Toward Generalizable Graph Learning for 3D Engineering AI Explainable Workflows for CAE Mode Shape Classification and CFD Field Prediction
- 提供方法
- 本サイト上にてダウンロード・閲覧可
- 形態
- 価格
- 一般価格(税込)：￥1,100 会員価格(税込)：￥880
- 文献番号
- 20265249
- 文献・情報種別
- 学術講演会予稿集（春）
No.58-26
- 掲載ページ
- 1-8(Total 8 p)
- 発行年月
- 2026年 5月
- 出版社
- (公社)自動車技術会
- 言語
- 英語
- イベント
- 2026年春季大会
書誌事項
| 著者 | 1) Tong Duy Son, 2) Kohta Sugiura, 3) Marc Brughmans, 4) Andrey Hense, 5) Zhihao Liu, 6) Amirthalakshmi Veeraraghavan, 7) Ajinkya Bhave, 8) Jay Masters, 9) Paolo di Carlo, 10) Theo Geluk |
|---|---|
| 著者（英） | 1) Tong Duy Son, 2) Kohta Sugiura, 3) Marc Brughmans, 4) Andrey Hense, 5) Zhihao Liu, 6) Amirthalakshmi Veeraraghavan, 7) Ajinkya Bhave, 8) Jay Masters, 9) Paolo di Carlo, 10) Theo Geluk |
| 勤務先 | 1) Siemens Digital Industries Software, 2) Siemens Digital Industries Software, 3) Siemens Digital Industries Software, 4) Siemens Digital Industries Software, 5) Siemens Digital Industries Software, 6) Siemens Digital Industries Software, 7) Siemens Digital Industries Software, 8) Siemens Digital Industries Software, 9) Siemens Digital Industries Software, 10) Siemens Digital Industries Software |
| 勤務先（英） | 1) Siemens Digital Industries Software, 2) Siemens Digital Industries Software, 3) Siemens Digital Industries Software, 4) Siemens Digital Industries Software, 5) Siemens Digital Industries Software, 6) Siemens Digital Industries Software, 7) Siemens Digital Industries Software, 8) Siemens Digital Industries Software, 9) Siemens Digital Industries Software, 10) Siemens Digital Industries Software |
| 抄録（英） | PhysicsAI delivers fast physics predictions enabling engineering teams to generate design variations rapidly. PhysicsAI learns physics behavior using Graph Neural Networks (GNNs) trained on mesh geometries and CAD models data. Engineers can explore various design variations, optimize parameters, and accelerate innovation. We present two applications: (1) External aerodynamic drag prediction using CFD simulation data, achieving high accuracy while reducing computation time from hours to minutes; (2) Vibration mode shape recognition and classification for NVH optimization, demonstrating expert-level accuracy on complex automotive structures. Validation from comprehensive automotive datasets will be presented. 翻訳 |
