This study investigates the application of machine learning (ML) algorithms for seismic damage classification of bridges supported by helical pile foundations in cohesive soils. While ML techniques have shown strong potential in seismic risk modeling, most prior research has focused on regression tasks or damage classification of overall bridge systems. The unique seismic behavior of foundation elements, particularly helical piles, remains unexplored. In this study, numerical data derived from finite element simulations are used to classify damage states for three key metrics: piers' drift, piles' ductility factor, and piles' settlement ratio. Several ML algorithms, including CatBoost, LightGBM, Random Forest, and traditional classifiers, are evaluated under original, oversampled, and undersampled datasets. Results show that CatBoost and LightGBM outperform other methods in accuracy and robustness, particularly under imbalanced data conditions. Oversampling improves classification for specific targets but introduces overfitting risks in others, while undersampling generally degrades model performance. This work addresses a significant gap in bridge risk assessment by combining advanced ML methods with a specialized foundation type, contributing to improved post-earthquake damage evaluation and infrastructure resilience.

In seasonally frozen areas, freezing of topsoil is detrimental to the seismic response of bridge substructures and may cause bridge damage. In order to counter this problem, this paper proposes the use of a temperature-insensitive composite material (PolyBRuS) to replace the soil around the with the aim of preventing seismic damage brought about by the seasonally frozen soil, which is named as the replacement method. Firstly, a three-dimensional finite element model was built based on the model tests, and the results of the model tests were used for verification and calibration. Secondly, based on the finite element model, a time-history analysis of the seismic response of the bridge substructure was carried out to explore the nonlinear seismic response of the bridge foundation in different seasons and with or without replacement conditions. The result of numerical simulations showed that frozen soil significantly reduced the extent of the plastic zone of the soil under seismic loading and affected the seismic response of the bridge substructure, including an increase of foundation acceleration (19% increase), a decrease of foundation displacement (32% decrease), and an increase of foundation bending moment (10% increase). Notably, it can be found that the replacement method can reduce the seismic acceleration, increased column deformation (21% increase), and reduced column bending moment of the winter bridge foundations (9% decrease), consequently reducing the risk of seismic damage to the bridge substructure. Meanwhile, the compressive stress and compressive strain characteristics of the PolyBRuS material on the column side under seismic action are similar to those of unfrozen soil in summer. Above all, the adverse effects of surface freezing on bridge substructures can be effectively mitigated by the replacement method, and the bridge foundations will have similar seismic responses in winter and summer. This achievement has practical application prospects and is expected to provide a new seismic strategy for bridge engineering in seasonally frozen soil areas.

This paper presents a case study of a bridge failure during construction in an infrastructure development project in Nakhon Si Thammarat, Thailand. This highlights the critical role of thorough inspection and early detection of structural failures. The failure, related to foundationrelated issues, shows how even minor errors in the construction sequence can lead to significant structural problems. Key steps for evaluating foundation failures are assessing the structure's movement and utilizing an inclinometer to determine ongoing failure. Resistivity surveys, in conjunction with screw driving sounding tests (SDS), were performed to assess soil properties, while the finite element method (FEM) was applied to validate the observed failure behavior. The results show that an inclinometer effectively monitored these structures' movement. The resistivity surveys proved useful in identifying soil layers in the wide area. Meanwhile, the SDS tests were able to determine the soil's undrained shear strength. FEM simulations provided valuable insights into the behavior of underground structures. Consequently, comprehensive inspections are essential to mitigate foundation failure risks and ensure critical structures' safety and longevity.

Long-span river or sea crossing bridge projects are commonly subjected to significant and complex long-term cyclic loads driven by factors such as wind and waves. The lattice-shaped diaphragm wall (LSDW) foundation, a novel and promising solution for long-span bridges, offers advantages in construction safety, adaptability, costeffectiveness, and stiffness. However, research in this area remains limited, impeding the further application of LSDWs. This study comprehensively investigates the bearing behavior of LSDWs under horizontal cyclic loads in soft soils. It introduces a detailed methodology utilizing a dual-layer wall setup and mathematical calculations to measure key parameters such as wall bending moments, displacements, and soil pressures. The research explores LSDW behavior throughout cyclic loading cycles, revealing trends in soil compression, densification, and displacement growth rates. Analysis of cumulative displacement and rotation patterns underscores the influence of load amplitudes and wall stiffness. The findings highlight the significant impact of cyclic loading cycles on cumulative displacement, with curve fitting revealing a logarithmic function with a strong correlation. Additionally, the study delves into the reduction in lateral soil resistance with increasing cyclic loads, proposing cyclic weakening factors for predicting soil pressure distribution and cyclic p-y curves. This study offers valuable insights into the comprehensive analysis and prediction of the performance of LSDW subjected to horizontal cyclic loading, with potential implications for long-span bridge construction projects.

A shaking table test for a bridge foundation reinforced by anti-slide piles on a silty clay landslide model with an inclined interlayer was performed. The deformation characteristics of the bridge foundation piles and anti-slide piles were analyzed in different loading conditions. The dynamic response law of a silty clay landslide with an inclined interlayer was summarized. The spacing between the rear anti-slide piles and bridge foundation should be reasonably controlled according to the seismic fortification requirements, to avoid the two peaks in the forced deformation of the bridge foundation piles. The blocking effect of the bridge foundation piles reduced the deformation of the forward anti-slide piles. The stress-strain response of silty clay was intensified as the vibration wave field appeared on the slope. Since the vibration intensified, the thrust distribution of the landslide underwent a process of shifting from triangle to inverted trapezoid, the difference in the acceleration response between the bearing platform and silty clay landslide tended to decrease, and the spectrum amplitude near the natural vibration frequency increased. The rear anti-slide piles were able to slow down the shear deformation of the soil in front of the piles and avoid excessive acceleration response of the bridge foundation piles.

The structure of a bridge has certain peculiarities, and its pile foundations are susceptible to uplift or settlement deformation due to various factors. This can result in bridge deck cracking, structural instability, tilting, and even irreversible damage, which significantly impacts the bridge's stability and driving safety. This study focuses on the Shiyangtai No.1 Bridge and aims to investigate the factors that cause abnormal rise and fall deformations of bridge pile foundations. The study combines macro and micro analysis, physical characteristic testing of the overlying soil under the bridge pile foundation, and numerical simulation of the bridge pile foundation in the goaf. The study discusses in-depth the formation mechanism of the abnormal uplift of some pile foundations of the Shiyangtai No.1 Bridge based on the analysis of the factors influencing the abnormal rise and fall deformation of the bridge pile foundations at home and abroad. The expansive soil beneath the pile foundation is weak, and the force generated by the water expansion is insufficient to cause the pile foundation to rise to 309 mm. The results indicate that the pile foundation of the bridge is not affected by the expansion characteristics of the overlying soil. The collapse of the goaf roof generates double lateral thrust from the accumulation body at the bottom of the goaf and the upper collapse arch. This causes staggered bending uplift of the sandstone soil layer, resulting in upward squeezing pressure that causes the bridge pile foundation to rise. Therefore, the coal mining area is the main factor influencing the abnormal uplift of the pile foundation of the Shiyangtai No.1 Bridge.