期刊
INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER
卷 97, 期 -, 页码 103-109出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.icheatmasstransfer.2018.07.001
关键词
Conductive heat transfer; Deep learning; Topology optimization; SIMP
资金
- National Natural Science Foundation of China [51605371, 51635010]
- Fundamental Research Funds for the Central Universities [xjj2016013]
- China Postdoctoral Science Foundation [2015 M580853]
- Postdoctoral Science Foundation of Shaanxi Province [2016BSHYDZZ21]
A deep learning approach combining with the traditional solid isotropic material with penalization (SIMP) method is presented in this paper to accelerate the topology optimization of the conductive heat transfer. This deep learning predictor is structured based on the deep fully convolutional neural network. The validity and accuracy of this deep learning approach is investigated based on the typical 'Volume-Point' heat conduction problems. The time consumption of the optimization process will be reduced significantly by introducing the deep learning approach.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据