基于MEC-BP神经网络的臧湾东河特大桥施工挠度监测研究

Study on Construction Deflection Monitoring of Zangwan Donghe Bridge Based on MEC-BP Neural Network

为提高特大桥施工挠度预测准确度,以臧湾东河特大桥为研究对象,采用MEC-BP神经网络模型对大桥施工挠度进行预测,并将预测值与数值模拟值和实测值进行对比。结果表明:现场实测值与MEC-BP模型预测值相差较小,MEC-BP模型在训练样本上表现出很好的准确性;MEC-BP模型的性能明显优于传统BP模型,在挠度预测方面具有更高的效率和精度,平均误差都小于5 mm。借助MEC算法实现对传统BP模型参数的全局优化,能够提高桥梁结构力学行为预测能力,为连续梁桥施工过程中的结构安全问题提供了有效解决方案。

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 MECBP 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.