Prediction of Aerodynamic Coefficients using Artificial Neural Network in Shape Optimization of Centrally-Slotted Box Deck Bridge
|
|
|||||||||||
Bibliographic Details
| Author(s): |
Mohammed Elhassan
(Department of Bridge Engineering / State Key Laboratory of Disaster Reduction in Civil Engineering, Tongji University, Shanghai, China)
Ledong Zhu (Department of Bridge Engineering / State Key Laboratory of Disaster Reduction in Civil Engineering, Tongji University, Shanghai, China) Zhongxu Tan (Department of Bridge Engineering / State Key Laboratory of Disaster Reduction in Civil Engineering, Tongji University, Shanghai, China) Wael Alhaddad (Department of Structural Engineering, Tongji University, Shanghai, China) |
||||
|---|---|---|---|---|---|
| Medium: | conference paper | ||||
| Language(s): | English | ||||
| Conference: | IABSE Congress: Bridges and Structures: Connection, Integration and Harmonisation, Nanjing, People's Republic of China, 21-23 September 2022 | ||||
| Published in: | IABSE Congress Nanjing 2022 | ||||
|
|||||
| Page(s): | 444-451 | ||||
| Total no. of pages: | 8 | ||||
| DOI: | 10.2749/nanjing.2022.0444 | ||||
| Abstract: |
Aerodynamic shape optimization of bridge deck is a very important task in the wind-resistant design of long-span bridges and often carried out via wind tunnel tests of sectional model or CFD simulation, both of which commonly need heavy workload, thus are time-consuming and costly. In this paper, an artificial neural network (ANN) model was developed to predict aerodynamic coefficients of a central-slotted box deck of a 1600m main span cable-stayed bridge during the aerodynamic shape optimization to enhance its performance of wind-induced static stability. The ANN model was built and trained with a data set of aerodynamic coefficients obtained from limited cases of wind tunnel tests. The effect of neuron numbers in the hidden layer on prediction accuracy was discussed. The results show that the built ANN model can accurately predict the aerodynamic coefficients and significantly reduce the workload of wind tunnel tests. |
||||
| Keywords: |
aerodynamic coefficients long-span bridge Artificial Neural Network centrally-slotted box deck aerodynamic shape optimization
|
||||
| Copyright: | © 2022 International Association for Bridge and Structural Engineering (IABSE) | ||||
| License: | This creative work is copyrighted material and may not be used without explicit approval by the author and/or copyright owner. |
||||