| id |
caadria2022_172 |
| authors |
Xiao, Yahan, Hotta, Akito, Fuji, Takaaki, Kikuzato, Naoto and Hotta, Kensuke |
| year |
2022 |
| title |
Urban Scale 3 Dimensional CFD Approximation Based on Deep Learning A Quick Air Flow Prediction for Volume Study in Architecture Early Design Stage |
| source |
Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 303-312 |
| doi |
https://doi.org/10.52842/conf.caadria.2022.1.303
|
| summary |
The CFD generated by an object and its surroundings is critical during architectural design. The most common method of CFD calculation is to discretize the spatial region into small cells to form a three-dimensional grid or grid point and then apply a suitable algorithm to solve the equation iteratively until the steady state, which usually takes a significant amount of time before it converges to the exact solution of the problem. Deep learning is a subset of a Machine Learning algorithm that uses multiple layers of neural networks to perform in processing data and computations on a large amount of data. This paper presents a deep learning model CNN architecture to provide a quick and approximated 3-dimensional solution for the CFD. Our network speeds up 45 times compared to the standard CFD solver. Moreover, our network is able to predict a CFD in which the wind inlet and outlet appear at the same surface of a wind tunnel. |
| keywords |
Urban Microclimate, Machine Learning, 3D Unet, Residual Block, 3 Dimensional CFD Prediction, SDG 11 |
| series |
CAADRIA |
| email |
|
| full text |
 file.pdf (887,651 bytes) |
| references |
Content-type: text/plain
|
An, W., Liu, X., Lyu, H. & Wu, H. (2021)
 A generative deep learning framework for airfoil flow field prediction with sparse data
, Chinese Journal of Aeronautics, 35(1), 470-484. https://www.sciencedirect.com/science/article/pii/S1000936121000728
|
|
|
|
|
Bhat, B., Huval, B., Manning, C. D., Ng, A. Y. & Socher, R. (2012)
Convolutional-Recursive Deep Learning for 3D Object Classification
, Advances Neural Information Processing Systems, 25 (NIPS 2012). The Conference on Neural Information Processing Systems
|
|
|
|
|
Brunton, S. L., Callaham, J. L. & Loiseau, J. C. (2021)
On the role of nonlinear correlations in reduced-order modeling
, arXiv Physics. Retrieved September 7, 2021, from https://arxiv.org/abs/2106.02409
|
|
|
|
|
Chen, S. F., Hsiung, P. A. & Utomo, D. (2017)
Landslide Prediction with Model Switching
, Applied Sciences, 9(9). https://www.mdpi.com/2076-3417/9/9/1839
|
|
|
|
|
Davila, C. C., Mokhtar, S. & Sojika, A. (2020)
Conditional Generative Adversarial Networks for Pedestrian Wind Flow Approximation
, The 11th annual Symposium on Simulation for Architecture and Urban Design, SimAUD2020 (pp. 469-476). The Symposium on Simulation for Architecture and Urban Design (SimAUD)
|
|
|
|
|
Ding, C. & Lam, K, P. (2019)
Data-driven model for cross ventilation potential in high-density cities based on coupled CFD simulation and machine learning
, Building and Environment, 165, Article 106394. https://www.sciencedirect.com/science/article/abs/pii/S0360132319306043
|
|
|
|
|
Guo, X. & Li, W. (2016)
Convolutional Neural Networks for Steady Flow Approximation
, KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 481-490). The annual ACM SIGKDD conference
|
|
|
|
|
He, Y., Liu, X. H., Mei, Y., Schnabel, M. A., Zhang, H, L., Zhao, F. Y. & Zheng, W. (2021)
Hybrid framework for rapid evaluation of wind environment around buildings through parametric design, CFD simulation, image processing and machine learning
, Sustainable Cities and Society, 73, Article 103092. https://www.sciencedirect.com/science/article/abs/pii/S2210670721003759
|
|
|
|
|
Huang, Y., Lu, X., Sun, C., Zhang, F., Zhao, P. & Zhao, X. (2021)
Automated Simulation Framework for Urban Wind Environments Based on Aerial Point Clouds and Deep Learning
, Remote Sensing, 13(12), 2383#. https://www.mdpi.com/2072-4292/13/12/2383#
|
|
|
|
|
Jain, V., Lee, K., Li, P., Seung, H. S. & Zung, J. (2017)
Superhuman Accuracy on the SNEMI3D Connectomics Challenge
, arXiv Computer Science. Retrieved September 7, 2021, from https://arxiv.org/abs/1706.00120
|
|
|
|
|
Liu, Ping & Dou, Qi & Wang, Qiong & Heng, Pheng-Ann. (2020)
An Encoder-Decoder Neural Network With 3D Squeeze-and-Excitation and Deep Supervision for Brain Tumor Segmentation
, IEEE Access, 8, 34029-34037. https://ieeexplore.ieee.org/document/8998244
|
|
|
|
|
Lui, H. F. S. & Wolf, W. R. (2019)
Construction of reduced-order models for fluid flows using deep feedforward neural networks
, arXiv Physics. Retrieved September 7, 2021, from https://www.cambridge.org/core/journals/journal-of-fluid-mechanics/article/abs/construction-of-reducedorder-models-for-fluid-flows-using-deep-feedforward-neural-networks/ECEC52E32AEBBEA049CF26D6C79EE394
|
|
|
|
| last changed |
2022/07/22 07:34 |
|
