A Remaining Useful Life Prediction Method for Aero-Engines Based on Degradation-Aware Masked Augmentation and a CNN–Transformer Hybrid Network
Machines · 17.08.2026 · 14 (8) · 943
DOI: 10.3390/machines14080943 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machines, online erschienen am 17.08.2026. Verfasst von Xudong Song und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Top Talent of SZTU, Shenzhen Science and Technology Program.
Abstract (Originalsprache)
Accurate remaining useful life (RUL) prediction is essential for condition-based maintenance and safe aero-engine operation. To address non-stationary monitoring data, limited informative degradation samples, and the difficulty of jointly modeling local degradation patterns and temporal dependencies, this study proposes a degradation-aware dynamic masking augmentation method combined with a multiscale CNN–Transformer network. The 21 sensor variables in the NASA C-MAPSS dataset are first grouped by physical meaning and reconstructed into four-dimensional state features. A degradation-state score integrating local variance and trend slope is then used to adapt temporal masking probabilities across degradation stages, while feature masking probabilities are assigned according to feature importance. Masked positions are filled with adjacent unmasked observations, and invalid augmented samples are removed through trend consistency verification. A multiscale CNN with channel attention extracts local degradation features, and a Transformer encoder captures temporal dependencies. Bayesian optimization is used to determine key hyperparameters. On FD001, the proposed method achieves an MSE of 348.3970, an MAE of 8.3908, and an R2 of 0.9227, reducing MSE and MAE by 4.27% and 28.42%, respectively, compared with ML-RFR. It also achieves the highest R2 of 0.9369 on FD003. Cross-dataset and multi-seed experiments further confirm its applicability and stability.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Top Talent of SZTU
- Shenzhen Science and Technology Program
Zitieren
APA
Song, X., Wu, G., Wang, M., Liu, J., Wang, W., Song, M., Lu, H., & Shen, Y. (2026). A Remaining Useful Life Prediction Method for Aero-Engines Based on Degradation-Aware Masked Augmentation and a CNN–Transformer Hybrid Network. Machines, 14(8), 943. https://doi.org/10.3390/machines14080943
Vancouver
Song X, Wu G, Wang M, Liu J, Wang W, Song M, et al. A Remaining Useful Life Prediction Method for Aero-Engines Based on Degradation-Aware Masked Augmentation and a CNN–Transformer Hybrid Network. Machines. 2026;14(8):943. doi:10.3390/machines14080943
BibTeX
@article{Song2026,
author = {Song, Xudong and Wu, Guohua and Wang, Mengdan and Liu, Jian and Wang, Wenlin and Song, Mengchu and Lu, Hongxing and Shen, Yue},
title = {A Remaining Useful Life Prediction Method for Aero-Engines Based on Degradation-Aware Masked Augmentation and a CNN–Transformer Hybrid Network},
journal = {Machines},
year = {2026},
volume = {14},
number = {8},
pages = {943},
doi = {10.3390/machines14080943}
}
EUVIMED