Towards a priori mesh quality estimation using Machine Learning Techniques
TypeCommunications avec actes
Since the quality of FE meshes strongly affects the quality of the FE simulations, it is known to be very important to generate good quality meshes. Thus, it is crucial to be able to estimate very early what can be the expected quality of a mesh without having to play in loop with several control parameters. This paper addresses the way the quality of FE meshes can be estimated a priori, i.e. before meshing the CAD models. In this way, designers can generate good quality meshes at first glance. Our approach is based on the use of a set of rules which allow estimating what will be the mesh quality according to the shape characteristics of the CAD model to be meshed. Those rules are built using Machine Learning Techniques, notably classification ones, which analyse a huge amount of configurations for which the shape characteristics of both the CAD models and meshes are known. For an unknown configuration, i.e. for a CAD model not yet meshed, the learnt rules help understanding what can be the expected classes of quality, or in another way what are the control parameters to be set up to reach a given mesh quality. The proposed approach has been implemented and tested on academic and industrial examples.
Fichier(s) constituant cette publication
Cette publication figure dans le(s) laboratoire(s) suivant(s)
Visualiser des documents liés par titre, auteur, créateur et sujet.
LOU, Ruding; GIANNINI, Franca; FALCIDIENO, Bianca; PERNOT, Jean-Philippe; VERON, Philippe; MIKCHEVITCH, Alexei; MARC, Raphael (World Scientific Publishing Company, 2010)Behaviour analysis loop is largely performed on virtual product model before its physical manufacturing. The last avoids high expenses in terms of money and time spent on intermediate manufacturing. It is gainful from the ...
PERNOT, Jean-Philippe; MORARU, George; VERON, Philippe (Taylor & Francis, 2007)The Reverse Engineering process consists of a succession of operations that aim at creating a digital representation of a physical model. The reconstructed geometric model is often a triangle mesh built from a point cloud ...
Merging enriched Finite Element triangle meshes for fast prototyping of alternate solutions in the context of industrial maintenance LOU, Ruding; PERNOT, Jean-Philippe; MIKCHEVITCH, Alexei; VERON, Philippe (Elsevier, 2010)A new approach to the merging of Finite Element (FE) triangle meshes is proposed. Not only it takes into account the geometric aspects, but it also considers the way the semantic information possibly associated to the ...
LI, Zongcheng; GIANNINI, Franca; PERNOT, Jean-Philippe; VERON, Philippe; FALCIDIENO, Bianca (Springer, 2016)Today, digital data such as 2D images, 3D meshes and 3D point clouds are widely used to design virtual environments (VE). Most of the time, only one type of those multimodal data is used to describe and specify the shapes ...
Parts internal structure definition using lattice patterns optimization for mass reduction in additive manufacturing CHOUGRANI, Laurent; VERON, Philippe; PERNOT, Jean-Philippe; ABED, Stéphane (2016)With the rise of additive manufacturing, complex internal structure optimization is now a relevant topic. Additive manufacturing allows designers and engineers to go further in their modeling, designing and optimization ...