EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable Prediction of Remaining Useful Life for Turbofan Engines Using Kolmogorov–Arnold Network

Li Zhao, Yiqiao Zhang, Bin Huang

Aerospace · 27.10.2026 · 13 (11) · 986

DOI: 10.3390/aerospace13110986 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Aerospace, online erschienen am 27.10.2026. Verfasst von Li Zhao und 2 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhejiang Provincial Natural Science Foundation, “Innovation Yongjiang 2035” Key R&D Programme, Ningbo Municipal Excellence Research Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes a Remaining Useful Life (RUL) prediction framework combining Kolmogorov–Arnold Network (KAN), LSTM and BiLSTM to improve prediction accuracy and interpretability for turbofan engines. The proposed framework uses KAN to perform nonlinear mapping of sensor and operating-condition inputs before temporal modeling. LSTM and BiLSTM then extract the temporal degradation features, with the final forward and backward hidden states combined for RUL prediction. In terms of interpretability, this work analyzes sensor importance within the KAN representation through structural attribution. In addition, t-SNE feature-space visualization, SHAP attribution of the complete prediction model and XGBoost analysis are incorporated to provide complementary evidence for interpretation. Fixed-model sensor-retention experiments further examine whether sensors ranked highly by KAN preserve predictive information. Experimental results demonstrate favorable prediction accuracy and low variability across repeated training runs on the four C-MAPSS subsets. Under matched parameter counts, placing KAN before temporal modeling reduces FD001 mean RMSE by 23.83% relative to placing it in the regression stage. Further analysis identifies recurring pressure, flow, rotational speed and temperature variables, whose relative contributions vary across degradation stages and operating conditions. The KAN-ranked Top-10 sensors achieve a lower RMSE than the mean of equal-size random sensor sets and the low-ranked sets on all four subsets under fixed-model retention. The proposed method provides an integrated approach to prediction and sensor-level interpretation, offering support for turbofan-engine health assessment and maintenance planning.

Förderung

  • Zhejiang Provincial Natural Science Foundation
  • “Innovation Yongjiang 2035” Key R&D Programme
  • Ningbo Municipal Excellence Research Program

Zitieren

APA

Zhao, L., Zhang, Y., & Huang, B. (2026). Explainable Prediction of Remaining Useful Life for Turbofan Engines Using Kolmogorov–Arnold Network. Aerospace, 13(11), 986. https://doi.org/10.3390/aerospace13110986

Vancouver

Zhao L, Zhang Y, Huang B. Explainable Prediction of Remaining Useful Life for Turbofan Engines Using Kolmogorov–Arnold Network. Aerospace. 2026;13(11):986. doi:10.3390/aerospace13110986

BibTeX
@article{Zhao2026,
  author = {Zhao, Li and Zhang, Yiqiao and Huang, Bin},
  title = {Explainable Prediction of Remaining Useful Life for Turbofan Engines Using Kolmogorov–Arnold Network},
  journal = {Aerospace},
  year = {2026},
  volume = {13},
  number = {11},
  pages = {986},
  doi = {10.3390/aerospace13110986}
}
Kostenlos starten →