi.org/10.1021/acs.est.8b04060
  • Ateş, K. T. (2022). Investigation of factors affecting compressive strength of cement and concrete with prediction methods used in artificial intelligence algorithms. International Journal of Advances in Engineering and Pure Sciences, 34(2), 242–261. https://doi.org/10.7240/jeps.1013130
  • Brink, L. F. J. (2020). Modeling the impact of fuel composition on aircraft engine NOx, CO and soot emissions. (Doctoral dissertation, Massachusetts Institute of Technology). Retrieved from https://dspace.mit.edu/handle/1721.1/129181
  • Christie, S., Lobo, P., Lee, D., & Raper, D. (2017). Gas turbine engine nonvolatile particulate matter mass emissions: correlation with smoke number for conventional and alternative fuel blends. Environmental Science & Technology, 51(2), 988-996. https://doi.org/10.1021/acs.est.6b03766
  • Deng L, Chen Q, He Y, Sui X, Wang Q. (2021), Detection of smoke from infrared image frames in the aircraft cargoes. International Journal of Distributed Sensor Networks, 17(4). https://doi.org/10.1177/15501477211009808
  • Ge, F., Yu, Z., Li, Y., Zhu, M., Zhang, B., Zhang, Q., & Chen, L. (2022). Predicting aviation non-volatile particulate matter emissions at cruise via convolutional neural network. Science of The Total Environment, 850, 158089. https://doi.org/10.1016/j.scitotenv.2022.158089
  • International Civil Aviation Organization. (2020). Airport air quality manual (Doc 9889). Erişim: 03 Nisan, 2025, https://www.icao.int/publications/documents/9889_cons_en.pdf
  • International Civil Aviation Organization. (2024). ICAO Aircraft Engine Emissions Databank. Erişim: 01 Kasım, 2024, https://www.easa.europa.eu/en/domains/environment/icao-aircraft-engine-emissions-databank
  • Jagtap, S. S., Childs, P. R., & Stettler, M. E. (2024). Conceptual design-optimisation of a future hydrogen-powered ultrahigh bypass ratio geared turbofan engine. International Journal of Hydrogen Energy, 95, 317-328. https://doi.org/10.1016/j.ijhydene.2024.10.329
  • Kılıç, İ., Aydın, M., & Şahin, H. (2024). Predicting battery capacity with artificial neural networks. Akıllı Ulaşım Sistemleri ve Uygulamaları Dergisi, 7(2), 99-112. https://doi.org/10.51513/jitsa.1380584
  • Kodak, G. (2024). An Investigation on the use of air quality models in ship emission forecasts. Akıllı Ulaşım Sistemleri ve Uygulamaları Dergisi, 7(1), 15-30. https://doi.org/10.51513/jitsa.1425614
  • Kurt, B. (2024a). Prediction of performance degradation in aircraft engines with fuel flow parameter. Neural Computing and Applications, 36(6), 2973-2982. https://doi.org/10.1007/s00521-023-09174-9
  • Kurt, B. (2024b). Evaluation of aircraft engine performance during takeoff phase with machine learning methods. Neural Computing and Applications, 36(30), 19173-19190. https://doi.org/10.1007/s00521-024-10220-3
  • Ma, S., Lin, S., Han, B., Zhang, C., Wei, Z., Xue, L., & Hopke, P. K. (2025). Revealing considerable emissions reduction potential in flight operations: A real-time emission perspective. Transportation Research Part D: Transport and Environment, 143, 104745. https://doi.org/10.1016/j.trd.2025.104745
  • Martini, B. (2008). Development and assessment of a soot emissions model for aircraft gas turbine engines. (Doctoral dissertation, Massachusetts Institute of Technology). Retrieved from https://dspace.mit.edu/handle/1721.1/45256
  • Mumcu, B., & Meşhur, H. F. A. (2025). Yapay Zekâ ve Yeşil Ulaşım Birlikteliğinin Kente Etkileri. Akıllı Ulaşım Sistemleri ve Uygulamaları Dergisi, 8(1), 66-89. https://doi.org/10.51513/jitsa.1529225
  • Oruc, R. (2025). Prediction of emission and exergy parameters of commercial high by-pass turbofan engines based on CSA-SVR model. Journal of Thermal Analysis and Calorimetry, 1-13. https://doi.org/10.1007/s10973-025-14403-5
  • Qasem, M. A. A., Al-Mutairi, E. M., & Jameel, A. G. A. (2023). Smoke point prediction of oxygenated fuels using neural networks. Fuel, 332, 126026. https://doi.org/10.1016/j.fuel.2022.126026
  • Stettler, M. E., Swanson, J. J., Barrett, S. R., & Boies, A. M. (2013). Updated correlation between aircraft smoke number and black carbon concentration. Aerosol Science and Technology, 47(11), 1205-1214. https://doi.org/10.1080/02786826.2013.829908
  • Taşar, B., Üneş, F., Demirci, M., & Kaya, Y. Z. (2018). Yapay sinir ağları yöntemi kullanılarak buharlaşma miktarı tahmini. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 9(1), 543-551.
  • Trivanovic, U., & Pratsinis, S. E. (2023). Opinion: Eliminating aircraft soot emissions. Aerosol Research Discussions, 2023, 1-17. https://doi.org/10.5194/ar-2-207-2024
  • Wayson, R. L., Fleming, G. G., & Iovinelli, R. (2009). Methodology to estimate particulate matter emissions from certified commercial aircraft engines. Journal of the Air & Waste Management Association, 59(1), 91-100. https://doi.org/10.3155/1047-3289.59.1.91
  • Yavuz, S., & Deveci, M. (2012). İstatiksel normalizasyon tekniklerinin yapay sinir ağin performansina etkisi. Erciyes Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, (40), 167-187.
  • Zou, R., Wang, B., Wang, K., Shang, W. L., Xue, D., & Ochieng, W. Y. (2025). A pathway to sustainable aviation: Modeling aircraft takeoff mass for precise fuel consumption and aircraft emission calculations. Energy, 319, 135074. https://doi.org/10.1016/j.energy.2025.135074
Toplam 24 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Modelleme ve Simülasyon, Hava Kirliliği Modellemesi ve Kontrolü, Hava Kirliliği ve Gaz Arıtma, Hava-Uzay Ulaşımı
Bölüm Makaleler
Yazarlar

Bülent Kurt 0000-0002-1741-5427

Erken Görünüm Tarihi 22 Ekim 2025
Yayımlanma Tarihi 25 Ekim 2025
Gönderilme Tarihi 5 Mayıs 2025
Kabul Tarihi 3 Eylül 2025
Yayımlandığı Sayı Yıl 2025 Cilt: 8 Sayı: 2

Kaynak Göster

APA Kurt, B. (2025). Kalkış safhasında uçak motorlarından kaynaklanan görsel duman yoğunluğunun yapay sinir ağları ile tahmin edilmesi. Akıllı Ulaşım Sistemleri ve Uygulamaları Dergisi, 8(2), 147-157. https://doi.org/10.51513/jitsa.1692078