Folding Reticulated Shell Structure Wind Pressure Coefficient Prediction Research based on RBF Neural Network

DOI

10.2991/icismme-15.2015.265How to use a DOI?

Keywords

neural network; folding reticulated shells; wind pressure coefficient; prediction.

Abstract

In order to make up for the wind tunnel test equipment of folding reticulated shells restrictions which lead to wind pressure data measured on the surface of structure has a low density. This passage based on the basic principle of RBF neural network, using the programming software MATLAB to predict the wind pressure coefficient under three kinds of condition on the folding reticulated shell when the wind speed 20 m/s and wind direction angle is 0 °, 45 ° and 90 °, respectively. The forecast results are compared with wind tunnel tests, and it was shown a good agreement with the test studies. Results show that using the RBF neural network method to predict the wind pressure on the surface of a structure is feasible. Based on the limited wind tunnel test , neural network method is applied to forecast the unknown point of wind pressure coefficient, improve and rich the wind tunnel test data, and provide an effective method for folding reticulated shell structure wind load forecast and analysis.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Si Gao
AU  - Yanru Wu
AU  - Zheng Huang
PY  - 2015/07
DA  - 2015/07
TI  - Folding Reticulated Shell Structure Wind Pressure Coefficient Prediction Research based on RBF Neural Network
BT  - Proceedings of the First International Conference on Information Sciences, Machinery, Materials and Energy
PB  - Atlantis Press
SP  - 1238
EP  - 1242
SN  - 1951-6851
UR  - https://doi.org/10.2991/icismme-15.2015.265
DO  - 10.2991/icismme-15.2015.265
ID  - Gao2015/07
ER  -