EUVIMEDEUVIMED entdecken
Crossref

Innovative transformer-driven remaining useful life (RUL) prediction enhanced by adaptive multi-scale feature engineering

Lydia Hsiao-Mei Lin, Fang-Kai Ting, Shu-Han Liao, Chia-Hsun Hsieh, Chia-Hsuan Ho, Simon Hung-Yi Lu, Richard Tzong-Han Tsai

The International Journal of Advanced Manufacturing Technology · 2026-08 · 145 (11-12) · 7799-7813

DOI: 10.1007/s00170-026-17963-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The International Journal of Advanced Manufacturing Technology, online erschienen am 02.04.2026. Verfasst von Lydia Hsiao-Mei Lin und 6 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate remaining useful life (RUL) prediction is essential for condition-based maintenance in modern manufacturing systems. While Transformer-based models have demonstrated strong sequence modeling capability, RUL prediction requires degradation-consistent representation learning across multiple temporal resolutions. This study investigates multi-scale degradation-aware feature representation within a Transformer framework and proposes a Multi-scale Feature Dual-Aspect Self-Attention Transformer (MFDAST). The proposed approach integrates multi-resolution statistical feature extraction and a monotonic Health Indicator (HI) as a regularization mechanism to encourage stable degradation modeling. Genetic algorithm (GA)-based hyperparameter tuning is further applied to explore parameter interactions under controlled settings. Experiments conducted on the FEMTO-ST (PRONOSTIA) bearing degradation dataset demonstrate consistent performance improvements over representative RNN-based and baseline Transformer models under identical experimental configurations, achieving up to 50% reduction in RMSE under specific operating conditions. An additional ablation study on the C-MAPSS turbofan engine dataset further validates the generality of the proposed design across different RUL prediction scenarios. The results confirm that multi-scale degradation representation is the primary source of performance gains, while HI modeling and GA optimization provide incremental improvements in prediction accuracy and training stability. These findings highlight the importance of degradation-aware multi-resolution representation for RUL prediction and provide practical insights for designing Transformer-based prognostic models in industrial applications.

Zitieren

APA

Lin, L. H., Ting, F., Liao, S., Hsieh, C., Ho, C., Lu, S. H., & Tsai, R. T. (2026). Innovative transformer-driven remaining useful life (RUL) prediction enhanced by adaptive multi-scale feature engineering. The International Journal of Advanced Manufacturing Technology, 145(11-12), 7799-7813. https://doi.org/10.1007/s00170-026-17963-4

Vancouver

Lin LH, Ting F, Liao S, Hsieh C, Ho C, Lu SH, et al. Innovative transformer-driven remaining useful life (RUL) prediction enhanced by adaptive multi-scale feature engineering. The International Journal of Advanced Manufacturing Technology. 2026;145(11-12):7799-7813. doi:10.1007/s00170-026-17963-4

BibTeX
@article{Lin2026,
  author = {Lin, Lydia Hsiao-Mei and Ting, Fang-Kai and Liao, Shu-Han and Hsieh, Chia-Hsun and Ho, Chia-Hsuan and Lu, Simon Hung-Yi and Tsai, Richard Tzong-Han},
  title = {Innovative transformer-driven remaining useful life (RUL) prediction enhanced by adaptive multi-scale feature engineering},
  journal = {The International Journal of Advanced Manufacturing Technology},
  year = {2026},
  volume = {145},
  number = {11-12},
  pages = {7799--7813},
  doi = {10.1007/s00170-026-17963-4}
}
Kostenlos starten →