Health Index Modelling of Turbofan Engines Using Residual Dilated Convolutional Neural Networks for Predictive Maintenance

Alfia Nurlaili Tahiyat; Lusiana  Efrizoni; Triyani Arita  Fitri; Susanti Susanti

doi:10.52436/1.jutif.2026.7.4.5636

Authors

Alfia Nurlaili Tahiyat Informatics Engineering, Universitas Sains dan Teknologi Indonesia, Indonesia
Lusiana Efrizoni Informatics Engineering, Universitas Sains dan Teknologi Indonesia, Indonesia
Triyani Arita Fitri Informatics Engineering, Universitas Sains dan Teknologi Indonesia, Indonesia
Susanti Informatics Engineering, Universitas Sains dan Teknologi Indonesia, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.4.5636

Keywords:

Convolution Neural Network, Health Index, N-CMAPSS, Predictive Maintenance, Prognostics and Health Management

Abstract

Data-driven prognostics and health management (PHM) for turbofan engines requires a Health Index (HI) that is learnable from multivariate telemetry and credible as a basis for maintenance decisions. This study presents a deep learning-based HI modelling framework on the N-CMAPSS benchmark that converts operating conditions and sensor streams into a bounded HI and, subsequently, into decision-oriented outputs for predictive maintenance. A baseline convolutional model is benchmarked against a residual dilated CNN to capture multi-scale degradation signatures from fixed-length temporal windows. To preserve evaluative integrity, health-zone thresholds are calibrated on validation predictions and then fixed, producing a three-zone taxonomy (critical, warning, healthy) for rapid field triage, alongside a continuous risk score that induces a rank-ordered maintenance priority list from most critical to most healthy. The selected model achieves HI regression performance of RMSE = 0.1266, MAE = 0.0720, and R² = 0.7241, while the calibrated zone mapping attains accuracy = 0.8688 and macro-F1 = 0.6124. The main contribution is a leakage-aware, decision-coupled pipeline that delivers both interpretable health zoning and risk-ranked prioritization, strengthening the operational linkage between predictive modelling and maintenance triage within PHM-oriented Informatics.

Downloads

Download data is not yet available.

References

N. Sakib and T. Wuest, “Challenges and Opportunities of Condition-based Predictive Maintenance : A Review,” Procedia CIRP, vol. 78, no. March, pp. 267–272, 2023, doi: 10.1016/j.procir.2018.08.318.

B. Taşcı, A. Omar, and S. Ayvaz, “Remaining useful lifetime prediction for predictive maintenance in manufacturing,” Comput. Ind. Eng., vol. 184, p. 109566, 2023, doi: 10.1016/j.cie.2023.109566.

F. Wu, Q. Wu, Y. Tan, and X. Xu, “Remaining Useful Life Prediction Based on Deep Learning : A Survey,” Sensors, vol. 24, no. 11, pp. 1–30, 2024, doi: 10.3390/s24113454.

L. Huang, X. Pan, and L. Gong, “An Unsupervised Machine Learning Approach for Monitoring Data Fusion and Health Indicator Construction,” Sensors, vol. 23, no. 16, p. 7239, 2023, doi: 10.3390/s23167239.

M. Moradi, A. Broer, J. Chiachio, R. Benedictus, T. H. Loutas, and D. Zarouchas, “Intelligent health indicator construction for prognostics of composite structures utilizing a semi-supervised deep neural network and SHM data,” Eng. Appl. Artif. Intell., vol. 117, p. 105502, 2023, doi: 10.1016/j.engappai.2022.105502.

N. Tuan-Khai, Z. Ahmad, and J. Kim, “A Deep-Learning-Based Health Indicator Constructor Using Kullback – Leibler Divergence for Predicting the Remaining,” Sensors, vol. 22, no. 10, p. 3687, 2022, doi: 10.3390/s22103687.

S. Bai, J. Z. Kolter, and V. Koltun, “An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling,” Comput. Sci. Cornell Univ., vol. 19, no. 4, pp. 1–14, 2018, doi: 10.48550/arXiv.1803.01271.

M. A. Chao, C. Kulkarni, K. Goebel, and O. Fink, “Aircraft Engine Run-to-Failure Dataset under Real Flight Conditions for Prognostics and Diagnostics,” Data, vol. 6, no. 1, pp. 1–14, 2021, doi: 10.3390/data6010005.

F. Mohammadhasani and A. Pirouzmand, “Multi-state Risk-Based Maintenance Analysis of Redundant Safety Systems Using the Markov Model and Fault Tree Method,” Front. Energy Res., vol. 9, no. July, pp. 1–18, 2021, doi: 10.3389/fenrg.2021.685634.

H. Wang, D. Li, Y. Li, G. Zhu, and R. Lin, “Method for Remaining Useful Life Prediction of Turbofan Engines Combining Adam Optimization-Based Self-Attention Mechanism with Temporal Convolutional Networks,” Appl. Sci., vol. 14, no. 17, p. 7723, 2024, doi: 10.3390/app14177723.

C. Peng, Y. Chen, Q. Chen, Z. Tang, L. Li, and W. Gui, “A Remaining Useful Life Prognosis of Turbofan Engine Using Temporal and Spatial Feature Fusion,” Sensors, vol. 21, p. 418, 2021, doi: 10.3390/ s21020418 Received:

J. Li and Z. Yang, “Remaining Useful Life Prediction of Turbine Engines Using Multimodal Transfer Learning,” Machines, vol. 13, p. 789, 2025, doi: 10.3390/machines 13090789.

H. Li, Z. Wang, and Z. Li, “An enhanced CNN-LSTM remaining useful life prediction model for aircraft engine with attention mechanism,” PeerJ Comput. Sci., vol. 30, no. 8, pp. 1–19, 2022, doi: 10.7717/peerj-cs.1084.

T. Darrah, L. Andreas, J. Frank, G. Biswas, and M. Quinones-Gruiero, “Developing Deep Learning Models for System Remaining Useful Life Predictions : Application to Aircraft Engines,” Annu. Conf. PHM Soc., vol. 14, no. 1, pp. 1–10, 2022, doi: 10.36001/phmconf.2022.v14i1.3304.

Z. Lu et al., “A multi-scale cross-dimension interaction approach with adaptive dilated TCN for RUL prediction,” Sci. Rep., vol. 15, no. 1, pp. 1–27, 2025, doi: 10.1038/s41598-025-00572-8.

A. Wahid, M. Yahya, J. G. Breslin, and M. A. Intizar, “Self-Attention Transformer-Based Architecture Architecture for for Remaining Remaining Useful Life Estimation of Complex Machines Useful Life Estimation of Complex Machines,” Procedia Comput. Sci., vol. 217, no. 2022, pp. 456–464, 2023, doi: 10.1016/j.procs.2022.12.241.

L. Basora, A. Viens, M. Arias, and X. Olive, “A Benchmark on Uncertainty Quantification for Deep Learning Prognostics,” Elsevier, vol. 253, 2023.

H. Dong and W. Lian, “A Novel Approach for Aircraft Engine Modeling Considering the Energy Accumulation Effect Based on a Variable Mass System Thermodynamics Method,” Energies, vol. 17, no. 24, pp. 1–13, 2024, doi: 10.3390/en17246424.

C. Okoh, R. Roy, J. Mehnen, and L. Redding, “Overview of Remaining Useful Life Prediction Techniques in Through-Life Engineering Services,” Procedia CIRP, vol. 16, pp. 158–163, 2014, doi: 10.1016/j.procir.2014.02.006.

A. F. Azyus and S. K. Wijaya, “Determining the Method of Predictive Maintenance for Aircraft Engine Using Machine Learning,” J. Comput. Sci. Technol. Stud., pp. 1–6, 2022, doi: 10.32996/jcsts.2022.4.1.1.

O. Asif, S. A. Haider, S. R. Naqvi, J. Zaki, K. S. Kwak, and S. M. R. Islam, “A Deep Learning Model for Remaining Useful Life Prediction of Aircraft Turbofan Engine on C-MAPSS Dataset,” IEEE Access, vol. PP, p. 1, 2022, doi: 10.1109/ACCESS.2022.3203406.

Z. Shang, B. Zhang, W. Li, S. Qian, and J. Zhang, “Machine remaining life prediction based on multi-layer self-attention and temporal convolution network,” Complex Intell. Syst., vol. 8, pp. 1409–1424, 2022, doi: 10.1007/s40747-021-00606-4.

B. Sajiwo, T. Prahasto, and A. Widodo, “PREDIKSI REMAINING USEFUL LIFE ( RUL ) PADA JET ENGINE SEBAGAI UPAYA,” J. Tek. Mesin, vol. 11, no. 4, pp. 7–18, 2023.

A. Chaoub, A. Voisin, C. Cerisara, and B. Iung, “Few-shot remaining useful life prognostics through auxiliary training with related data-set To cite this version : HAL Id : hal-04819657 Few-shot remaining useful life prognostics through auxiliary training with related data-set,” Neural Comput. Appl., vol. 37, 2025, doi: 10.1007/s00521-024-10431-8.

T. Berghout, M. Mouss, L. Mouss, and M. Benbouzid, “ProgNet : A Transferable Deep Network for Aircraft Engine Damage Propagation Prognosis under Real Flight Conditions,” Aerospace, vol. 10, no. 1, pp. 1–12, 2023, doi: 10.3390/aerospace10010010.

S. M. Elsherif, B. Hafiz, M. A. Makhlouf, and O. Farouk, “A deep learning-based prognostic approach for predicting turbofan engine degradation and remaining useful life,” Sci. Rep., vol. 15, no. 26251, pp. 1–31, 2025, doi: 10.1038/s41598-025-09155-z.

Z. Wen et al., “Temporal and Heterogeneous Graph Neural Network for Remaining Useful Life Prediction,” IEEE Trans. NEURAL NETWORKS Learn. Syst., vol. 6, pp. 1–14, 2025.

L. Shen, Y. Wang, B. Du, H. Yang, and H. Fan, “Remaining Useful Life Prediction of Aero-Engine Based on Improved GWO and 1DCNN,” Machines, vol. 13, no. 7, pp. 1–24, 2025, doi: 10.3390/machines13070583.

Y. Ma et al., “Learning a Deep Attention Dilated Residual Convolutional Neural Network for Landslide Susceptibility Mapping in,” Remote Sens., vol. 13, p. 3296, 2023, doi: 10.3390/rs15133296.

L. Wen, Y. Dong, and L. Gao, “A new ensemble residual convolutional neural network for remaining useful life estimation,” Math. Biosci. Eng., vol. 16, no. 2, pp. 862–880, 2019, doi: 10.3934/mbe.2019040.

F. Wang, A. Liu, C. Qu, R. Xiong, and L. Chen, “A Deep-Learning Method for Remaining Useful Life Prediction of Power Machinery via Dual-Attention Mechanism,” Sensors, vol. 25, no. 2, pp. 1–19, 2025, doi: 10.3390/s25020497.

K. Ensarioglu, T. Inkaya, and E. Emel, “Remaining Useful Life Estimation of Turbofan Engines with Deep Learning Using Change-Point Detection Based Labeling and Feature Engineering,” Appl. Sci., vol. 13, no. 21, p. 11893, 2023, doi: 10.3390/app132111893.