In recent years, the high development of high-speed railway lines cross through areas with poor geological conditions, such as soft soil, offshore and low-lying marsh areas, resulting geotechnical problems, such as large settlements and reduction of bearing capacity. As a new soil reinforcement method in high speed railway lines, the piled raft structure has been used to improve soil conditions and control excess settlement. In order to study the dynamic behavior of piled raft supported ballastless track system in soft soil, an experimental study on vibration velocities of piled raft supported embankment and foundations is presented in soft soil with different underground water levels. Vibration velocities at specified positions of the piled raft supported embankment and foundations are obtained and discussed. The vibration velocity curves on various testing locations of piled raft foundations are clearly visible and have sharp impulse and relaxation pattern, corresponding to loading from train wheels, bogies, and passages. Vibration velocity distribution in the horizontal direction at three train speeds clearly follows an exponential curves. Most of the power spectrums of vibration velocity at various locations are mainly concentrated at harmonic frequencies. The change in water level has slight impaction on the peak spectrum of vibration velocity at harmonic frequencies. The vibration power induced by train loads are transmitted, absorbed, and weakened to a certain extent through embankment and piled raft structure. The dynamic response character of embankments are affected by their self-vibration characteristics and the dynamic bearing capacity of the piled raft structure.

The three-dimensional finite difference method was used in this study to analyze the deformation and stresses of a passive pile under surcharge load in extensively deep soft soil. A three-dimensional numerical model was proposed and verified by a field test. The horizontal displacements of the pile agreed well with the field results. This study investigated the pile-foundation soil interaction, the load transfer mechanism, the excess pore water pressure (EPWP), and the horizontal resistance of the foundation soil. The results show that the soil in the corner of the loading area developed a large uplift deformation, while the center of the loading area developed a large settlement. The lateral displacement of the pile decreased sharply with the increase of the depth and increased with the surcharge load. The lateral displacement of the soil was negligible when the depth exceeded 30 m. The EPWP increased in a nonlinear way with the increase of the surcharge load and accumulated with the placement of the new lift. The distribution of the lateral earth pressure in the shallow soil layer was complex, and the negative value was observed under a high surcharge load due to the suction effect. The proportion coefficient of the horizontal resistance coefficient showed much smaller value in the situation of large lateral deformation and high surcharge load. The design code overestimated the horizontal resistance of the shallow foundation soil, which should be given attention for the design and analysis of the laterally loaded structures in extensively soft soil.

Large‐scale model tests were established at a scale of 1/5 using a 7 m deep model tank with cross‐sectional dimension of 5 m × 4 m, to study the vibration response characteristics of ballastless track, embankment, and X‐section piled raft foundation under cyclic axial load, including the vibration displacement, velocity, dynamic soil, and pile stress. Cyclic dynamic loading can be achieved by controlling the loading frequency and cycles through the vibration servo control loading system. The test results are presented in the variation of dynamic displacement, velocity, and stress of X‐section piled raft composite foundation. The vibration displacement, velocity, and stress of the track, embankment, and pile foundation follow a pattern of vibration characteristics of loading sine wave. The vibration characteristics of loading waves can be identified easily from the peaks and troughs in the dynamic response of displacement, velocity, and stress at many locations of track slab, embankment, cushion, and underlying soil, at which the vibration response presents almost monotonically increasing tendency with the loading frequencies. With the increase of loading frequency, the vibration responses at the track structure and embankment have higher increasing rates than those at substructure (raft, cushion, and subsoil). The piled raft bears more dynamic load than cushion and subsoils, to ensure long‐term dynamic stability and safety of the foundation soils. The model testing results provide a better understanding of the dynamic response characteristics of ballastless track, embankment, and X‐section piled raft foundation under cyclic axial load in soft soil.

A series of dynamic large-scale model tests and three-dimensional finite element analyses were conducted to investigate the dynamic response of track embankment and XCC pile-raft composite foundation in soft soil for a ballastless high-speed railway under moving train loads. The results indicate that the vibration velocity obtained from the FE numerical simulation agrees well with that from the model test in vibration waveform, amplitude, and frequency characteristics. The peak values corresponding to the passing frequency of train carriage geometry (lc = 25 m), bogie (lab = 7.5 m), and axle distance (lwb = 2.5 m) respectively reflect the characteristic frequencies of the train compartment, adjacent bogie, and wheel load passing through. The peak velocity significantly depends on the distance from the track center in the horizontal direction, of which the attenuation follows the exponential curve distribution. The vibration velocities decrease rapidly within embankment, show a vibration enhancement region from raft to the 1 m depth of foundation soil, then decreases gradually along the subsoil foundation, to a very low level at the bottom of the subsoil, which is much lower than that at the track slab and roadbed. The pile-raft composite foundation can reduce the vibration level effectively and improve the safety of trains running in soft soil areas.

During the construction of deep foundation pits, closely monitoring the deformation of the foundation pit retaining structure is of vital importance for ensuring the stability and safety of the foundation pit and reducing the risk of structural damage caused by foundation pit deformation. While theoretical and numerical methods exist for displacement prediction, their practical application is often hindered by the complex, non-linear nature of soil behavior and the numerous influencing parameters involved, making direct calculation methods challenging for real-time prediction and control. To address this, this study proposes a novel and interpretable machine learning framework for modeling both vertical and horizontal displacements in foundation pit engineering. Six widely used machine learning algorithms—Decision Tree (DT), Random Forest (RF), Extremely Randomized Trees (ET), K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGB), and Light Gradient Boosting Machine (LGBM)—were developed and compared. To improve model performance, the Sparrow Search Algorithm (SSA) was employed for hyperparameter optimization, leading to the creation of hybrid models such as SSA-XGB and SSA-LGBM. The SSA-optimized XGBoost (SSA-XGB) model achieved superior performance, with R² values of 0.988 and 0.990 for vertical and horizontal displacement prediction, respectively, alongside the lowest RMSE (0.785 and 5.684) and MAE (0.562 and 2.427). Notably, the study also found that hyperparameter tuning does not consistently enhance model performance; in some cases, simpler baseline models such as unoptimized ET performed better in noisy environments. Furthermore, SHAP-based interpretability analysis revealed a strong mutual dependency between vertical and horizontal displacements: horizontal displacement was the most influential feature in predicting vertical displacement, and vice versa. Overall, the proposed SSA-XGB model offers a reliable, cost-effective, and interpretable tool for excavation-induced displacement prediction.