Multi‐fidelity data meta‐learning approach for seismic response prediction of high‐rise shear wall buildings
Computer-Aided Civil and Infrastructure Engineering · 2025-12 · 40 (29) · 5512-5533
DOI: 10.1111/mice.70103 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer-Aided Civil and Infrastructure Engineering, 2025-12. Verfasst von Chenyu Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Rapid and accurate estimation of seismic responses in city‐scale buildings is critical for post‐earthquake loss assessment and pre‐event identification of vulnerable buildings. However, conventional numerical simulation methods struggle to balance efficiency and accuracy when applied to large‐scale buildings, while existing data‐driven methods often rely on single‐source datasets, limiting generalizability. Numerical simulation data of varying detail (e.g., floor‐ and component‐based models) and field monitoring data form inherently multi‐fidelity datasets, but integrating these heterogeneous sources remains challenging, particularly when different fidelities correspond to different building targets. To address this gap, we propose a multi‐fidelity meta‐learning algorithm that extends deep learning methods for seismic response prediction, demonstrated on multiple high‐rise shear wall buildings. The proposed algorithm enables incremental data learning and model updates and is applied and validated across datasets of varying fidelities, including multiple numerical simulations and field monitoring data. Under small‐sample field monitoring scenarios, the proposed method reduces overall prediction errors by 40.4%, compared to the typical transfer learning approach, demonstrating superior learning capabilities in limited‐data settings. Additionally, to account for inaccuracies and potential noise in acquired structural information inputs under real‐world conditions, the meta‐learning model was trained and evaluated with varying levels of noise based on field monitoring data. Results indicate that the proposed meta‐learning algorithm exhibits strong robustness when handling noisy inputs.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhang, C., Zhai, C., Wen, W., & Zhang, G. (2025). Multi‐fidelity data meta‐learning approach for seismic response prediction of high‐rise shear wall buildings. Computer-Aided Civil and Infrastructure Engineering, 40(29), 5512-5533. https://doi.org/10.1111/mice.70103
Vancouver
Zhang C, Zhai C, Wen W, Zhang G. Multi‐fidelity data meta‐learning approach for seismic response prediction of high‐rise shear wall buildings. Computer-Aided Civil and Infrastructure Engineering. 2025;40(29):5512-5533. doi:10.1111/mice.70103
BibTeX
@article{Zhang2025,
author = {Zhang, Chenyu and Zhai, Changhai and Wen, Weiping and Zhang, Guoqing},
title = {Multi‐fidelity data meta‐learning approach for seismic response prediction of high‐rise shear wall buildings},
journal = {Computer-Aided Civil and Infrastructure Engineering},
year = {2025},
volume = {40},
number = {29},
pages = {5512--5533},
doi = {10.1111/mice.70103}
}
EUVIMED