In deep foundation pit engineering, the rational arrangement of internal struts plays a crucial role in controlling diaphragm wall displacement and minimizing environmental impacts. This study investigates the effects of servo steel struts through model tests, analyzing diaphragm wall displacement, bending moment, surface settlement, and surrounding soil pressure during both excavation and active servo control phases. The results show that installing servo struts near the pit bottom significantly improves deformation control, whereas strut placement in shallow zones more effectively mitigates surface settlement. The servo system dynamically adjusts strut displacements, thereby inducing internal force redistribution in the diaphragm wall and modifying the stress field in surrounding soils. This mechanism leads to an increase in positive bending moments on the wall’s backside, which may necessitate the localized reinforcement of the diaphragm wall at servo strut connections to ensure structural integrity. The lateral wall and surrounding soil pressure exhibit further increase, effectively compensating for the pressure loss induced by excavation unloading. Notably, the influence on soil pressure demonstrates a dissipating trend with an increasing distance from the excavation.

The axial force in assembly steel struts with servo systems is a critical indicator of stability in foundation pit support systems. Due to its high sensitivity to temperature variations and direct influence on the lateral deformation of the foundation pit enclosure structure, accurate prediction is essential for safety monitoring and early warning. This study proposes a novel method for predicting the axial force in assembly steel struts with servo systems based on a spatiotemporal adaptive network. The method begins by feeding historical axial force data from multiple steel struts into an LSTM network to extract temporal sequence features. A self-attention mechanism is then employed to capture the global dependencies within the axial force data, enhancing the feature representation. Concurrently, a convolutional neural network (CNN) is utilized to extract local spatial features. Additionally, excavation depth and excavated soil stratification data are processed through convolutional operations to derive stratification-related features. Subsequently, the temporal and spatial features of axial force are fused with stratification-related features derived from excavation data and further refined through a CNN, enabling more accurate predictions. Validation using deep foundation pit data from a metro station in Zhejiang Province demonstrated the method’s reliability and improved performance across multiple metrics compared to the existing approaches.

The deep foundation pit excavation of subway will cause horizontal displacement, uneven settlement and other adverse effects on the adjacent shield. The use of servo steel strut has a certain effect on deflection correction, but the current understanding of the influencing factors of deflection correction is not comprehensive. Based on structural and spatial symmetry, the influence of tunnel depth, tunnel and foundation pit clear distance and deformation control quantity of enclosure structure on deflection correction quantity was studied by symmetrically designed model test and numerical simulation, and the prediction formula of deflection correction quantity considering tunnel and foundation pit clear distance and deformation control quantity of enclosure structure was proposed. The results show that with an increase in the tunnel’s burial depth, deflection correction decreases significantly. When the tunnel is near the foundation pit bottom, there is no significant correction effect, and the control law of the tunnel ground pressure under the servo steel strut loading is consistent with the correction law. Deflection correction is negatively correlated with the tunnel and foundation pit clear distance, and positively correlated with the deformation control of the diaphragm wall. The curve of the deformation control of the enclosure structure and the deflection correction is parabolic. The deflection correction is an exponential function of the ratio of the deformation control of the enclosure structure to the clear distance between the tunnel and the foundation pit, and the servo deflection correction follows a normal distribution along the longitudinal axis of the tunnel, showing obvious symmetry characteristics in the foundation pit influence zone.