Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Asahi, Yuichi; Hatayama, Sora*; Shimokawabe, Takashi*; Onodera, Naoyuki; Hasegawa, Yuta; Idomura, Yasuhiro
Proceedings of 2021 IEEE International Conference on Cluster Computing (IEEE Cluster 2021) (Internet), p.686 - 691, 2021/10
Times Cited Count:2 Percentile:72.38(Computer Science, Hardware & Architecture)We develop a convolutional neural network model to predict the multi-resolution steady flow. Based on the state-of-the-art image-to-image translation model pix2pixHD, our model can predict the high resolution flow field from the set of patched signed distance functions. By patching the high resolution data, the memory requirements in our model is suppressed compared to pix2pixHD.
Asahi, Yuichi; Hatayama, Sora*; Shimokawabe, Takashi*; Onodera, Naoyuki; Hasegawa, Yuta; Idomura, Yasuhiro
Keisan Kogaku Koenkai Rombunshu (CD-ROM), 26, 4 Pages, 2021/05
We develop a convolutional neural network model to predict the multi-resolution steady flow. Based on the state-of-the-art image-to-image translation model Pix2PixHD, our model can predict the high resolution flow field from the signed distance function. By patching the high resolution data, the memory requirements in our model is suppressed compared to Pix2PixHD.
Hatayama, Sora*; Shimokawabe, Takashi*; Onodera, Naoyuki
no journal, ,
Computational fluid dynamics (CFD) is widely used as a fluid analysis technique. However, these have a problem that the calculation cost is very expensive and the execution time for reaching a steady-state is long. To solve this problem, we use convolutional neural networks (CNN), which is one of the deep learning methods, to predict CFD results. In this research, we provide the method and implementation of steady flow prediction using CNN with boundary exchange to predict the CFD results in a large area.
Hatayama, Sora*; Shimokawabe, Takashi*; Onodera, Naoyuki
no journal, ,
We propose a prediction method for large-scale simulation results by dividing the input geometry into multiple parts and applying a single small neural network to each part in parallel. The constructed model predicts a two-dimensional velocity field using a signed distance function as input. In addition, we divide a large area into multiple regions and the prediction is iteratively performed for each region until convergence. Finally, we confirmed that the velocity fields of multiple regions are reproduced by using a boundary exchange method.