ISpliter: an intelligent and automatic surface mesh generator using neural networks and splitting lines
Abstract In this paper, we present a novel surface mesh generation approach that splits B-rep geometry models into isotropic triangular meshes based on neural networks and splitting lines. In the first stage, a recursive method is designed to generate plentiful data to train the neural network model...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-06-01
|
| Series: | Advances in Aerodynamics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s42774-023-00150-4 |
| _version_ | 1827933191497842688 |
|---|---|
| author | Zengsheng Liu Shizhao Chen Xiang Gao Xiang Zhang Chunye Gong Chuanfu Xu Jie Liu |
| author_facet | Zengsheng Liu Shizhao Chen Xiang Gao Xiang Zhang Chunye Gong Chuanfu Xu Jie Liu |
| author_sort | Zengsheng Liu |
| collection | DOAJ |
| description | Abstract In this paper, we present a novel surface mesh generation approach that splits B-rep geometry models into isotropic triangular meshes based on neural networks and splitting lines. In the first stage, a recursive method is designed to generate plentiful data to train the neural network model offline. In the second stage, the implemented mesh generator, ISpliter, maps each surface patch into the parameter plane, and then the trained neural network model is applied to select the optimal splitting line to divide the patch into subdomains continuously until they are all triangles. In the third stage, ISpliter remaps the 2D mesh back to the physical space and further optimizes it. Several typical cases are evaluated to compare the mesh quality generated by ISpliter and two baselines, Gmsh and NNW-GridStar. The results show that ISpliter can generate isotropic triangular meshes with high average quality, and the generated meshes are comparable to those generated by the other two software under the same configuration. |
| first_indexed | 2024-03-13T07:21:16Z |
| format | Article |
| id | doaj.art-7cfed8d04532410a8c75cd5b7fb94c99 |
| institution | Directory Open Access Journal |
| issn | 2524-6992 |
| language | English |
| last_indexed | 2024-03-13T07:21:16Z |
| publishDate | 2023-06-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Advances in Aerodynamics |
| spelling | doaj.art-7cfed8d04532410a8c75cd5b7fb94c992023-06-04T11:39:35ZengSpringerOpenAdvances in Aerodynamics2524-69922023-06-015112510.1186/s42774-023-00150-4ISpliter: an intelligent and automatic surface mesh generator using neural networks and splitting linesZengsheng Liu0Shizhao Chen1Xiang Gao2Xiang Zhang3Chunye Gong4Chuanfu Xu5Jie Liu6State Key Laboratory of High Performance Computing, National University of Defense TechnologyState Key Laboratory of High Performance Computing, National University of Defense TechnologyState Key Laboratory of High Performance Computing, National University of Defense TechnologyState Key Laboratory of High Performance Computing, National University of Defense TechnologyCollege of Computer, National University of Defense TechnologyState Key Laboratory of High Performance Computing, National University of Defense TechnologyCollege of Computer, National University of Defense TechnologyAbstract In this paper, we present a novel surface mesh generation approach that splits B-rep geometry models into isotropic triangular meshes based on neural networks and splitting lines. In the first stage, a recursive method is designed to generate plentiful data to train the neural network model offline. In the second stage, the implemented mesh generator, ISpliter, maps each surface patch into the parameter plane, and then the trained neural network model is applied to select the optimal splitting line to divide the patch into subdomains continuously until they are all triangles. In the third stage, ISpliter remaps the 2D mesh back to the physical space and further optimizes it. Several typical cases are evaluated to compare the mesh quality generated by ISpliter and two baselines, Gmsh and NNW-GridStar. The results show that ISpliter can generate isotropic triangular meshes with high average quality, and the generated meshes are comparable to those generated by the other two software under the same configuration.https://doi.org/10.1186/s42774-023-00150-4Surface mesh generationArtificial neural networkSplitting lineTriangular elementFeature extraction |
| spellingShingle | Zengsheng Liu Shizhao Chen Xiang Gao Xiang Zhang Chunye Gong Chuanfu Xu Jie Liu ISpliter: an intelligent and automatic surface mesh generator using neural networks and splitting lines Advances in Aerodynamics Surface mesh generation Artificial neural network Splitting line Triangular element Feature extraction |
| title | ISpliter: an intelligent and automatic surface mesh generator using neural networks and splitting lines |
| title_full | ISpliter: an intelligent and automatic surface mesh generator using neural networks and splitting lines |
| title_fullStr | ISpliter: an intelligent and automatic surface mesh generator using neural networks and splitting lines |
| title_full_unstemmed | ISpliter: an intelligent and automatic surface mesh generator using neural networks and splitting lines |
| title_short | ISpliter: an intelligent and automatic surface mesh generator using neural networks and splitting lines |
| title_sort | ispliter an intelligent and automatic surface mesh generator using neural networks and splitting lines |
| topic | Surface mesh generation Artificial neural network Splitting line Triangular element Feature extraction |
| url | https://doi.org/10.1186/s42774-023-00150-4 |
| work_keys_str_mv | AT zengshengliu ispliteranintelligentandautomaticsurfacemeshgeneratorusingneuralnetworksandsplittinglines AT shizhaochen ispliteranintelligentandautomaticsurfacemeshgeneratorusingneuralnetworksandsplittinglines AT xianggao ispliteranintelligentandautomaticsurfacemeshgeneratorusingneuralnetworksandsplittinglines AT xiangzhang ispliteranintelligentandautomaticsurfacemeshgeneratorusingneuralnetworksandsplittinglines AT chunyegong ispliteranintelligentandautomaticsurfacemeshgeneratorusingneuralnetworksandsplittinglines AT chuanfuxu ispliteranintelligentandautomaticsurfacemeshgeneratorusingneuralnetworksandsplittinglines AT jieliu ispliteranintelligentandautomaticsurfacemeshgeneratorusingneuralnetworksandsplittinglines |