Search

Research Progress and Comparative Study of Deep Excavation Deformation Prediction Models under Complex Geological Conditions

Author(s)

Guohao Feng, Shiwei Shen*

Affiliation(s)

College of Construction Engineering, Jilin University, Changchun, China *Corresponding Author

Abstract

With the continuous development of urban underground space, the safety and construction control of deep foundation pits have become a central focus in engineering management and design research. Predicting foundation pit deformation plays a vital role in ensuring construction safety, optimizing support design, and mitigating construction risks. This paper reviews the primary methods for predicting pit deformation and systematically analyzes the factors affecting prediction accuracy, with particular emphasis on key aspects of data acquisition and processing, including data quality, feature selection, spatial distribution, and temporal continuity. Through a synthesis and comparison of domestic and international research findings, it is highlighted that high-quality, multi-dimensional, and spatiotemporally continuous monitoring data are decisive for enhancing the reliability and accuracy of predictive models, while the spatiotemporal coupling characteristics of deformation are emphasized as critical in the analysis of deformation evolution.

Keywords

Deformation Prediction; Monitoring Data; Influencing Factors; Nonlinear Models

References

[1] Zhu Z, Chang D, Xu F, et al. Deformation Control and Early Warning Analysis of Deep Riverside Foundation Pit Construction Process Based on Machine Learning [J]. World Journal of Engineering and Technology, 2025,13(03):536-555. [2] Wenbo L, Tingting L, Xiao L. ModuCLIP: multi-scale CLIP framework for predicting foundation pit deformation in multi-modal robotic systems [J]. Frontiers in Neurorobotics,2025,191544694-1544694. [3] Liu R, Zhang Q, Jiang F, et al. Research on Deformation Prediction of VMD-GRU Deep Foundation Pit Based on PSO Optimization Parameters [J]. Materials,2024,17(10): [4] Ouyang X, Nie J, Xiao X. Study of Improved Grey BP (Back Propagation) Neural Network Combination Model for Predicting Deformation in Foundation Pits [J]. Buildings,2023,13(7): [5] Qiang L, Yan C Y, Li L. Deformation Prediction of a Deep Foundation Pit Based on the Combination Model of Wavelet Transform and Gray BP Neural Network [J]. Mathematical Problems in Engineering,2021,2021 [6] Zhao Y, Zhang J, Li H. Deformation prediction analysis of vertical displacement of deep foundation pit based on LIBSVM [J]. E3S Web of Conferences, 2020,20601021-. [7] Yunhong G, Shihao Z. Application of GA-BP in Displacement Force Inverse Analysis and Mechanical Parameter Inversion of Deep Foundation Pits [J]. European Journal of Computational Mechanics,2023,32(1):53-84. [8] Xiaofeng W, Song Y, Di Z, et al. Transformer based neural network for daily ground settlement prediction of foundation pit considering spatial correlation [J]. PloS one, 2023,18(11):e0294501-e0294501.