基于神经网络的桥梁施工控制研究

Study on Construction Control of Bridge Based on Neural Network

将神经网络方法结合Matlab用于处理大跨度预应力混凝土连续梁挢施工控制中的箱粱线形控制的误差预测和调整。由于受诸多因素影响,标高的实测值与理论计算值有一定的差异,只有通过前期预测和后期调整相结合,才能保证成桥实际状态同设计要求一致。神经网络可利用实测样本的自学习达到到此目的。应用实例表明神经网络法的预测精度高,这对同类桥梁的施工控制具有一定指导意义。

Combined with Matlab, the neural network is used to deal with the error prediction and adjustment of box beam alignment control in the construction control of long-span pre-stressed concrete continuous beam bridge. Owing to many factors, the measured value of elevation is some different from the theoretic calculation value. Only through the combination of early prediction and later adjustment, it can ensure the actual status of bridge identical with the design requirements. The neural network can achieve this objective by the self learning mode of measured sample. The use of practical cases shows that the prediction precision of neural network is high, which has some guiding significance for the construction control of the similar bridges.