Research on the Prediction of Seismic Response for Bridges Based on Neural Network
Earthquake is one kind of suddenly-happened natural disaster, and a strong earthquake can result in heavy losses to the national resources and the life and property of people. So it is very important to investigate and demonstrate the optimal prediction methodology of the seismic responses of engineering structures. In this paper, based on identification and prediction ability of ANN for nonlinear systems, an improved neural network is adopted to predict the seismic responses of the bridge structures. First of all, the improved neural network described in this paper has been trained by the imitated seismic responses of the first 4 seconds which were obtained from practical seismic waves, then the seismic responses of 4th to 12 seconds for the same bridge structure were predicted use the neural network which has been trained, and the predict responses were compared with the practical data. It can be shown from the prediction analysis that improved neural network is of very good convergence rate, and the ANN can predict the dynamic response of bridge structures well enough.
ANN Seismic response Prediction Arch Bridge
Ying Wang Zhao Renda Quan Chen Pengzhen Lu Zhou Shi
Architecture Engineering College, Shanghai Normal University, Shanghai, China, 201418 School of Civi School of Civil Engineering, Southwest Jiaotong University, Chengdu, China, 610031 School of Information Science and Technology, Southwest Jiaotong University, Chengdu, China, 610031
国际会议
The First Anniversary of Wenchuan Earthquake(纪念汶川地震一周年国际学术会议)
成都
英文
456-459
2009-05-10（万方平台首次上网日期，不代表论文的发表时间）