Öznitelik Odaklı Sensor Verisi Bazlı Uçak Motorları Geriye Kalan Faydalı Ömür Tahminleme

Year 2022, Issue: 37, 21 - 27, 15.07.2022

Kemal Çağlar Girgin , Cemil Zalluhoğlu

https://doi.org/10.31590/ejosat.1125433

Abstract

Uçak motorunun durumu, uçağın güvenliğini, uçuş kalitesini ve çalışmasını doğrudan etkiler. Uçak motorları için belirti izleme faaliyetleri, motorun kalan faydalı ömrünü tahmin etmek için bir önceden önlem alınmasını sağlayabilecek bir avantaj yaratabilir. Uçak motoru yapıları hem soyut hem de somut bileşenlerle karmaşık olduğundan, motor faaliyet bozulma sürecini göstermek oldukça zahmetlidir. Bu yazıda, kalan faydalı ömür tahmini doğruluğunu iyileştirmek için öznitelik odaklı çerçeve geliştirilmiştir. Bu çerçeve, motorlardan gelen gereksiz duyusal girdileri ortadan kaldırır ve hesaplama maliyetlerini düşürür. Bir uygulama örneği olarak, sensör verilerine dayalı olarak uçak motorunun kalan faydalı ömrünü tahmin etmek için geliştirilmiş öznitelik odaklı çerçeve kullanılmıştır. Sonuçlar, diğer yöntemleri uygulamadan önce, birçok girdi özelliğine sahip sistemlerin, maliyeti düşürmek için özellik uyarlama prosedürlerine ihtiyaç duyduğunu, ancak kalan faydalı ömrü tahmin etmek için kesinliği artırdığını göstermektedir.

Keywords

Uçak Motor, Veri Madenciliği, Makine Öğrenmesi, Destek Vektör Makineleri, Lojistik Regresyon, Doğrusal Regresyon, NASA Turbofan Veri Seti, Öznitelik Seçme, PCA

Thanks

Çalışma kapsamında önce kendime sonra her zorlukta yanımda olan ailem Mustafa Girgin, Candan Girgin ve İremsu Girgin’e ve son olarak çalışmaya olan tüm yardımlarından dolayı Cemil Zalluhoğlu’na teşekkürlerimi sunarım.

Feature-Oriented Remaining Useful Life Prediction of Aircraft Engines Based on Sensor Data

Abstract

Aircraft engine’s condition straightforwardly influences the security, unwavering quality, and operation of the aircraft. Prognostics and wellbeing administration for aircraft engines can give a advantage to estimate the remaining useful life of the engine and can enable to take precautionary actions in advanced. Be that as it may, aircraft engine frameworks are complex with both intangible and dubious components, it is troublesome to demonstrate the complex degradation process. In this article, the remaining useful life estimation is developed to improve feature -oriented framework. This frame eliminates unnecessary sensory inputs from engines and reduces calculation costs. As an application example, the developed feature -oriented frame has been used to estimate the remaining use of the aircraft engine based on sensor data. The results show that before applying other methods, systems with many input characteristics need feature adaptation procedures to reduce costs, but increase the certainty to estimate the remaining useful life.

Keywords

Aircraft engine, data mining, machine learning, support vector machines, logistics regression, linear regression, nasa turbofan data set, attribute selection, PCA

References

• J. Xu, Y. Wang and L. Xu. (April 2014). PHM-Oriented Integrated Fusion Prognostics for Aircraft Engines Based on Sensor Data. (2014 IEEE Sensors Journal, vol. 14, no. 4, pp. 1124-1132). https://doi.org/10.1109/JSEN.2013.2293517.
• E. Ramasso and T. Denoeux. (April 2014). Making Use of Partial Knowledge About Hidden States in HMMs: An Approach Based on Belief Functions. (2014 IEEE Transactions on Fuzzy Systems, vol. 22, no. 2, pp. 395-405). https://doi.org/10.1109/TFUZZ.2013.2259496.
• P. Tamilselvan, Y. Wang and P. Wang. (2012). Deep Belief Network based state classification for structural health diagnosis. (2012 IEEE Aerospace Conference, pp. 1-11). https://doi.org/10.1109/AERO.2012.6187366.
• K. Javed, R. Gouriveau and N. Zerhouni. (2013). Novel failure prognostics approach with dynamic thresholds for machine degradation. (IECON 2013 - 39th Annual Conference of the IEEE Industrial Electronics Societ, pp. 4404-4409). https://doi.org/10.1109/IECON.2013.6699844.
• Chao Hu, B. D. Youn and Pingfeng Wang. (2011). Ensemble of data-driven prognostic algorithms for robust prediction of remaining useful life. (2011 IEEE Conference on Prognostics and Health Management, pp. 1-10). https://doi.org/10.1109/ICPHM.2011.6024361.
• Gouriveau, Rafael et al. (2013). Strategies to Face Imbalanced and Unlabelled Data in Phm Applications. Chemical engineering transactions 33: 115-120.
• T. Wang, Jianbo Yu, D. Siegel and J. Lee. (2008). A similarity-based prognostics approach for Remaining Useful Life estimation of engineered systems". (2008 International Conference on Prognostics and Health Management, pp. 1-6). https://doi.org/10.1109/PHM.2008.4711421.
• K. Liu, N. Z. Gebraeel and J. Shi. (July 2013). A Data-Level Fusion Model for Developing Composite Health Indices for Degradation Modeling and Prognostic Analysis. (2013 IEEE Transactions on Automation Science and Engineering, vol. 10, no. 3, pp. 652-664). https://doi.org/10.1109/TASE.2013.2250282.
• Ramin Moghaddass, Ming J. Zuo. (2014). An integrated framework for online diagnostic and prognostic health monitoring using a multistate deterioration process, Reliability Engineering & System Safety. (Volume 124, Pages 92-104, ISSN 0951-8320). https://doi.org/10.1016/j.ress.2013.11.006.
• Tamilselvan, P & Wang. (2013). Failure diagnosis using deep belief learning based health state classification. (P 2013, Reliability Engineering and System Safety, vol. 115, pp. 124-135). https://doi.org/10.1016/j.ress.2013.02.022
• Javed, Kamran & Gouriveau, Rafael & Zerhouni, Noureddine. (2013). SW-ELM : A summation wavelet extreme learning machine algorithm with a priori initialization. (2014, Neurocomputing, 123). https://doi.org/10.1016/j.neucom.2013.07.021.
• D. K. Frederick, J. A. Decastro, and J. S. Litt. (2007). Users guide for the commercial modular aero-propulsion system simulation (c-mapss)''. (Tech. Rep. NASA/TM2007-215026).
• C. Liu, L. Zhang, Y. Liao, C. Wu and G. Peng. (2019). Multiple Sensors Based Prognostics With Prediction Interval Optimization via Echo State Gaussian Process. (2019 IEEE Access, vol. 7, pp. 112397-112409). https://doi.org/10.1109/ACCESS.2019.2925634.
• A. Saxena, G. Kai, D. Simon, and N. Eklund. (Oct. 2008). Damage propagation modeling for aircraft engine run-to-failure simulation. (Proc. Int. Conf. Prognostics Health Manage, pp. 1-9).
• National Aeronautics and Space Administration. (Mayıs,2022). PCoE Datasets. https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/#turbofan
• Fitzgerald E. (Ağustos, 2021) https://4cda.com/intro-to-predictive-maintenance-on-nasa-turbofan-engine-dataset-using-machine-learning/ .(Mayıs, 2022)
• Stephanie. (Ekim, 2016). https://www.statisticshowto.com/absolute-error/ .(Mayıs,2022)
• Fernando J. (Eylül, 2021). https://www.investopedia.com/terms/r/r-squared.asp .(Mayıs, 2022)