A large-scale series of cyclic triaxial tests were conducted to explore the evolution of the dynamic resilient modulus of silty clay for the heavy-haul railway subgrade. A novel loading sequence for measuring the dynamic resilient modulus was established, which characterized the dynamic stress state of the subgrade induced by the heavy-haul train load. In the experimental investigation, the deviatoric stresses, confining stress, initial moisture content, and compaction degree were considered as variables, and the effects of the aforementioned variables were evaluated quantitatively. The experimental results showed that the dynamic resilient modulus was negatively related to deviatoric stresses and initial moisture content, where the average decreased rates were 14.65% and 27.79% with the increase in deviatoric stresses from 60 kPa to 150 kPa and increase in the initial moisture content from 9.8% to 15.8%, respectively. Furthermore, the dynamic resilient modulus was positively related to confining stress and compaction degree, where the average increased rates were 23.25% and 27.48% with the increase in confining stress from 20 kPa to 60 kPa and increase in compaction degree from 0.91 to 0.95. To provide a better application, the two high-accuracy predicted methods were established through the empirical model and artificial neural network approach including the aforementioned variables. This study can provide useful guidelines for the effective and safe design of the heavy-haul railway subgrade filled with silty clay.

The bearing capacity of the rock‐socketed part of the end‐suspended pile and rock‐socketed pile was investigated. Numerical models have been partially established with half of the pile and half of the pile space to simplify the model and reduce the number of elements. The strain‐softening model was adopted for the rock mass, and the Coulomb friction model was used to simulate the friction between the pile and the soil. Subsequently, the stress deformation and bearing capacity were obtained in the numerical simulation analysis. Finally, the effects of the different support structures, rock‐socketed depth, diameter, spacing, and rock shoulder width on piles were analyzed. The numerical results show that both the ultimate bearing capacity and the antideformation capacity of the end‐suspended pile are lower than those of the rock‐socketed pile. The bearing capacity of both the end‐suspended pile and rock‐socketed pile increases with an increase in rock‐socketed depth, diameter, and spacing. In addition, the performance of the end‐suspended pile is also positively correlated with the rock shoulder width.

The shakedown state of the subgrade is crucial for the sustainable design and long-term stability evaluation of pavement structures. In order to characterize the plastic deformation and shakedown behavior of subgrade soil in seasonal frozen regions, cyclic triaxial tests were conducted on the thawed subgrade soil after seven cycles of freeze-thaw. The influences of the numbers of cycle loading, the amplitude of cyclic deviator stress, and the confining stress were considered variables. The evolution features of accumulative plastic strain, accumulative plastic strain rate, and critical dynamic stress were experimentally analyzed. Based on the shakedown theory, the ensuing discoveries were that the accumulative plastic strain response-behavior of thawed subgrade soil was typically divided into plastic shakedown, plastic creep, and incremental collapse under the long-term cyclic loading. Furthermore, the shakedown standard for thawed subgrade soil was also proposed based on the evolution of the accumulative plastic strain rate. The critical dynamic stresses can be obtained by the proposal formula to determine the different plastic deformation ranges.

The high-precision geometric measurement capabilities of sensor-based point clouds provide significant advantages for sewer defect detection. To enhance the classification of valuable yet data-scarce sewer-defect knowledge within the point cloud community, this study proposes a cross-modal framework that combines self-supervised pre-training with supervised fine-tuning. The proposed Sewer Vision Transformer (Sewer-ViT) integrates key-edge sampling, neighborhood dilation learning, dual-domain feature fusion, and inverted bottleneck structures to reinforce defect feature embedding and inductive bias. These features are subsequently processed by a transformer encoder pre-trained with two-dimensional in-domain knowledge, and the latent representations are further optimized through weight fusion within a unified vector space, thereby improving classification performance. The method achieved average precision, recall, and F1-scores of 75.87%, 76.73%, and 75.44% on the overall test set, and 65.09%, 62.47%, and 62.58% on a real-world test set, respectively—surpassing existing approaches. These results highlight the practical potential of this method for sewer defect detection and point to a promising future for multi-modal fusion research.

A three-dimensional dynamic model of vehicle-road-unsaturated subgrade coupling is established. The semi-analytical and numerical solutions of three-dimensional dynamic response of highway subgrade under vehicle load are presented for the first time. Then, the accuracy of the theoretical model is verified by the field measurement data. Finally, the spatial distribution of dynamic stress and depth of working zone under different influencing factors are studied, and the calculation model of depth of working zone of highway subgrade is proposed. The results show that the dynamic stresses, σ_x, σ_y, σ_z, and τ_xz increase significantly with the increase of vehicle axle load and decrease significantly with the increase of road thickness under the same subgrade depth. In addition, with the increase of axle load and the decrease of road thickness, the peak values of dynamic stress σ_x, σ_y, σ_z, and τ_xz decrease more obviously along the depth of roadbed. In the process of vehicle movement, the traditional subgrade working area can be divided into a sensitive area and an influence area of dynamic load. The depth of these two areas is positively correlated with the axle load of the vehicle and negatively correlated with the thickness of the road surface. The advantage of the model in this paper is that the semi-analytical solution of the total stress component of the soil element in the course of traffic load is given.