計算力学講演会講演論文集
Online ISSN : 2424-2799
セッションID: OS-2213
会議情報

グラフニューラルネットワークを用いた輻射伝熱解析のサロゲートモデリング
*酒井 佑典奥田 洋司
著者情報
会議録・要旨集 認証あり

詳細
抄録

This study aimed to develop an effective approach for fast simulation of material processing by surrogate modeling with graph neural network. Specifically, radiation problems which imitate heating process of thermoplastic materials were addressed. The training data for surrogate model was generated through calculations using finite element method as steady-state heat transfer analysis. The simulation model consisted of single material and six heaters. And the material was exposed to radiative heat from the heaters under different heating conditions with different material shapes. A structure of neural network model suitable for these problems was proposed, incorporating surficial graphs and edges to express pairs for radiative heat transport. The model predicted view factor on each edge using the information of relative coordinates between relevant nodes. It demonstrated good results in predicting radiative flux for various material shapes and conditions. Although there is still room for improving accuracy, fast prediction of radiation was achieved successfully.

著者関連情報
© 2024 一般社団法人 日本機械学会
前の記事 次の記事
feedback
Top