Pile base resistance is an important part of the ultimate bearing capacity, and the soil within a certain range above and below the pile end contributes to the pile base resistance. In general, pile base resistance is calculated according to the average value of soil strength within a certain range of the pile end in the current calculating method, so it is very important to determine the influence range of pile base resistance. Based on the soil parameters and the results of the cone penetration test of the LiuHua 11-1 site in the South China Sea, the difference of pile base resistance calculated by different methods, the regularity of pile base resistance affected by calculation depth range is revealed. Additionally, the numerical simulation method is used to analyze the distribution of a plastic zone around the pile end in homogeneous soil and stratified soil, the results show the influence depth range of pile base resistance is 0.12 D above the pile end to 0.83 D below the pile end in clay, and the influence depth range is 0.9 D above the pile end to 1.3 D below the pile end in stratified soil.

The randomness and complexity of ice loads present major challenges to the safety and stability of offshore platforms. Traditional methods for identifying ice loads often lack accuracy and adaptability under changing environmental conditions. This study proposes a novel inversion method based on Temporal Convolutional Networks (TCNs), integrating finite element simulation with deep learning to effectively identify random ice loads. A random ice load model is first developed, and its dynamic characteristics are validated through finite element analysis. The TCN model is then applied to capture the time-dependent features of ice loads. To improve the model’s generalization ability, its hyperparameters are optimized using particle swarm optimization (PSO). The results show that the TCN model achieves goodness-of-fit (R²) values of 0.821 and 0.808 on the training and test sets, respectively, indicating strong predictive performance. Under different ice thickness and velocity conditions, the model achieves R² values close to 0.99, demonstrating high robustness. This work represents the first application of TCN to ice load identification. By combining it with simulation data, we offer a high-precision, data-driven approach for dynamic load identification, enhancing the efficiency and reliability of safety assessments for conical offshore platforms.

Infrastructure located on the seabed is vulnerable to earthquake-triggered submarine landslides, although the propagation of failure and the post-seismic movement of slides on the continental margin or in a submarine canyon have not been well interpreted. A three-dimensional depth-averaged method was used to revisit the initiation, progressive failure, and runout of two typical scenarios: a back-analysis of the deep-seated Ashton Seamount landslide and a scenario prediction in a canyon system in the South China Sea. For the former, the shear band is propagated extensively through a weak layer prior to the slab failure of thick overlying sediment. The influence of soil sensitivity on initial co-seismic softening may be insignificant, while it severely affects the subsequent shear band propagation and runout. The ratio of the affected area approaches six as soil sensitivity is increased from two to five. In the canyon system, several fully softened regions may be caused independently on steep canyon flanks. These regions are then progressively expanded and merged during the earthquake. The sliding masses move along several canyon channels before converging at the gully junctions. Sediment downslope is removed during the initial slope failure, thereby impairing the support provided to the upslope sediment and suggesting more retrogressive failures even after the earthquake. As a result, a peak velocity of 40.8 m/s and an affected area of 23.4 km² are predicted.

Submarine landslides are a major geohazard in deep water, posing a severe threat to the safety of seabed infrastructure. Progressive failure on gentle slopes is commonly governed by strain softening of soils and shear band propagation (SBP). Several criteria have been developed analytically and numerically to predict catastrophic failure initiated from a pre-existing fully softened zone. In this study, dynamic SBPs during the progressive formation of an externally softened zone are investigated. Strength degradation is caused by both externally imposed softening and cumulative shear deformation. The governing dynamic equation is solved using a finite difference method. Depending on the extent of externally imposed softening, finite SBP followed by slope re-equilibration and catastrophic SBP are identified. The critical length of the externally softened zone required for catastrophic failure is quantified for different terminal strengths and formation durations. Two limiting lengths of the externally softened zone are determined. Below the lower limit, catastrophic failure cannot be triggered even when the zone is fully softened. Above the upper limit, only a slight strength reduction below the gravitational shear stress is sufficient to initiate catastrophic failure. The effect of the duration of externally imposed softening is also explored. Simple empirical criteria are proposed to predict both limiting lengths for practical application.