Study on Construction Deflection Monitoring of Zangwan Donghe Bridge Based on MEC-BP Neural Network
In order to improve the accuracy of construction deflection prediction of the large bridge,the Zangwan Donghe Bridge is taken as the research object.The construction deflection of the bridge is predicted by the MEC-BP neural network model.And the predicted values are compared with the numerical simulation ones and the measured ones.The results show that the difference between the measured values and the predicted values of the MEC-BP model is smaller.The MEC-BP model shows good accuracy on the training samples;The performance of the MEC-BP model is significantly better than the traditional BP one and has higher efficiency and accuracy in the deflection prediction with the average errors of less than 5 mm.MEC algorithm helps to realize the whole optimization of the parameters of traditional BP model,which can improve the ability of predicting the mechanical behavior of bridge structure,and provide an effective solution for the structural safety problems during the construction of continuous girder bridges.
国家科技期刊平台
NSTL
万方数据
