Comparison of machine learning algorithms performance in predictive maintenance of turbofan engines

Year 2024, , 99 - 106, 15.01.2024

Osman Güler

https://doi.org/10.28948/ngumuh.1266541

Abstract

One of the important steps taken within the scope of Industry 4.0 is predictive maintenance studies. In this way, machine and equipment life is extended and working efficiency is increased. Predictive maintenance studies of aircraft and aircraft engines are important, especially since flight safety is of vital importance in the aviation industry. In this study, 10 different machine learning algorithms were used to predict the remaining useful life of turbofan engines and their results were compared. For the trainings, the CMAPSS dataset, which shows the working conditions of turbofan engines under certain conditions, presented by NASA was used. The results of the study show that machine learning models generally achieve similar performance to each other. As a result of the experiments, it was seen that the LDA algorithm was the most successful algorithm.

Keywords

Machine learning, Predictive maintenance, NASA Turbofan dataset, Aircraft engine, Remaining useful life

Turbofan motorlarının kestirimci bakımında makine öğrenimi algoritmaları performanslarının karşılaştırılması

Abstract

Endüstri 4.0 kapsamında atılan önemli adımlardan birisi kestirimci bakım çalışmalarıdır. Bu sayede makine ve ekipman ömrünü uzatılmakta, çalışma verimliliği artırılmaktadır. Özellikle havacılık sanayii alanında uçuş güvenliği hayati önem taşıdığından dolayı, uçakların ve uçak motorlarının kestirimci bakım çalışmaları önemlidir. Bu çalışmada, turbofan motorlarının kalan faydalı ömrünü tahmin etmek için 10 farklı makine öğrenmesi algoritmaları kullanılmış ve sonuçları karşılaştırılmıştır. Eğitimler için NASA tarafından sunulan turbofan motorların belirli koşullar altında çalışma durumlarını gösteren CMAPSS veriseti kullanılmıştır. Çalışma sonuçları makine öğrenmesi modellerinin genel olarak birbirlerine yakın performans elde ettiğini göstermektedir. Yapılan deneyler sonucunda LDA algoritmasının en başarılı algoritma olduğu görülmüştür.

Keywords

Makine Öğrenmesi, Kestirimci Bakım, NASA Turbofan Veri Seti, Uçak Motoru, Kalan Faydalı Ömür

References

• D. Rengasamy, H.P. Morvan and G.P. Figueredo, Deep learning approaches to aircraft maintenance, repair and overhaul: A review. 21st International Conference on Intelligent Transportation Systems, pp. 150-156, IEEE, 2018.
• K.T. Nguyen and K. Medjaher, A new dynamic predictive maintenance framework using deep learning for failure prognostics. Reliability Engineering & System Safety, 188, 251-262, 2019. https://doi.org/10.1016/j.ress.2019.03.018
• I. Mallidis, V. Yakavenka, A. Konstantinidis and N. Sariannidis, A goal programming-based methodology for machine learning model selection decisions: a predictive maintenance application. Mathematics, 9(19), 2405, 2021. https://doi.org/10.3390/math9192405
• A.P. Hermawan, D.S. Kim and J.M. Lee, Predictive maintenance of aircraft engine using deep learning technique. International Conference on Information and Communication Technology Convergence (ICTC), pp. 1296-1298, IEEE, 2020. http://dx.doi.org/10.1109/ICTC49870.2020.9289466
• S. Savaş, K. Duraklar, O.A. Çınar, M. Koç, A. Turan, U. Uslu, A.S. Doğanay, O.G. Özceyhan, M.Y. Destan and H. Duşbudak, Güneş enerjisi sistemlerinde yenilikçi ve akıllı bakım onarım. Journal of Information Systems and Management Research, 4(2), 35-49, 2022.
• M.A. Kızrak and B. Bolat, Uçak motoru sağlığı için uzun-kısa süreli bellek yöntemi ile öngörücü bakım. Bilişim Teknolojileri Dergisi, 12(2), 103-109, 2019. https://doi.org/10.17671/gazibtd.495730
• A.N. Abbas, G. Chasparis and J.D. Kelleher, Interpretable hidden markov model-based deep reinforcement learning hierarchical framework for predictive maintenance of turbofan engines. arXiv preprint arXiv:2206.13433, 2022. https://doi.org/10.48550/arXiv.2206.13433
• M.D. Dangut, Z. Skaf and I.K. Jennions, Handling imbalanced data for aircraft predictive maintenance using the BACHE algorithm. Applied Soft Computing, 123, 108924, 2022. https://doi.org/10.1016/j.asoc.2022.108924
• L. Xu, S.F.,Yuan, J. Chen and Q. Bao, Deep learning based fatigue crack diagnosis of aircraft structures. In Proceedings of the 7th Asia-Pacific Workshop on Structural Health Monitoring, 2018.
• S. Vollert and A. Theissler, Challenges of machine learning-based RUL prognosis: A review on NASA's C-MAPSS data set. In 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation, pp. 1-8, IEEE, 2021, September. http://dx.doi.org/10.1109/ETFA45728.2021.9613682
• D. Bruneo and F. De Vita, On the use of LSTM networks for predictive maintenance in smart industries. In 2019 ieee international conference on smart computing (smartcomp), pp. 241-248, IEEE, 2019. https://doi.org/10.1109/SMARTCOMP.2019.00059
• H.V. Düdükçü, M. Taşkıran and N. Kahraman, LSTM and WaveNet implementation for predictive maintenance of turbofan engines. In 2020 IEEE 20th International Symposium on Computational Intelligence and Informatics, pp. 000151-000156, IEEE, 2020.
• V. Mathew, T. Toby, V. Singh, B.M. Rao and M.G. Kumar, Prediction of remaining useful lifetime (RUL) of turbofan engine using machine learning. In 2017 IEEE international conference on circuits and systems (ICCS), pp. 306-311, IEEE, 2017.
• K. Khan, M. Sohaib, A. Rashid, S. Ali, H. Akbar, A. Basit and T. Ahmad, Recent trends and challenges in predictive maintenance of aircraft’s engine and hydraulic system. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 43, 1-17, 2021. http://dx.doi.org/10.1007/s40430-021-03121-2
• K.Ç. Girgin and C. Zalluhoğlu, Öznitelik odaklı sensor verisi bazlı uçak motorları geriye kalan faydalı ömür tahminleme. Avrupa Bilim ve Teknoloji Dergisi, 37, 21-27, 2022. https://doi.org/10.31590/ejosat.1125433
• S. Pillai and P. Vadakkepat, Two stage deep learning for prognostics using multi-loss encoder and convolutional composite features. Expert Systems with Applications, 171, 114569, 2021. http://dx.doi.org/10.1016/j.eswa.2021.114569
• A. Siddique, R.K. Kundu, G.R. Mode and K.A. Hoque, RobustPdM: designing robust predictive maintenance against adversarial attacks. arXiv preprint arXiv: 2301.10822, 2023. https://doi.org/10.48550/arXiv.2301.10822
• D.K. Frederick, J.A. Decastro and J.S. Litt. Users guide for the commercial modular aero-propulsion system simulation (c-mapss). Tech. Rep. NASA/TM2007- 215026, 2007.
• A. Saxena, K. Goebel, D. Simon and N. Eklund, Damage propagation modeling for aircraft engine run-to-failure simulation. In 2008 international conference on prognostics and health management, pp. 1-9, IEEE, 2008. http://dx.doi.org/10.1109/PHM.2008.4711414
• H.A. Gohel, H. Upadhyay, L. Lagos, K. Cooper and A. Sanzetenea, Predictive maintenance architecture development for nuclear infrastructure using machine learning. Nuclear Engineering and Technology, 52(7), 1436-1442, 2020. https://doi.org/10.1016/j.net.2019.12.029
• Ö.Ç. Yavuz, E. Karaman and C. Yeşilyaprak, Makine öğrenmesi algoritmalarıyla astronomik gözlem kalitesi tahminine yönelik karar destek sistemi geliştirilmesi ve uygulanması. Trends in Business and Economics, 36(3), 289-303, 2022. http://doi.org/10.5152/TBE.2022.1049957
• A.B. Andre, E. Beltrame and J. Wainer, A combination of support vector machine and k-nearest neighbors for machine fault detection. Applied Artificial Intelligence, 27(1), 36-49, 2013. http://dx.doi.org/10.1080/08839514.2013.747370
• F. Arena, M. Collotta, L. Luca, M. Ruggieri and F.G. Termine, Predictive maintenance in the automotive sector: A literature review. Mathematical and Computational Applications, 27(1), 2, 2022. https://doi.org/10.3390/mca27010002
• S.R. Safavian and D. Landgrebe, A survey of decision tree classifier methodology. IEEE transactions on systems, man, and cybernetics, 21(3), 660-674, 1991.
• Z.M. Çınar, A. Abdussalam Nuhu, Q. Zeeshan, O. Korhan, M. Asmael and B. Safaei, Machine learning in predictive maintenance towards sustainable smart manufacturing in industry 4.0. Sustainability, 12(19), 8211, 2020.
• Y. Freund and R.E. Schapire, A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences, 55(1), 119-139, 1997. https://doi.org/10.1006/jcss.1997.1504
• T. Chen and C. Guestrin, Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp. 785-794, 2016.
• G.I. Webb, E. Keogh and R. Miikkulainen, Naïve Bayes. Encyclopedia of machine learning, 15, 713-714, 2010.
• S. Savaş, Naive Bayes Sınıflandırıcısı. Teori ve Uygulamada Makine Öğrenmesi, (69-92), Nobel Akademik Yayıncılık, Ankara, 2022.
• L. Bottou, Large-scale machine learning with stochastic gradient descent. In Proceedings of COMPSTAT'2010: 19th International Conference on Computational Statistics Paris France, August 22-27, 2010 Keynote, Invited and Contributed Papers, pp. 177-186, Physica-Verlag HD, 2010. https://doi.org/10.1007/978-3-7908-2604-3_16
• P. Xanthopoulos, P.M. Pardalos and T.B. Trafalis, Linear discriminant analysis. Robust data mining, 27-33, 2013. http://dx.doi.org/10.1007/978-1-4419-9878-1