Fu Lin, Jiasheng Shi, Shijie Luo, Qinpei Zhao, Weixiong Rao, Lei Chen
{"title":"用于模拟物理系统的仅向上采样和基于网格的自适应 GNN","authors":"Fu Lin, Jiasheng Shi, Shijie Luo, Qinpei Zhao, Weixiong Rao, Lei Chen","doi":"arxiv-2409.04740","DOIUrl":null,"url":null,"abstract":"Traditional simulation of complex mechanical systems relies on numerical\nsolvers of Partial Differential Equations (PDEs), e.g., using the Finite\nElement Method (FEM). The FEM solvers frequently suffer from intensive\ncomputation cost and high running time. Recent graph neural network (GNN)-based\nsimulation models can improve running time meanwhile with acceptable accuracy.\nUnfortunately, they are hard to tailor GNNs for complex mechanical systems,\nincluding such disadvantages as ineffective representation and inefficient\nmessage propagation (MP). To tackle these issues, in this paper, with the\nproposed Up-sampling-only and Adaptive MP techniques, we develop a novel\nhierarchical Mesh Graph Network, namely UA-MGN, for efficient and effective\nmechanical simulation. Evaluation on two synthetic and one real datasets\ndemonstrates the superiority of the UA-MGN. For example, on the Beam dataset,\ncompared to the state-of-the-art MS-MGN, UA-MGN leads to 40.99% lower errors\nbut using only 43.48% fewer network parameters and 4.49% fewer floating point\noperations (FLOPs).","PeriodicalId":501309,"journal":{"name":"arXiv - CS - Computational Engineering, Finance, and Science","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Up-sampling-only and Adaptive Mesh-based GNN for Simulating Physical Systems\",\"authors\":\"Fu Lin, Jiasheng Shi, Shijie Luo, Qinpei Zhao, Weixiong Rao, Lei Chen\",\"doi\":\"arxiv-2409.04740\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Traditional simulation of complex mechanical systems relies on numerical\\nsolvers of Partial Differential Equations (PDEs), e.g., using the Finite\\nElement Method (FEM). The FEM solvers frequently suffer from intensive\\ncomputation cost and high running time. Recent graph neural network (GNN)-based\\nsimulation models can improve running time meanwhile with acceptable accuracy.\\nUnfortunately, they are hard to tailor GNNs for complex mechanical systems,\\nincluding such disadvantages as ineffective representation and inefficient\\nmessage propagation (MP). To tackle these issues, in this paper, with the\\nproposed Up-sampling-only and Adaptive MP techniques, we develop a novel\\nhierarchical Mesh Graph Network, namely UA-MGN, for efficient and effective\\nmechanical simulation. Evaluation on two synthetic and one real datasets\\ndemonstrates the superiority of the UA-MGN. For example, on the Beam dataset,\\ncompared to the state-of-the-art MS-MGN, UA-MGN leads to 40.99% lower errors\\nbut using only 43.48% fewer network parameters and 4.49% fewer floating point\\noperations (FLOPs).\",\"PeriodicalId\":501309,\"journal\":{\"name\":\"arXiv - CS - Computational Engineering, Finance, and Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computational Engineering, Finance, and Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.04740\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computational Engineering, Finance, and Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.04740","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Up-sampling-only and Adaptive Mesh-based GNN for Simulating Physical Systems
Traditional simulation of complex mechanical systems relies on numerical
solvers of Partial Differential Equations (PDEs), e.g., using the Finite
Element Method (FEM). The FEM solvers frequently suffer from intensive
computation cost and high running time. Recent graph neural network (GNN)-based
simulation models can improve running time meanwhile with acceptable accuracy.
Unfortunately, they are hard to tailor GNNs for complex mechanical systems,
including such disadvantages as ineffective representation and inefficient
message propagation (MP). To tackle these issues, in this paper, with the
proposed Up-sampling-only and Adaptive MP techniques, we develop a novel
hierarchical Mesh Graph Network, namely UA-MGN, for efficient and effective
mechanical simulation. Evaluation on two synthetic and one real datasets
demonstrates the superiority of the UA-MGN. For example, on the Beam dataset,
compared to the state-of-the-art MS-MGN, UA-MGN leads to 40.99% lower errors
but using only 43.48% fewer network parameters and 4.49% fewer floating point
operations (FLOPs).