このアイテムのアクセス数: 97
このアイテムのファイル:
ファイル | 記述 | サイズ | フォーマット | |
---|---|---|---|---|
s10489-023-04565-w.pdf | 1.19 MB | Adobe PDF | 見る/開く |
タイトル: | Deep deterministic policy gradient and graph attention network for geometry optimization of latticed shells |
著者: | Kupwiwat, Chi-tathon Hayashi, Kazuki ![]() ![]() ![]() Ohsaki, Makoto ![]() ![]() ![]() |
著者名の別形: | 林, 和希 大﨑, 純 |
キーワード: | Bézier surface Deep deterministic policy gradient Geometry optimization Graph attention network Reinforcement learning |
発行日: | Sep-2023 |
出版者: | Springer Nature |
誌名: | Applied Intelligence |
巻: | 53 |
号: | 17 |
開始ページ: | 19809 |
終了ページ: | 19826 |
抄録: | This paper proposes a combined approach of deep deterministic policy gradient (DDPG) and graph attention network (GAT) to the geometry optimization of latticed shells with surface shapes defined by a Bézier control net. The optimization problem is formulated to minimize the strain energy of the latticed structures with heights of the Bézier control points as design variables. The information of the latticed shells, including nodal configurations, element properties and internal forces, and the Bézier control net, consisting of control points and control net, are represented as graphs using node feature matrices, adjacency matrices, and weighted adjacency matrices. A specifically designed DDPG agent utilizes GAT and matrix manipulations to observe the state of the structure through the graphs, and decides which and how Bézier control points to move. The agent is trained to excel in the task through a reward signal computed from changes in the strain energy in each optimization step. As shown in numerical examples, the trained agent can effectively optimize structures of different sizes, control nets, configurations, and initial geometries from those used during the training. The performance of the trained agent is competitive compared to particle swarm optimization and simulated annealing despite using a lower computational cost. |
著作権等: | This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/10.1007/s10489-023-04565-w The full-text file will be made open to the public on 17 March 2024 in accordance with publisher's 'Terms and Conditions for Self-Archiving'. This is not the published version. Please cite only the published version. この論文は出版社版でありません。引用の際には出版社版をご確認ご利用ください。 |
URI: | http://hdl.handle.net/2433/285165 |
DOI(出版社版): | 10.1007/s10489-023-04565-w |
出現コレクション: | 学術雑誌掲載論文等 |

このリポジトリに保管されているアイテムはすべて著作権により保護されています。