首页|Data on Machine Learning Described by a Researcher at Indian Institute of Techno logy Roorkee (Local interface remapping based curvature computation on unstructu red grids in volume of fluid methods using machine learning)
Data on Machine Learning Described by a Researcher at Indian Institute of Techno logy Roorkee (Local interface remapping based curvature computation on unstructu red grids in volume of fluid methods using machine learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New study results on artificial intelligence have been published. According to news reporting from Roorkee, India, by NewsRx jour nalists, research stated, "The volume of fluid method is widely used for interfa ce capturing in two-phase flows including surface tension." Financial supporters for this research include Science And Engineering Research Board. Our news reporters obtained a quote from the research from Indian Institute of T echnology Roorkee: "Calculation of surface forces requires accurate local interf acial curvature, which, despite receiving considerable attention, remains a chal lenge due to the abrupt variation of volume fraction near the interface. Based o n recent studies showing the potential of data-driven techniques, a machine lear ning (ML) model using a multi-layered artificial neural network is initially dev eloped to predict curvature on structured grids. Known shapes in the form of cir cular interface segments are used to generate a synthetic training dataset consi sting of interfacial curvature and volume fractions. An optimum model configurat ion is carefully obtained, with a larger 5 x 5 input stencil showing increased a ccuracy for test data along with analytical test cases. However, an extension of the model to unstructured grids, required in simulations involving complex geom etries, is non-trivial. To overcome the limitations, a local interface remapping algorithm is proposed where the stencil around a target cell is transformed int o a structured stencil for the generation of the input dataset."
Indian Institute of Technology RoorkeeRoorkeeIndiaAsiaAlgorithmsCyborgsEmerging TechnologiesMachine Learni ng
NETL
NSTL
