Ould el Moctar

Physics-Informed Neural Networks (PINNs) offer a physically driven alternative to conventional computational fluid dynamics, yet their application to sloshing remains largely unexplored. This paper establishes a self-consistent PINN paradigm for two-dimensional linear sloshing that trains exclusively on physical residuals, requiring no reference data. The dynamic free-surface boundary condition is enforced as a hard constraint, which removes it from the loss function and structurally eliminates the gradient imbalance that dominates conventional penalization-based formulations. This single modification reduces the free-surface elevation error from above 6% to below 2%. Validation against analytical solutions, experimental measurements, and computational fluid dynamic simulations across sway, roll, and combined excitation modes yields median steady-state amplitude deviations below one millimeter across all benchmarks. A systematic ablation study covering six hyperparameter categories and 13 variants isolates the influence of each design choice and yields practical tuning guidance. Because the paradigm relies entirely on physics residuals, it generalizes naturally to configurations for which analytical reference data are unavailable.

In this research, the behavior of a cavitation bubble collapse adjacent to a three dimensional patterned structure was examined through numerical methods. The numerical analysis utilized a compressible two phase flow solver integrated within the open source software OpenFOAM. We specifically investigated how the patterned structure influences the cavitation of a single bubble during its collapse at two distinct relative wall distances, and we illustrated the corresponding pressure and velocity contours surrounding the bubble as it collapses near the boundary at these two relative wall distances. Additionally, the behavior of the bubble near a smooth surface was simulated to contrast the effects of the patterned structure with those of the unaltered surface. The findings indicated that the microjet directed towards the surface wall during the initial collapse of the bubble was influenced by the effects of the patterned structure. Moreover, the maximum pressure exerted on the patterned structure as aresult of the bubble's collapse was considerably lower than the pressure impact experienced on the smooth surface. Furthermore, the equivalent bubble radius and the peak jet velocity during the bubble's initial collapse were significantly reduced due to the influence of the patterned structure. This study offered new perspectives on the intricate fluid dynamics of a cavitation bubble in proximity to a bio inspired structure, which may hold significance for the design and operation of various engineering applications that are susceptible to erosion caused by cavitation bubbles near a boundary.