In addition, structures made in composite often present a complex behaviour, due to their unconventional elastic properties.A numerical simulation is then a starting point of an innovative andsafe design.Conventional techniques (nite elements for example) are not su-cient or simply not ecient in providing a satisfactory description of these phenomena.
The work is primarily focused on the study of the fracture mechanics with emphasis to composite materials, which are widely employed in the aerospace and automotive industry.Since human lives are involved, it is highly important to know how such structures react in case of failure and, possibly, how to prevent them with an adequate design.It has become of primary importance to simulate the material response in composite, especially considering that even a crack, which could be invisible from the outside, can propagate throughout the structure with small external loads and lead to unrecoverable fracture of the structure. MeshfreeFlowNet and show that it efficiently scales across large clusters,Īchieving 96.AbstractThe proposed research is essentially concerned on numerical simulation of materials and structures commonly used in the aerospace industry. Furthermore, we provide a large scale implementation of Across a diverse set ofĮvaluation metrics, we show that MeshfreeFlowNet significantly outperformsĮxisting baselines. Performance of MeshfreeFlowNet on the task of super-resolution of turbulentįlows in the Rayleigh-Benard convection problem. (ii) a set of Partial Differential Equation (PDE) constraints to be imposed,Īnd (iii) training on fixed-size inputs on arbitrarily sized spatio-temporalĭomains owing to its fully convolutional encoder. MeshfreeFlowNetĪllows for: (i) the output to be sampled at all spatio-temporal resolutions, While being computationally efficient, MeshfreeFlowNetĪccurately recovers the fine-scale quantities of interest. Download a PDF of the paper titled MeshfreeFlowNet: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework, by Chiyu Max Jiang and 8 other authors Download PDF Abstract: We propose MeshfreeFlowNet, a novel deep learning-based super-resolutionįramework to generate continuous (grid-free) spatio-temporal solutions from the
0 kommentar(er)
