Elif KARTAL, Zeki ÖZEN, Sevinç GÜLSEÇEN, İlker Güven YILMAZ

Havacılık Endüstrisinde Yakıt Taşımacılığının Makine Öğrenmesi Algoritmaları ile Tahmini

Yakıt taşımacılığı, kalkış ve varış meydanı arasındaki yakıt fiyatı farklılıklarından kaynaklanan yakıt giderlerini azaltmak için kullanılan bir yöntemdir. Gelecek uçuş için gerekli olan yakıtın kârlı taşınmasını sağlamaktadır. Literatürde yakıt taşımacılığı hesaplamasında kullanılan bazı temel özelleştirilebilir formüller/modeller mevcuttur; ancak formüllerin/modellerin özelleştirilebilir olması, hesaplama yapan araştırmacılar için farklı parametre tercihlerini (hava durumu, rota gibi) ortaya koymakta ve buna bağlı olarak da yakıt taşımacılığı için elde edilecek sonuçların değişkenlik gösterebileceğine işaret etmektedir. Ayrıca, günümüzde yapay zekânın yakıt taşımacılığı öngörüsünde kullanıldığı bir çalışma literatürde bulunamamıştır. Bu çalışmada bahsi geçen bu formüllerden/modellerden bağımsız olarak ham veriden öğrenen makine öğrenmesi algoritmaları ile havacılık endüstrisinde yakıt taşımacılığı öngörüsünde bulunmak hedeflenmiştir. Çalışmanın sonuçlarına göre, en iyi performans geri besleme algoritmasının kullanıldığı Yapay Sinir Ağları modeli ile elde edilmiştir (doğruluk=0.838). Ayrıca, bu YSA modeliyle yakıt taşımacılığı öngörüsünde bulunulan çevrimiçi bir uygulama geliştirilmiştir. Bu çalışma, havacılık şirketlerinin kullandığı yakıt taşımacılığı hesaplamalarına alternatif olarak farklı bir bakış açısı sağlayacaktır.

Prediction of Fuel Tankering in Aviation Industry with Machine Learning Algorithms

Fuel tankering is a method that is used in the aviation industry to reduce fuel expenses inflicted by fuel price differences between departure and arrival airport. It provides profitable transport of required fuel for the scheduled upcoming flight. Today, there are a number of basic customizable formulas/models used in the fuel tankering calculation referred in the literature; however, the customizability of the formulas/models reveals different parameter preferences (such as weather, route, etc.) for the researchers making calculations, and consequently, the results to be obtained for fuel tankering may vary. Besides, an artificial intelligence study, which may be used in fuel tankering estimation/prediction, could not be found in the literature. In this study, it is aimed to predict fuel tankering in the airline industry with machine learning algorithms that learn from raw data which is independent from these formulas/models. According to the results of the study, the best performance is obtained with Artificial Neural Networks by using the Backpropagation algorithm (accuracy = 0.838). Furthermore, an online application for predicting fuel tankering is developed with the ANN model. This study will provide a different and rather an alternative insight to the fuel tankering calculations that are used by aviation companies.

PDF

___

[1] C. Barnhart, P. Belobaba, and A. R. Odoni, "Applications of Operations Research in the Air Transport Industry", Transportation Science, vol. 37, no. 4, pp. 368-391, November 2003,
[2] Boeing, ‘Boeing: Commercial Market Outlook’. [Online] http://www.boeing.com/commercial/market/commerci al-market-outlook/. [Accessed: Aug. 03, 2020].
[3] V. Singh and S. K. Sharma, "Fuel consumption optimization in air transport: a review, classification, critique, simple meta-analysis, and future research implications", European Transport Research Review, vol. 7, no. 2, pp. 1-24, June 2015.
[4] M. Naumann and L. Suhl, "How does fuel price uncertainty affect strategic airline planning?", Operational Research, vol. 13, no. 3, pp. 343-362, October 2013.
[5] U.S. Energy Information Administration, "U.S. Gulf Coast Kerosene-Type Jet Fuel Spot Price FOB (Dollars per Gallon)", [Online]. https://www.eia.gov/dnav/pet/hist/LeafHandler.ashx?n =PET&s=EER_EPJK_PF4_RGC_DPG&f=A [Accessed: June 17, 2020].
[6] FAA, ‘Air Traffic By The Numbers’. [Online]. Available: https://www.faa.gov/air_traffic/by_the_numbers/ [Accessed: October 07, 2020].
[7] DHMİ, ‘Statistics’. [Online]. Available: https://dhmi.gov.tr/Sayfalar/Istatistikler.aspx [Accessed: July 26, 2020].
[8] EUROCONTROL, ‘DATA’, Skyway Magazine, vol. Spring/Summer, no. 70, p. 12-14, March 2019.
[9] V. K. Rao, "Fuel price risk management using futures", Journal of Air Transport Management, vol. 5, no. 1, pp. 39-44, January 1999
[10] Air Transport Action Group (ATAG), The economic & social benefits of air transport, 2011. [Online]. Available: http://www.icao.int/Meetings/wrdss2011/Documents/J ointWorkshop2005/ATAG_SocialBenefitsAirTranspo rt.pdf [Accessed: Feb. 10, 2017].
[11] U.S. Energy Information Administration, "International Energy Statistics - World Regions", Feb. 2019. [Online]. Available: https://www.eia.gov/beta/international/data/browser/#/ ?pa=0000000000g&c=4100000002000060000000000 000g000200000000000000001&tl_id=5- A&vs=~~~~~~~~~~~~~~~~INTL.63-2-AFRC- TBPD.A~~INTL.63-2-ASOC-TBPD.A~~INTL.63-2- CSAM-TBPD.A~~INTL.63-2-EURA- TBPD.A~~INTL.63-2-EURO-TBPD.A~~INTL.63-2- MIDE-TBPD.A~~INTL.63-2-NOAM- TBPD.A~~~~INTL.63-2-WORL- TBPD.A&cy=2013&vo=0&v=C&start=2000&end=2 016 [Accessed: Feb. 02, 2017].
[12] The International Air Transport Association, Economic performance of the airline industry, 2018. [Online]. Available: http://www.iata.org/publications/economics/Reports/I ndustry-Econ-Performance/IATA-Economic- Performance-of-the-Industry-end-year-2018- report.pdf.
[13] M. S. Ryerson, M. Hansen, and J. Bonn, Fuel consumption and operational performance, 2011, [Online]. Available: http://atmseminar.org/seminarContent/seminar9/paper s/72-Ryerson-Final-Paper-4-14-11.pdf. [Accessed: Jan. 25, 2017].
[14] M. Lindgren and J. Brynhagen, Fuel Tankering - for Flygprestanda AB’s flight planning system, Bachelor Dissertation, Department of Computer Engineering, Lund University, Helsingborg, 2012.
[15] V. Singh, S. K. Sharma, and S. Vaibhav, ‘Modeling the civil aircraft operations for the optimization of fuel consumption in Indian air transport industry’, Industrial Engineering Letters, vol. 2, no. 7, pp. 20-29, January 2012.
[16] A. Filippone, The Universty of Manchester, Case Study Fuel Tankering: Is it Worth it?, 2015. http://www.flight.mace.manchester.ac.uk/aircraft- performance-software/case-studies/by- solution/11_CS_Fuel_Tankering.pdf [Accessed Feb. 13, 2017].
[17] J. A. T. Guerreiro Fregnani, C. Müller, and A. R. Correia, "A fuel tankering model applied to a domestic airline network", J. Adv. Transp., vol. 47, no. 4, pp. 386-398, June 2013.
[18] C. Mair et al., "An investigation of machine learning based prediction systems", Journal of Systems and Software, vol. 53, no. 1, pp. 23-29, July 2000.
[19] A. Filippone, Advanced Aircraft Flight Performance. Cambridge University Press, 2012.
[20] Boeing, Flight Operations Engineering, Boeing Commercial Airplanes, Fuel Conservation, 2004. [Online]. Available: http://www.phenom.aero/resources/library/fuel_conser vation.pdf. [Accessed: Jan. 31, 2017].
[21] T. Hubert, C. Guo, C. A. Mouton, and J. D. Powers, Tankering fuel on U.S. Air Force transport aircraft: an assessment of cost savings, Rand Corporation, Santa Monica, California, 2015. [Online]. Available: http://www.rand.org/content/dam/rand/pubs/research_ reports/RR800/RR837/RAND_RR837.pdf. [Accessed: Feb. 13, 2017].
[22] B. Nash, "A Simplified Alternative to Current Airline Fuel Allocation Models", Interfaces, vol. 11, no. 1, pp. 1-9, February 1981.
[23] W. J. Lesinski, "Tankering Fuel: A Cost Saving Initiative", Graduate Research Paper, Graduate School of Engineering and Management, Air Force Institute of Technology, Air University, Air Education and Training Command, 2011.
[24] Airbus, Getting To Grips With Fuel Economy, Flight Operations Support & Line Assistance, no. 4, 2004. [Online]. Available: https://ansperformance.eu/library/airbus-fuel- economy.pdf [Accessed: Aug. 03, 2020 ]
[25] J. Peroyea, "Aircraft Ferry Fuel Calculator", Aircraft Ferry Fuel Calculator, 2017. http://www.ferryfuelcalculator.com/ [Accessed: Jan. 26, 2017].
[26] FuelerLinx, "FuelerLinx - Aviation Jet Fuel Planning & Tankering Software for Enhanced Flight Planning", 2015. [Online]. Available: https://fuelerlinx.com/Landing/index.html#. [Accessed: Jan. 26, 2017].
[27] Cockpit Apps LLC., "iFuel – Fuel Tankering App", Cockpit Apps, 2016. [Online]. Available: http://www.cockpitapps.com/aviation-apps/ifuel-fuel- tankering-app. [Accessed: Jan. 26, 2017].
[28] İ. E. Emre, N. Erol, Y. İ. Ayhan, Y. Özkan, and Ç. Erol, "The analysis of the effects of acute rheumatic fever in childhood on cardiac disease with data mining", International Journal of Medical Informatics, vol. 123, pp. 68-75, March 2019.
[29] E. Kartal and M. E. Balaban, "Machine learning techniques in cardiac risk assessment", Turkish Journal of Thoracic and Cardiovascular Surgery, vol. 26, no. 3, pp. 394-401, July 2018.
[30] I. Smeureanu, G. Ruxanda, and L. M. Badea, ‘Customer segmentation in private banking sector using machine learning techniques’, Journal of Business Economics and Management, vol. 14, no. 5, pp. 923-939, November 2013,
[31] P. Flach, Machine Learning: The Art and Science of Algorithms that Make Sense of Data, 1st ed. Glasgow, UK: Cambridge University Press, 2012.
[32] P. Domingos, ‘A few useful things to know about machine learning’, Communications of the ACM, vol. 55, no. 10, pp. 78-87, October 2012.
[33] E. Kurklu, R. A. Morris, and N. Oza, "Machine Learning for Earth Observation Flight Planning Optimization", Association for the Advancement of Artificial Intelligence, 2007, [Online]. Available: https://ntrs.nasa.gov/search.jsp?R=20090026327. [Accessed: Mar. 07, 2017]
[34] J. K. Williams, "Using random forests to diagnose aviation turbulence", Mach Learn, vol. 95, pp. 51-70, April 2014.
[35] A. Collins and L. Thomas, "Comparing reinforcement learning approaches for solving game theoretic models: a dynamic airline pricing game example", Journal of the Operational Research Society, vol. 63, no. 8, pp. 1165-1173, August 2012.
[36] S. A. H. O. Ali, "Optimization of Economic Fuelling for The Fokker 70/100". VU University Amsterdam, 2010, [Online]. Available: https://beta.vu.nl/nl/Images/stageverslag- aithaddououali_tcm235-159729.doc. [Accessed: Mar. 07, 2020].
[37] P. Korvesis, "Machine Learning for Predictive Maintenance in Aviation", Artificial Intelligence, Universite Paris-Saclay, 2017.
[38] A. Rahim Taleqani, K. Nygard, R. Bridgelall, and J. Hough, "Machine Learning Approach to Cyber Security in Aviation", 2018 IEEE International Conference on Electro/Information Technology (EIT). IEEE, 3-5 May 2018, pp. 0147-0152.
[39] OpenAirlines, "SkyBreathe Fuel Management Software", OpenAirlines, 2020. [Online]. Available: https://openairlines.com/fuel-management-software/ [Accessed: May 29, 2020].
[40] OpenAirlines, "MyFuelCoach, Pilot Engagement Ap"’, OpenAirlines, 2020. [Online]. Available: https://openairlines.com/pilot-engagement-app/ [Accessed: May 29, 2020].
[41] Honeywell, "Introducing Honeywell Forge", Aircraft | Honeywell Forge, 2020. [Online]. Available: https://www.honeywell.com/content/honeywell/us/en/ honeywell-forge/aircraft.html. [Accessed: May 29, 2020].
[42] Honeywell, "Honeywell Forge Flight Efficiency", 2020. [Online]. Available: https://aerospace.honeywell.com/content/aero/en/us/h ome/learn/services/flight-services/flight- efficiency.html. [Accessed: May 29, 2020].
[43] C. Shearer, "The CRISP-DM model: the new blueprint for data mining", Journal of data warehousing, vol. 5, no. 4, pp. 13-22, January 2000.
[44] SAS Institute Inc., "How do I interpret the Shapiro-Wilk test for normality in JMP?", 2017. [Online]. Available: http://www.jmp.com/support/notes/35/406.html [Accessed: Jun. 28, 2017].
[45] Laerd Statistics, ‘Spearman’s Correlation in Stata’, 2013. [Online]. Available: https://statistics.laerd.com/stata-tutorials/spearmans- correlation-using-stata.php.
[46] T. Wei and V. Simko, "corrplot: Visualization of a Correlation Matrix", 2016. [Online]. Available: https://CRAN.R-project.org/package=corrplot. [Accessed: Jun. 28, 2017].
[47] J. Han and M. Kamber, Data mining: concepts and techniques (the Morgan Kaufmann Series in data management systems), 2nd Edition. Morgan Kaufmann Publishers, 2006.
[48] Z. Özen and S. Gülseçen, R ile Geri Yayılım Yapay Sinir Ağı Algoritması Kullanarak Bir Sınıflandırma Uygulaması, in R ile Veri Madenciliği Uygulamaları, 1. Baskı., M. E. Balaban and E. Kartal, Eds. İstanbul: Çağlayan Kitabevi, 2016, pp. 73–99.
[49] M. E. Balaban and E. Kartal, Veri Madenciliği ve Makine Öğrenmesi Temel Algoritmaları ve R Dili ile Uygulamaları, Birinci Baskı. İstanbul: Çağlayan Kitabevi, 2015.
[50] M. Sarkar and T.-Y. Leong, ‘Application of K- nearest neighbors algorithm on breast cancer diagnosis problem.’, in Proceedings of the AMIA Symposium, 2000, p. 759, Accessed: Mar. 22, 2017. [Online]. Available: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2243 774/. [Accessed: Jun. 28, 2017].
[51] P. Harrington, Machine Learning in Action, 1st Edition. Shelter Island, NY: Manning Publications, 2012.
[52] I. H. Witten, E. Frank, and M. A. Hall, Data Mining: Practical Machine Learning Tools and Techniques, Third Edition, 3rd ed. Morgan Kaufmann, 2011.
[53] K. Adhatrao, A. Gaykar, A. Dhawan, R. Jha, and V. Honrao, "Predicting Students’ Performance Using ID3 and C4.5 Classification Algorithms", International Journal of Data Mining & Knowledge Management Process, vol. 3, no. 5, pp. 39-52, Sepember 2013.
[54] S. Miertschin, ‘Decision Trees’, 2017. [Online]. Available: http://www.uh.edu/~smiertsc/4397cis/C4.5_Decision_ Tree_Algorithm.pdf. [Accessed: Jun. 28, 2019].
[55] B. Boutsinas and I. X. Tsekouronas, ‘Splitting Data in Decision Trees Using the New False-Positives Criterion’, in Proceedings of Methods and Applications of Artificial Intelligence: Third Helenic Conference on AI, G. A. Vouros and T. Panayiotopoulos, Eds. Springer, 2004, pp. 174-182.
[56] B. Hssina, A. Merbouha, H. Ezzikouri, and M. Erritali, "A comparative study of decision tree ID3 and C 4.5", International Journal of Advanced Computer Science and Applications, vol. 4, no. 2, pp. 13-19, Jully 2014.
[57] G. H. John and P. Langley, "Estimating Continuous Distributions in Bayesian Classifiers", in Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence, San Francisco, CA, USA, 1995, pp. 338-345.
[58] J. E. Dayhoff and J. M. DeLeo, "Artificial neural networks", Cancer, vol. 91, no. S8, pp. 1615-1635, April 2001.
[59] C. Bitter, J. North, D. A. Elizondo, and T. Watson, "An Introduction to Use of Neural Networks for Network Intrusion Detection", in Computational Intelligence for Privacy and Security, D. Elizondo, A. Solanas, and A. Martinez-Balleste, Eds. Springer, 2012.
[60] A. Abraham, "Artificial Neural Networks", in Handbook of Measuring System Design, John Wiley & Sons, Ltd, 2005.
[61] Z. Özen, ‘Kimlik Doğrulaması için Tuş Vuruş Dinamiklerine Dayalı Bir Güvenlik Sisteminin Yapay Sinir Ağları ile Geliştirilmesi’, Doktora Tezi, İstanbul Üniversitesi Fen Bilimleri Enstitüsü, İstanbul, 2016.
[62] D. Svozil, V. Kvasnicka, and J. Pospichal, "Introduction to multi-layer feed-forward neural networks", Chemometrics and Intelligent Laboratory Systems, vol. 39, no. 1, pp. 43-62, November 1997.
[63] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagating errors", Nature, vol. 323, no. 6088, pp. 53-536, October 1986.
[64] D. Graupe, Advanced Series in Circuits and Systems - Principles of Artificial Neural Networks, 3rd edition, vol. 7. Singapore: World Scientific Publishing Co. Pte. Ltd., 2013.
[65] R Core Team, R: A Language and Environment for Statistical Computing. Vienna, Austria: R Foundation for Statistical Computing, 2017.
[66] RStudio, RStudio: Integrated development environment for R. Boston, MA.: RStudio, 2017.
[67] M. Kuhn, "caret: Classification and Regression Training", cran.r-project.org, March 20, 2020. [Online]. Available: https://CRAN.R- project.org/package=caret. [Accessed: Jun. 28, 2020].
[68] W. N. Venables and B. D. Ripley, Modern Applied Statistics with S, Fourth. New York: Springer, 2002.
[69] M. Walesiak and A. Dudek, "clusterSim: Searching for Optimal Clustering Procedure for a Data Set", cran.r-project.org, Jul. 20, 2020. [Online]. Available: https://CRAN.R- project.org/package=clusterSim. [Accessed: Aug. 28, 2020].
[70] D. Meyer, E. Dimitriadou, K. Hornik, A. Weingessel, and F. Leisch, "e1071: Misc Functions of the Department of Statistics, Probability Theory Group (Formerly: E1071), TU Wien", cran.r-project.org, 2015. [Online]. Available: https://CRAN.R- project.org/package=e1071. [Accessed: Aug. 28, 2020].
[71] S. Fritsch and F. Guenther, "neuralnet: Training of Neural Networks", cran.r-project.org, 2016. [Online]. Available: https://CRAN.R- project.org/package=neuralnet. [Accessed: Aug. 28, 2020].
[72] T. Hothorn and A. Zeileis, "partykit: A Modular Toolkit for Recursive Partytioning in R", Journal of Machine Learning Research, vol. 16, pp. 3905-3909, December 2015.
[73] H. Wickham, "The split-apply-combine strategy for data analysis", Journal of Statistical Software, vol. 40, no. 1, pp. 1-29, April 2011.
[74] K. Hornik, C. Buchta, and A. Zeileis, "Open- Source Machine Learning: R Meets Weka", Computational Statistics, vol. 24, no. 2, pp. 225-232, May 2009.
[75] I. H. Witten and E. Frank, Data Mining: Practical machine learning tools and techniques, 2nd Edition. Morgan Kaufmann, 2005.
[76] W. Chang, ‘shinythemes: Themes for Shiny’, cran.r-project.org, 2016. [Online]. Available: https://CRAN.R-project.org/package=shinythemes. [Accessed: Aug. 28, 2020].
[77] C. Müssel, L. Lausser, M. Maucher, and H. A. Kestler, "Multi-Objective Parameter Selection for Classifiers", Journal of Statistical Software, vol. 46, no. 5, pp. 1-27, January 2012.
[78] S. Sun, C. Wang, H. Ding, and Q. Zou, "Machine learning and its applications in plant molecular studies", Briefings in Functional Genomics, vol. 19, no. 1, pp. 40-48, January 2020.
[79] RStudio, "Shiny", shiny.rstudio.com, 2016. https://shiny.rstudio.com/ [Accessed: March 21, 2017].
[80] RStudio, "shinyapps.io", 2017. [Online]. Available: http://www.shinyapps.io/ [Accessed: March 21, 2017].