Research on deep excavation deformation prediction model based on machine learning algorithms
Archives of Civil Engineering · 27.02.2026 · 393-393
DOI: 10.24425/ace.2026.157481 ↗Kurz gefasst
Fachartikel in der Zeitschrift Archives of Civil Engineering, online erschienen am 27.02.2026. Verfasst von Yujun Guo und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Due to the continuous rise of urban underground space development, there has been an increasing number of deep excavation project in recent years, in China. The complexity of hydrogeological conditions and surrounding environment makes it difficult to calculate the deformation of excavation wall caused by deep excavation. Based on the monitoring data during the entire deep excavation process, four datadriven machine-learning algorithms were developed and evaluated in this study to predict deep horizontal displacement (DHD) of excavation wall considering the excavation process and spatial effect. The results showed that the XGBoost algorithm has the best performance, with an RMSE of 2.3397, an MAE of 1.5732 and ��2 of 0.9088. Furthermore, it has higher accuracy in predicting the DHD at the corners, followed by the deformation caused by excavation stage 2. It can be seen that the machine-learning algorithms can be a potential tool for predicting DHD caused by deep excavation in practical engineering.
Zitieren
APA
Guo, Y., Yang, X., & Deng, Y. (2026). Research on deep excavation deformation prediction model based on machine learning algorithms. Archives of Civil Engineering, 393-393. https://doi.org/10.24425/ace.2026.157481
Vancouver
Guo Y, Yang X, Deng Y. Research on deep excavation deformation prediction model based on machine learning algorithms. Archives of Civil Engineering. 2026:393-393. doi:10.24425/ace.2026.157481
BibTeX
@article{Guo2026,
author = {Guo, Yujun and Yang, Xu and Deng, Yansheng},
title = {Research on deep excavation deformation prediction model based on machine learning algorithms},
journal = {Archives of Civil Engineering},
year = {2026},
pages = {393--393},
doi = {10.24425/ace.2026.157481}
}
EUVIMED