TY - GEN
T1 - A Novel Gan-Based Method For Building Surface Wind Pressure Prediction
AU - Sun, Lin
AU - Cao, Shuqi
AU - Wang, Likai
AU - Ji, Guohua
N1 - Funding Information:
This study is funded by National Natural Science Foundation of China (52178017) and China Postdoctoral Science Foundation (2021M701664).
Publisher Copyright:
© 2022 SCS.
PY - 2022
Y1 - 2022
N2 - The wind pressure on the surface of buildings can be critical, especially for high-rise buildings. To overcome the limitations in applying time-consuming CFD simulations to early design stage, we introduce a novel approach for generating real-time surface wind pressure in high-rise buildings through Deep Learning (DL). The DL model is trained on datasets of hundreds of buildings geometries generated by Grasshopper plugin EvoMass, and their corresponding surface wind pressure is simulated by RhinoCFD. Moreover, regarding the current performance prediction using DL, we have noted that the common labeling map and DL model may hinder the efficiency of training. Thus, we proposed a new labeling approach and a modified DL model to assess the accuracy of the prediction. To demonstrate the validity of the approach, the experiments of simulation predictions were conducted, and the results shows that the presented method can greatly enhance the accuracy.
AB - The wind pressure on the surface of buildings can be critical, especially for high-rise buildings. To overcome the limitations in applying time-consuming CFD simulations to early design stage, we introduce a novel approach for generating real-time surface wind pressure in high-rise buildings through Deep Learning (DL). The DL model is trained on datasets of hundreds of buildings geometries generated by Grasshopper plugin EvoMass, and their corresponding surface wind pressure is simulated by RhinoCFD. Moreover, regarding the current performance prediction using DL, we have noted that the common labeling map and DL model may hinder the efficiency of training. Thus, we proposed a new labeling approach and a modified DL model to assess the accuracy of the prediction. To demonstrate the validity of the approach, the experiments of simulation predictions were conducted, and the results shows that the presented method can greatly enhance the accuracy.
KW - Deep Learning
KW - Surface Wind Pressure Simulation
KW - Surrogate Model
UR - http://www.scopus.com/inward/record.url?scp=85138024613&partnerID=8YFLogxK
U2 - 10.23919/ANNSIM55834.2022.9859495
DO - 10.23919/ANNSIM55834.2022.9859495
M3 - Conference Proceeding
AN - SCOPUS:85138024613
T3 - Proceedings of the 2022 Annual Modeling and Simulation Conference, ANNSIM 2022
SP - 512
EP - 522
BT - Proceedings of the 2022 Annual Modeling and Simulation Conference, ANNSIM 2022
A2 - Martin, Cristina Ruiz
A2 - Emami, Niloufar
A2 - Blas, Maria Julia
A2 - Rezaee, Roya
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 Annual Modeling and Simulation Conference, ANNSIM 2022
Y2 - 18 July 2022 through 20 July 2022
ER -