SavedAdd your journal

Journals / Journal of Aviation / 2026 / Volume: 10 Issue: 3

Seasonal Feature Augmentation for Interpretable Turbofan RUL Prediction via Bayesian-Optimized XGBoost

Ertuğrul Metehan Sertdemir(Fırat Unıversıty)0000-0002-4374-6289
Hülya Kaftelen Odabaşı(FIRAT ÜNİVERSİTESİ, SİVİL HAVACILIK YÜKSEKOKULU)0000-0003-1111-5420
Pages
—
Publication Date
2026-10-25
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Furthermore, the study explores the contribution of a synthetically constructed periodic feature to the predictive behavior and interpretability of the model.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The operational safety and sustainability of gas turbine engines in the aviation industry are directly contingent upon the accurate prediction of the Remaining Useful Life (RUL) of critical components.
📊
Key Findings & Data:To address this gap, the present study proposes a novel hybrid model grounded in the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset (FD001–FD004), integrating standard operational data with seasonal parameters.
💡
Conclusion & Impact:Furthermore, the study explores the contribution of a synthetically constructed periodic feature to the predictive behavior and interpretability of the model.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Predictive Maintenance · Remaining Useful Life (RUL) · XGBoost

Abstract

The operational safety and sustainability of gas turbine engines in the aviation industry are directly contingent upon the accurate prediction of the Remaining Useful Life (RUL) of critical components. Existing RUL prediction models in the aviation literature predominantly focus on in-engine sensor data, largely overlooking the cumulative impact of external environmental variables—particularly ambient temperature and seasonal fluctuations—on material fatigue. To address this gap, the present study proposes a novel hybrid model grounded in the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset (FD001–FD004), integrating standard operational data with seasonal parameters. The proposed model architecture is based on the Extreme Gradient Boosting (XGBoost) algorithm, with hyperparameter optimization conducted via the Bayesian-based Optuna framework. Experimental findings demonstrate that the model achieves RMSE = 15.84 and R² = 0.85, exhibiting competitive or superior predictive accuracy relative to complex deep learning architectures reported in the literature. Furthermore, the study explores the contribution of a synthetically constructed periodic feature to the predictive behavior and interpretability of the model.

🔖

Cite This Article

Sertdemir, E. M., Odabaşı, H. K. (2026). Seasonal Feature Augmentation for Interpretable Turbofan RUL Prediction via Bayesian-Optimized XGBoost. Journal of Aviation, Volume: 10 Issue: 3. https://doi.org/10.30518/jav.1940225

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (20)

  1. Ahmad, A., Yadav, A. K., & Singh, A. (2023). Application of machine learning and genetic algorithms to the prediction and optimization of biodiesel yield from waste cooking oil. Korean Journal of Chemical Engineering, 40(12), 2941–2956.
  2. Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019). Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 2623–2631).
  3. Alkharashi, A., et al. (2023). Machine learning models for biogas potential in sustainable aviation: XGBoost, random forest and ridge regression. Journal of Aviation, 7(1), 1–12.
  4. Bandara, K., Bergmeir, C., & Smyl, S. (2019). Forecasting across time series databases using recurrent neural networks on groups of similar series: A clustering approach. Expert Systems with Applications, 140, 112896.
  5. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794).
  6. Ghonem, H., Nicholas, T., & Pineau, A. (1993). Elevated temperature fatigue crack growth in alloy 718—Part I: Effects of environmental and loading variables. Fatigue & Fracture of Engineering Materials & Structures, 16(5), 565–576.
  7. Heimes, F. O. (2008). Recurrent neural networks for remaining useful life estimation. In Proceedings of the International Conference on Prognostics and Health Management (pp. 1–6).
  8. Keskin, F. (2024). Advanced driving cycle generation using XGBoost: A case study in Iğdır, Türkiye. In 2024 8th International Artificial Intelligence and Data Processing Symposium (IDAP). IEEE.
  9. Li, X., Ding, Q., & Sun, J. Q. (2018). Remaining useful life estimation in prognostics using deep convolutional neural networks. Reliability Engineering & System Safety, 172, 1–11.
  10. Ma, J., Su, H., Zhao, W. L., & Liu, B. (2018). Predicting the remaining useful life of an aircraft engine using a stacked sparse autoencoder with multilayer self-learning. Complexity, 2018, 3813657.
  11. Peringal, A., Mohiuddin, M. B., & Hassan, A. (2024). Remaining useful life prediction for aircraft engines using LSTM. arXiv. https://arxiv.org/abs/2401.07590
  12. Ramasso, E., & Saxena, A. (2014). Performance benchmarking and analysis of prognostic methods for CMAPSS datasets. International Journal of Prognostics and Health Management, 5(2), 1–15.
  13. Saravanamuttoo, H. I. H., Rogers, G. F. C., Cohen, H., & Straznicky, P. V. (2017). Gas turbine theory. Pearson Education.
  14. Saxena, A., Goebel, K., Simon, D., & Eklund, N. (2008). Damage propagation modeling for aircraft engine run- to-failure simulation. In Proceedings of the International Conference on Prognostics and Health Management (PHM) (pp. 1–9).
  15. Sertdemir, E. M., Odabaşı, H. K., & Altınok, A. (2025). Assessment of aircraft fuel efficiency in domestic flights using multiple regression analysis. Journal of Aviation, 9(2), 285–294.
  16. Volponi, A. J. (2014). Gas turbine engine health management: Past, present, and future perspectives. Journal of Engineering for Gas Turbines and Power, 136(5), 052101.
  17. Wu, B., Zhang, B., Li, W., & Jiang, F. (2022). A novel method for remaining useful life prediction of bearing based on spectrum image similarity measures. Mathematics, 10(13), 2209.
  18. Wu, F., Wu, Q., Tan, Y., & Xu, X. (2023). Remaining useful life prediction based on deep learning: A survey. Sensors, 23(14), 6454.
  19. Yu, B., Guo, H., & Shi, J. (2025). Remaining useful life prediction based on hybrid CNN-BiLSTM model with dual attention mechanism. International Journal of Electrical Power & Energy Systems, 172, 111152.
  20. Zhong, D., Xia, Z., Zhu, Y., & Duan, J. (2023). Overview of predictive maintenance based on digital twin technology. Heliyon, 9(3), e14534.