During the construction of deep foundation pits in subways, it is crucial to closely monitor the horizontal displacement of the pit enclosure to ensure stability and safety, and to reduce the risk of structural damage caused by pit deformations. With advancements in machine-learning (ML) techniques and correlation analysis in engineering, data-driven methods that combine ML with engineering monitoring data have become increasingly popular. These methods offer benefits such as high prediction accuracy, efficiency, and cost effectiveness. The main goal of this study was to develop a machine-learning method for predicting the enclosure deformation of deep foundation pits. This was achieved by analyzing the factors influencing deep foundation-pit enclosure deformation and incorporating historical cases and monitoring reports. The performance of each machine-learning prediction model was systematically analyzed and evaluated using K-Fold cross validation. The results revealed that the random forest model outperformed the other models. The result of the test data showed that the random forest model achieved an R² of 0.9905, an MAE of 0.8572 mm, and an RMSE of 1.9119 mm. Feature importance analysis identified the depth of enclosure structure, water level, surface settlement, axial force, and exposure time as the most critical factors for accurate prediction. The depth of the enclosure structure had an especially significant impact on the prediction of enclosure deformation.

To improve design rationality and deformation control of inclined-front, vertical-rear, double-row pile retaining structures in soft soil, we consider the foundation pit of the Xiantao Citizen Service Center, Hubei, China. We aim to numerically optimize pile reinforcement configuration in soft soil. Based on on-site measurements and finite element simulations, we study front pile angle, tie beam–soil interaction; range, depth, and elastic modulus of inter-pile soil reinforcement; pile displacement; bending moment; mechanical properties of pile displacement; pile displacement; bend moment; etc. We conclude that (1) inter-pile soil reinforcement strongly influences overall pile displacement, and the tie beam restricts local pile top displacement; (2) optimal deformation control is achieved when reinforcement depth is 1 to 1.5 times excavation depth; and (3) an elastic modulus of 200 to 300 MPa for reinforcement is best for displacement control. These results provide theoretical and practical guidance on parameter optimization and engineering design of similar soft-soil support structures.