首页|Studies from Karl-Franzens-University in the Area of Machine Learning Described (Learning Mesh Motion Techniques With Application To Fluid-structure Interaction )
Studies from Karl-Franzens-University in the Area of Machine Learning Described (Learning Mesh Motion Techniques With Application To Fluid-structure Interaction )
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 Daily News - Research findings on Machine Learning are discussed in a new report. According to news reporting from Graz, Austria, b y NewsRx journalists, research stated, “Mesh degeneration is a bottleneck for fl uid-structure interaction (FSI) simulations and for shapeoptimization via the me thod of mappings. In both cases, an appropriate mesh motion techniqueis required .” The news correspondents obtained a quote from the research from Karl-Franzens-Un iversity, “The choice is typically based on heuristics, e.g., the solution opera tors of partialdifferential equations (PDE), such as the Laplace or biharmonic e quation. Especially the latter,which shows good numerical performance for large displacements, is expensive. Moreover,from a continuous perspective, choosing th e mesh motion technique is to a certain extentarbitrary and has no influence on the physically relevant quantities. Therefore, we considerapproaches inspired by machine learning. We present a hybrid PDE-NN approach, where theneural network (NN) serves as parameterization of a coefficient in a second order nonlinearPDE. We ensure existence of solutions for the nonlinear PDE by the choice of the neu ralnetwork architecture. Moreover, we present an approach where a neural network corrects theharmonic extension such that the boundary displacement is not chang ed. In order to avoidtechnical difficulties in coupling finite element and machi ne learning software, we work witha splitting of the monolithic FSI system into three smaller subsystems. This allows to solve themesh motion equation in a sepa rate step. We assess the quality of the learned mesh motiontechnique by applying it to a FSI benchmark problem.”
NETL
NSTL
