Vol. - No.
|
Vol.8 - No.4
|
Date
|
Dec., 2019 |
Title
|
Optimization Calculations and Machine Learning Aimedat Reduction of Wind Forces Acting on Tall Buildingsand Mitigation of Wind Environment |
Author
|
Hideyuki Tanaka1+, Yasutomo Matsuoka2, Takuma Kawakami2, Yasuhiko Azegami1,Masashi Yamamoto1, Kazuo Ohtake1, and Takayuki Sone1 |
Institutions
|
1Takenaka Corporation, Inzai, Chiba, Japan2Takenaka Corporation, Shinsuna, Koto-ku, Tokyo, Japan |
Abstract
|
We performed calculations combining optimization technologies and Computational Fluid Dynamics (CFD) aimed at reducing wind forces and mitigating wind environments (local strong winds) around buildings. However, the Reynolds Averaged Navier-stokes Simulation (RANS), which seems somewhat inaccurate, needs to be used to create a realistic CFD optimization tool. Therefore, in this study we explored the possibilities of optimizing calculations using RANS. We were able to demonstrate that building configurations advantageous to wind forces could be predicted even with RANS. We also demonstrated that building layouts was more effective than building configurations in mitigating local strong winds around tall buildings. Additionally, we used the Convolutional Neural Network (CNN) as an airflow prediction method alternative to CFD in order to increase the speed of optimization calculations, and validated its prediction accuracy. |
Keyword
|
Optimization calculation, CFD, CNN, Wind force, Wind environment |
PP.
|
PP.291~302 |
Paper File
|
View |