
This paper investigates the isothermal sloshing characteristics of a circular tank. The liquid motion and free-surface evolution are numerically simulated using the open-source computational fluid dynamics tool OpenFOAM. Based on the CCP-WSI blind test series 5, numerical results are systematically compared with experimental data in terms of free-surface evolution, oscillation frequency, and amplitude variation to validate the reliability and accuracy of the proposed numerical model. Using the validated approach, the sloshing responses under various excitation conditions are further analysed, with particular attention paid to the temporal characteristics and spatial distribution of the free-surface motion, as well as the non-linear and asymmetric features of sloshing behaviour. In addition, the influence of vertical baffles on sloshing mitigation in a horizontally oriented circular tank is investigated by comparing cases with and without baffles of different heights. The present study provides useful guidance for the design and optimisation of sloshing mitigation measures in circular storage tanks.
Accurate ship-motion prediction and early identification of unstable navigation states are essential for autonomous vessels operating in following-oblique waves. This study proposes a physics-guided long short-term memory (LSTM)–Transformer encoder–decoder model for joint motion prediction and surf-riding/broaching identification of an autonomous trimaran. Numerical simulation data are generated under different operating conditions, and physics-based state labels are constructed using the ship–wave speed ratio, heading deviation, yaw-rate response and rudder saturation. The proposed framework combines LSTM-based local temporal feature extraction with Transformer-based global dependency modelling. A state-identification branch is further introduced, and a multi-objective loss function is designed by integrating motion prediction, state classification, physical consistency and ordinal risk constraints. Comparative studies with different models and model variants are conducted to evaluate the prediction accuracy, robustness and generalisation capability of the proposed method. The results show that physically meaningful variables and state-related constraints strongly affect the prediction of navigation-state features. The proposed model improves both motion-response prediction and unstable-state identification, providing a more interpretable and reliable short-term forecasting framework for surf-riding and broaching conditions.
Accurate prediction of wave overtopping discharge is essential for designing resilient coastal defences against increasing climate threats. This study demonstrates the superior performance of advanced machine learning models over traditional methods. Using an extensive dataset from EurOtop manual, authors developed and benchmarked models including convolutional and long short-term memory neural networks (CNNs and LSTMs), enhanced with attention mechanisms. Bayesian hyperparameter optimisation ensured robust performance. Predictive uncertainty was quantified via bootstrap resampling (100 ensembles). Results show LSTMs with attention achieved the highest predictive accuracy (R2 = 0.8704, RMSE = 0.0620), effectively capturing complex non-linear dependencies in wave-structure interactions. Coverage analysis revealed systematic under-coverage: 66.7% for the lowest predicted quartile rising to 89.2% for the highest, indicating overconfidence. Partial dependence plots are used to visualise the marginal effect of top input features of the best model, confirming physically expected trends. Permutation feature importance identified relative freeboard and roughness factor as the dominant predictors. The integration of attention mechanisms improved model interpretability by identifying most influential input features. This work provides a reliable, computationally efficient framework that surpasses traditional methods, offering coastal engineers a tool for coastal infrastructure risk assessment, design optimisation, and climate adaptation planning.
Subsea pipelines on a soft clayey seabed in deep waters are susceptible to lateral instability under steady currents. Two distinct mechanisms govern such instability behaviours: shear failure of the underlying soil (mechanism I) or slippage along the pipe–soil interface (mechanism II). This study presents a unified analytical model, based on limit equilibrium analysis and passive earth pressure theory, to quantify the ultimate lateral resistance while explicitly capturing the interplay between these competing mechanisms and the influence of the soil berm. The model is validated against experimental data and benchmarked against existing empirical solutions. Parametric analyses demonstrate that the critical embedment ratio for lateral stability decreases with increases in either soil undrained shear strength or pipe submerged weight. Furthermore, the governing mechanism exhibits contrasting trends: stiffer soils promote interface slippage (mechanism II), whereas greater pipe weight or higher interface adhesion favours soil shear failure (mechanism I). From these insights, an explicit correlation is established at the transition point, relating the critical dimensionless net vertical force to the embedment ratio and interface adhesion factor. This relationship identifies the dominant instability mode, offering a practical, mechanics-based tool for subsea pipeline on-bottom stability design.