Strain Prediction of Pile-Type Adjustable Wind-Turbine Foundation Caps Using XGBoost–SHAP Feature Selection and the TimeXer Model
Buildings · 10.06.2026 · 16 (12) · 2325
DOI: 10.3390/buildings16122325 ↗Kurz gefasst
Fachartikel in der Zeitschrift Buildings, online erschienen am 10.06.2026. Verfasst von Lei Bian und 4 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.
Abstract (Originalsprache)
Accurate prediction of pile-cap strain is crucial for the safety of wind-turbine foundations, yet conventional methods struggle to screen key features from high-dimensional monitoring data and to model the nonlinear coupling between endogenous and exogenous variables, hindering both accuracy and interpretability. To address these limitations, this paper proposes a pile-cap-strain prediction method integrating XGBoost-SHAP feature selection with the TimeXer deep-learning model. XGBoost-SHAP first identifies critical predictors from high-dimensional pile-stress data; the TimeXer model then exploits its endogenous–exogenous fusion mechanism for strain prediction. The results show that XGBoost-SHAP effectively selected 10 key features, of which the upper-middle and middle windward-side stresses (Z1-4A, Z1-5A) contributed over 40% of the explanatory power. This stage performs dimensionality reduction and sensor-importance interpretation, halving the input dimensionality while maintaining accuracy comparable to the full 19-channel input. TimeXer achieved a coefficient of determination (R2) of 0.993 in single-step prediction, comparable to the best-performing baselines, and maintained stable performance over a 120 min multi-step horizon. In a zero-shot cross-site transfer test, TimeXer attained the highest eight-step average R2 (0.914) among all models, indicating strong cross-site generalization. Attention-mechanism visualization further suggested consistency between the model’s prediction logic and structural mechanics principles. The proposed framework provides a technical solution combining high accuracy with strong interpretability for wind-turbine foundation health monitoring.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong Province
Zitieren
APA
Bian, L., Liu, C., Wei, H., Zhao, H., & Li, X. (2026). Strain Prediction of Pile-Type Adjustable Wind-Turbine Foundation Caps Using XGBoost–SHAP Feature Selection and the TimeXer Model. Buildings, 16(12), 2325. https://doi.org/10.3390/buildings16122325
Vancouver
Bian L, Liu C, Wei H, Zhao H, Li X. Strain Prediction of Pile-Type Adjustable Wind-Turbine Foundation Caps Using XGBoost–SHAP Feature Selection and the TimeXer Model. Buildings. 2026;16(12):2325. doi:10.3390/buildings16122325
BibTeX
@article{Bian2026,
author = {Bian, Lei and Liu, Cong and Wei, Huanwei and Zhao, Honghua and Li, Xinyang},
title = {Strain Prediction of Pile-Type Adjustable Wind-Turbine Foundation Caps Using XGBoost–SHAP Feature Selection and the TimeXer Model},
journal = {Buildings},
year = {2026},
volume = {16},
number = {12},
pages = {2325},
doi = {10.3390/buildings16122325}
}
EUVIMED