Welcome to the main page of Optimal heat transfer path prediction data (OHTPD).
Heat transfer structure design
This benchmark proposes a deep learning framework for multi-component heat transfer topology optimization based on image regression (as shown in Figure 2) for the topology optimization of volume-to-point heat transfer structures of planar heat source component layout (as shown in Figure 1).
The design scheme (output) of the optimal heat transfer path can be generated in near real time for different number and position (input) of heat generation components.
Citing
Optimal heat transfer path prediction benchmark
@article{zhang2021,
Author = {Zeyu Zhang and Yu Li and Weien Zhou and Xiaoqian Chen and Wen Yao and Yong Zhao},
Title = {TONR: An exploration for a novel way combining neural network with topology optimization},
Journal = {Computer Methods in Applied Mechanics and Engineering},
volume = {386},
Year = {2021}
}
@article{luo2021,
Author = {Jiaxiang Luo and Yu Li and Wenen Zhou and Zhiqiang Gong and Zeyu Zhang and Wen Yao},
Title = {An Improved Data-Driven Topology Optimization Method Using Feature Pyramid Networks with Physical Constraints},
Journal = {CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES},
volume = {128},
number = {3},
pages = {823-848},
Year = {2021}
}