摘要：Immense information and details observation of flow physics inside a draining tank can be achieved by adopting reliable numerical simulations. Yet the accuracy of numerical results has been always debatable and it is mainly affected by the grid convergence error and computational modeling approaches. Hence, this study is divided into two stages. In the first stage, this paper determines a systematic method of refining a computational grid for a liquid draining inside a tank using OpenFOAM software. The sensitivity of the computed flow field on different mesh resolutions is also examined. In order to study the effect of grid dependency, three different grid refinements are investigated: fine, medium and coarse grids. By using a form of Richardson extrapolation and Grid Convergence Index (GCI), the level of grid independence is attained. In this paper, a monotonic convergence criteria is reached when the fine grid has the GCI value below 10% for each parameter. In the second stage, different computational modeling approaches (DNS, RANS k-ε, RANS k-ω and LES turbulence models) are investigated using the finer grid from the first stage. The results for the draining time and flow visualization of the generation of an air-core are in a good agreement with the available published data. The Direct Numerical Simulation (DNS) seems most reasonably satisfactory for VOF studies relating air-core compared to other different turbulence modeling approaches.
其他摘要：Immense information and details observation of flow physics inside a draining tank can be achieved by adopting reliable numerical simulations. Yet the accuracy of numerical results has been always debatable and it is mainly affected by the grid convergence error and computational modeling approaches. Hence, this study is divided into two stages. In the first stage, this paper determines a systematic method of refining a computational grid for a liquid draining inside a tank using OpenFOAM software. The sensitivity of the computed flow field on different mesh resolutions is also examined. In order to study the effect of grid dependency, three different grid refinements are investigated: fine, medium and coarse grids. By using a form of Richardson extrapolation and Grid Convergence Index (GCI), the level of grid independence is attained. In this paper, a monotonic convergence criteria is reached when the fine grid has the GCI value below 10% for each parameter. In the second stage, different computational modeling approaches (DNS, RANS k-ε, RANS k-ω and LES turbulence models) are investigated using the finer grid from the first stage. The results for the draining time and flow visualization of the generation of an air-core are in a good agreement with the available published data. The Direct Numerical Simulation (DNS) seems most reasonably satisfactory for VOF studies relating air-core compared to other different turbulence modeling approaches.
