Enhancing Aircraft Safety through Predictive Monitoring of Engine Health

Mehmet Deniz

EN TR

Enhancing Aircraft Safety through Predictive Monitoring of Engine Health

Abstract

This study proposes an RMSE-calibrated (Root Mean Square Error) ensemble framework for Remaining Useful Life (RUL) prediction of turbofan engines using the NASA C-MAPSS dataset. The approach integrates CatBoost, XGBoost, and Random Forest regressors within a weighted ensemble optimized for bias-variance trade off. A 30-cycle sliding window and z-score normalization were employed to construct a robust feature space from multivariate sensor streams. Additionally, a cross-validated RMSE-based bias correction was applied to mitigate systematic underestimation at longer RUL horizons. Experimental results on the FD001 subset demonstrate that the proposed ensemble achieves an RMSE of 13.72 and an R² of 0.8909, outperforming individual learners and several reported benchmarks. The model exhibits stable generalization and a well-balanced error distribution, confirming its suitability for real-time prognostic health management (PHM) applications. The findings highlight that carefully calibrated ensemble learning can match or exceed deep learning approaches in accuracy while retaining full interpretability and computational efficiency.

Keywords

Remaining Useful Life (RUL) Prediction , Ensemble Learning , Predictive Maintenance , NASA C-MAPSS Dataset , Turbofan Engine

Tahmine Dayalı Motor Sağlığı İzleme ile Uçak Güvenliğinin Artırılması

Öz

Bu çalışma, NASA C-MAPSS veri kümesini kullanarak turbofan motorlarının kalan faydalı ömrünün (Remaining Useful Life, RUL) tahmini için RMSE (Root Mean Square Error) ile kalibre edilmiş bir ensemble çerçevesi önermektedir. Önerilen yaklaşım, CatBoost, XGBoost ve Random Forest modellerinin, yanlılık ve varyans dengesi açısından optimize edilmiş ağırlıklı bir topluluk modeli içinde birleştirmektedir. Çok değişkenli sensör verilerinden sağlam bir öznitelik uzayı oluşturmak için 30 çevrimlik bir kayan pencere ve z-skor normalizasyonu uygulanmıştır. Ayrıca, uzun vadeli RUL tahminlerinde görülen sistematik düşük tahmin eğilimini azaltmak için, çapraz doğrulama temelli RMSE esaslı bir yanlılık düzeltme yöntemi uygulanmıştır. FD001 alt kümesindeki deneysel sonuçlar, önerilen topluluk modelinin 13.72 RMSE ve 0.8909 R² değerleri elde ettiğini, böylece tekil modelleri ve literatürde raporlanan çeşitli yaklaşımları geride bıraktığını göstermektedir. Model, istikrarlı genelleme yeteneği ve dengeli hata dağılımı sergileyerek gerçek zamanlı kestirimci bakım (Prognostic Health Management, PHM) uygulamaları için uygunluğunu doğrulamaktadır. Bulgular, dikkatle kalibre edilmiş topluluk öğrenmesinin, yorumlanabilirlik ve hesaplama verimliliğini koruyarak derin öğrenme yaklaşımlarıyla eşdeğer veya daha yüksek doğruluk elde edebileceğini ortaya koymaktadır.

Anahtar Kelimeler

Kalan faydalı ömür (RUL) , Topluluk öğrenmesi , Kestirimci bakım , NASA C-MAPSS veri seti , Turbofan motor

Kaynakça

Bieber, M., Verhagen, W. J. C., & Santos, B. F. (2021). Data-Driven Prognostics Incorporating Environmental Factors for Aircraft Maintenance. 2021 Annual Reliability and Maintainability Symposium (RAMS), 1–6. https://doi.org/10.1109/RAMS48097.2021.9605715
Chen, Z., Cao, S., & Mao, Z. (2017). Remaining Useful Life Estimation of Aircraft Engines Using a Modified Similarity and Supporting Vector Machine (SVM) Approach. Energies, 11(1), 28. https://doi.org/10.3390/en11010028
Cheng, C., Ma, G., Zhang, Y., Sun, M., Teng, F., Ding, H., & Yuan, Y. (2020). A Deep Learning-Based Remaining Useful Life Prediction Approach for Bearings. IEEE/ASME Transactions on Mechatronics, 25(3), 1243–1254. https://doi.org/10.1109/TMECH.2020.2971503
DeCastro, J. A., & Litt, J. S. (2007). Dean K. Frederick Saratoga Control Systems, Inc., Saratoga Springs, New York. New York.
Elsheikh, A., Yacout, S., & Ouali, M.-S. (2019). Bidirectional handshaking LSTM for remaining useful life prediction. Neurocomputing, 323, 148–156. https://doi.org/10.1016/j.neucom.2018.09.076
Engine Failure During Takeoff—Multi-Engine Transport Category Jet Aircraft | SKYbrary Aviation Safety. (n.d.). Retrieved November 1, 2025, from https://skybrary.aero/articles/engine-failure-during-takeoff-multi-engine-transport-category-jet-aircraft
Garcia, P. P., Vismari, L. F., Camargo, J. B., de Almeida, J. R., & Cugnasca, P. S. (2026). Systematic literature review of artificial intelligence techniques on condition based maintenance models for transport applications. Engineering Applications of Artificial Intelligence, 164, 113230. https://doi.org/10.1016/j.engappai.2025.113230
Gharoun, H., Keramati, A., Nasiri, M. M., & Azadeh, A. (2019). An Integrated Approach for Aircraft Turbofan Engine Fault Detection Based on Data Mining Techniques. Expert Systems, 36(2). https://doi.org/10.1111/exsy.12370
Guangbin, Y., Ding, G., Lin, L., Xingfu, Z., & Yang, Z. (2014). Aircraft Engine Fuel Flow Prediction Using Process Neural Network. International Journal of Control and Automation, 7(3), 53–62. https://doi.org/10.14257/ijca.2014.7.3.06
Huang, Y., Tao, J., Sun, G., Zhang, H., & Hu, Y. (2022). A Prognostic and Health Management Framework for Aero-Engines Based on a Dynamic Probability Model and LSTM Network. Aerospace, 9(6), 316. https://doi.org/10.3390/aerospace9060316

Isbilen, F., Bektas, O., & Konar, M. (2025). Deep learning and similarity-based models for predicting turbofan engine remaining useful life: Insights from the CMAPSS dataset. The Aeronautical Journal, 129(1337), 2004–2035. Cambridge Core. https://doi.org/10.1017/aer.2025.25
Kabashkin, I., & Perekrestov, V. (2024). Ecosystem of Aviation Maintenance: Transition From Aircraft Health Monitoring to Health Management Based on IoT and AI Synergy. Applied Sciences, 14(11), 4394. https://doi.org/10.3390/app14114394
Li, Z., Goebel, K., & Wu, D. (2019). Degradation Modeling and Remaining Useful Life Prediction of Aircraft Engines Using Ensemble Learning. Journal of Engineering for Gas Turbines and Power, 141(4), 041008. https://doi.org/10.1115/1.4041674
Lin, R., Wang, H., Xiong, M., Hou, Z., & Che, C. (2023). Attention-based Gate Recurrent Unit for remaining useful life prediction in prognostics. Applied Soft Computing, 143, 110419. https://doi.org/10.1016/j.asoc.2023.110419
Liu, X., Xiong, L., Zhang, Y., & Luo, C. (2023). Remaining Useful Life Prediction for Turbofan Engine Using SAE-TCN Model. Aerospace, 10(8), 715. https://doi.org/10.3390/aerospace10080715
Rahman, P., & Mehnaz, S. (2024a). International Journal for Multidisciplinary Research (IJFMR). SSRN Electronic Journal. https://doi.org/10.2139/ssrn.5054029
Rahman, P., & Mehnaz, S. (2024b). International Journal for Multidisciplinary Research (IJFMR). SSRN Electronic Journal. https://doi.org/10.2139/ssrn.5054029
Rahman, P., & Mehnaz, S. (2024c). International Journal for Multidisciplinary Research (IJFMR). SSRN Electronic Journal. https://doi.org/10.2139/ssrn.5054029
Ramasso, E., & Saxena, A. (2014). Review and Analysis of Algorithmic Approaches Developed for Prognostics on CMAPSS Dataset. Annual Conference of the PHM Society, 6(1). https://doi.org/10.36001/phmconf.2014.v6i1.2512
Saxena, A., Simon, D., & Eklund, N. (n.d.). Damage Propagation Modeling for Aircraft Engine Prognostics.
Soualhi, M., Nguyen, K. T. P., & Medjaher, K. (2024a). Explainable RUL estimation of turbofan engines based on prognostic indicators and heterogeneous ensemble machine learning predictors. Engineering Applications of Artificial Intelligence, 133, 108186. https://doi.org/10.1016/j.engappai.2024.108186
Soualhi, M., Nguyen, K. T. P., & Medjaher, K. (2024b). Explainable RUL estimation of turbofan engines based on prognostic indicators and heterogeneous ensemble machine learning predictors. Engineering Applications of Artificial Intelligence, 133, 108186. https://doi.org/10.1016/j.engappai.2024.108186
Szrama, S. (2025a). Optimizing aircraft engine longevity: A comparative framework for dynamically adaptive predictive maintenance using autoencoders, LSTMs, and Gaussian processes. Engineering Applications of Artificial Intelligence, 156, 111199. https://doi.org/10.1016/j.engappai.2025.111199
Szrama, S. (2025b). Optimizing aircraft engine longevity: A comparative framework for dynamically adaptive predictive maintenance using autoencoders, LSTMs, and Gaussian processes. Engineering Applications of Artificial Intelligence, 156, 111199. https://doi.org/10.1016/j.engappai.2025.111199
Wang, H., Li, D., Li, D., Liu, C., Yang, X., & Zhu, G. (2023). Remaining Useful Life Prediction of Aircraft Turbofan Engine Based on Random Forest Feature Selection and Multi-Layer Perceptron. Applied Sciences, 13(12), 7186. https://doi.org/10.3390/app13127186
Xiao, D., Xiao, H., Li, R., & Wang, Z. (2024). Application of physical-structure-driven deep learning and compensation methods in aircraft engine health management. Engineering Applications of Artificial Intelligence, 136, 109024. https://doi.org/10.1016/j.engappai.2024.109024
Xue, F., Jin, G., Tan, L., Zhang, C., & Yu, Y. (2025a). Predictive maintenance programs for aircraft engines based on remaining useful life prediction. Scientific Reports, 15(1), 41756. https://doi.org/10.1038/s41598-025-19957-w
Xue, F., Jin, G., Tan, L., Zhang, C., & Yu, Y. (2025b). Predictive maintenance programs for aircraft engines based on remaining useful life prediction. Scientific Reports, 15(1), 41756. https://doi.org/10.1038/s41598-025-19957-w
Yang, F., Habibullah, M. S., Zhang, T., Xu, Z., Lim, P., & Nadarajan, S. (2016). Health Index-Based Prognostics for Remaining Useful Life Predictions in Electrical Machines. IEEE Transactions on Industrial Electronics, 63(4), 2633–2644. https://doi.org/10.1109/TIE.2016.2515054
Yao, P. (2024a). A Review of Aircraft Engine Fault Prediction and Performance Optimization Based on Deep Learning. International Journal of Computer Science and Information Technology, 4(2), 83–87. https://doi.org/10.62051/ijcsit.v4n2.12
Yao, P. (2024b). A Review of Aircraft Engine Fault Prediction and Performance Optimization Based on Deep Learning. International Journal of Computer Science and Information Technology, 4(2), 83–87. https://doi.org/10.62051/ijcsit.v4n2.12
Yildirim, S., & Rana, Z. A. (2024). Enhancing Aircraft Safety through Advanced Engine Health Monitoring with Long Short-Term Memory. Sensors, 24(2), 518. https://doi.org/10.3390/s24020518
Zhao, S., Zhang, Y., Wang, S., Zhou, B., & Cheng, C. (2019). A recurrent neural network approach for remaining useful life prediction utilizing a novel trend features construction method. Measurement, 146, 279–288. https://doi.org/10.1016/j.measurement.2019.06.004

Ayrıntılar

Birincil Dil

İngilizce

Konular

Hava Taşımacılığı ve Nakliye Hizmetleri

Bölüm

Araştırma Makalesi

Yazarlar

Mehmet Deniz ^*
0000-0002-5585-7947
Türkiye

Yayımlanma Tarihi

31 Aralık 2025

Gönderilme Tarihi

12 Kasım 2025

Kabul Tarihi

25 Aralık 2025

Yayımlandığı Sayı

Yıl 2025 Cilt: 2 Sayı: Aviation Technologies and Applications Conference (ATAConf'25) Special Issue

IZ

https://izlik.org/JA79MA37DY

APA

Deniz, M. (2025). Enhancing Aircraft Safety through Predictive Monitoring of Engine Health. Ege Üniversitesi Ulaştırma Yönetimi Araştırmaları Dergisi, 2(Aviation Technologies and Applications Conference (ATAConf’25) Special Issue), 21-42. https://izlik.org/JA79MA37DY

Enhancing Aircraft Safety through Predictive Monitoring of Engine Health

Abstract

Keywords

Tahmine Dayalı Motor Sağlığı İzleme ile Uçak Güvenliğinin Artırılması

Öz

Anahtar Kelimeler

Kaynakça

Ayrıntılar

Birincil Dil

Konular

Bölüm

Yazarlar

Yayımlanma Tarihi

Gönderilme Tarihi

Kabul Tarihi

Yayımlandığı Sayı

IZ

Kaynak Göster