In the waterway construction projects of the upper reaches of the Yangtze River, crushed mudstone particles are widely used to backfill the foundations of rock-socketed concrete-filled steel tube (RSCFST) piles, a structure widely adopted in port constructions. In these projects, the steel-mudstone interfaces experience complex loading conditions, and the surface profile tends to vary within certain ranges during construction and operation. The changes in boundary conditions and material profile significantly impact the bearing performance of these piles when subjected to cyclic loads, such as ship impacts, water level fluctuations, and wave-induced loads. Therefore, it is necessary to investigate the shear characteristics of the RSCFST pile-soil interface under cyclic vertical loading, particularly in relation to varying deformation levels in the steel casing's outer profile. In this study, a series of cyclic direct shear tests are carried out to investigate the influential mechanisms of roughness on the cyclic behavior of RSCFST pile-soil interfaces. The impacts of roughness on shear stress, shear stiffness, damping ratio, normal stress, and particle breakage ratio are discussed separately and can be summarized as follows: (1) During the initial phase of cyclic shearing, increased roughness correlates with higher interfacial shear strength and anisotropy, but also exacerbates interfacial particle breakage. Consequently, the sample undergoes more significant shear contraction, leading to reduced interfacial shear strength and anisotropy in the later stages. (2) The damping ratio of the rough interface exhibits an initial increase followed by a decrease, while the smooth interface demonstrates the exact opposite trend. The variation in damping ratio characteristics corresponds to the transition from soil-structure to soil-soil interfacial shearing. (3) Shear contraction is more pronounced in rough interface samples compared to the smooth interface, indicating that particle breakage has a greater impact on soil shear contraction compared to densification.

This study presents a comprehensive investigation into the cyclic shear behavior of sand-fly ash mixtures through experimental and data-driven modeling approaches. Cyclic direct shear tests were conducted on mixtures containing fly ash at 0%, 2.5%, 5%, 10%, 15%, and 20% by weight to examine the influence of fly ash content on the shear behavior under cyclic loading conditions. The tests were carried out under a constant stress of 100 kPa to simulate field-relevant stress conditions. Results revealed that the fly ash content initially reduces shear strength at lower additive contents, but shear strength increases and reaches a maximum at 20% fly ash content. The findings highlight the trade-offs in mechanical behavior associated with varying fly ash proportions. To enhance the understanding of cyclic shear behavior, a Nonlinear Autoregressive Model with External Input (NARX) model was employed. Using data from the loading cycles as input, the NARX model was trained to predict the final shear response under cyclic conditions. The model demonstrated exceptional predictive performance, achieving a coefficient of determination (R2) of 0.99, showcasing its robustness in forecasting the cyclic shear performance based on the composition of the mixtures. The insights derived from this research underscore the potential of incorporating fly ash in sand mixtures for soil stabilization in geotechnical engineering. Furthermore, the integration of advanced machine learning techniques such as NARX models offers a powerful tool for predicting the behavior of soil mixtures, facilitating more effective and data-driven decision-making in geotechnical applications. Evidently, this study not only advances the understanding of cyclic shear behavior in fly ash-sand mixtures but also provides a framework for employing data-driven methodologies to address complex geotechnical challenges.