Article: AI-driven hybrid deep learning for real-time excavation risk assessment in deep foundation pit engineering Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.19 pp.57 - 78 Abstract: Excavation of the deep foundation pit is a challenging organisation due to unstable soil, groundwater seepage, and structural failures. Traditional risk assessments are useful but computationally expensive and inflexible to real-time conditions. This study then proposes a hybrid deep learning model that integrates CNN, LSTM and transformer architectures for improving excavation risk prediction. FEM data are used to capture spatial features, LSTM models sequential deformations, and the transformer incorporating multi-source geotechnical data. The model was validated on a Shanghai excavation project with an RMSE of 2.90 mm, which outperforms FEM, CNN-LSTM and transformer only. In addition, it achieved 94.5% F1 score for failure detection and had reduced inference time to 1.4 seconds. The accuracy and speed of these results provides confidence in the model to be deployed in real-time for safety monitoring and AI based geotechnical risk management. Inderscience Publishers - linking academia, business and industry through research

Title: AI-driven hybrid deep learning for real-time excavation risk assessment in deep foundation pit engineering

Authors: Xuhui Luo

Addresses: Central and Southern China Municipal Engineering Design and Research Institute Co, Ltd., Hube, Wuhan, 430010, China

Abstract: Excavation of the deep foundation pit is a challenging organisation due to unstable soil, groundwater seepage, and structural failures. Traditional risk assessments are useful but computationally expensive and inflexible to real-time conditions. This study then proposes a hybrid deep learning model that integrates CNN, LSTM and transformer architectures for improving excavation risk prediction. FEM data are used to capture spatial features, LSTM models sequential deformations, and the transformer incorporating multi-source geotechnical data. The model was validated on a Shanghai excavation project with an RMSE of 2.90 mm, which outperforms FEM, CNN-LSTM and transformer only. In addition, it achieved 94.5% F1 score for failure detection and had reduced inference time to 1.4 seconds. The accuracy and speed of these results provides confidence in the model to be deployed in real-time for safety monitoring and AI based geotechnical risk management.

Keywords: deep foundation pit engineering; excavation risk prediction; hybrid deep learning; DL; finite element method; FEM; multi-source data fusion; real-time geotechnical monitoring.

DOI: 10.1504/IJICT.2025.146699

International Journal of Information and Communication Technology, 2025 Vol.26 No.19, pp.57 - 78

Received: 24 Mar 2025
Accepted: 16 Apr 2025
Published online: 13 Jun 2025 *

Title: AI-driven hybrid deep learning for real-time excavation risk assessment in deep foundation pit engineering

Keep up-to-date