以垫邻高速铜锣山隧道为例,在分析隧道涌水和降雨响应特征的基础上,建立了综合考虑降雨脉冲、降雨累积效应和地下水系统整合作用的隧道涌水量预测的BP神经网络模型。计算结果表明,该模型对训练样本的拟合程度较好(平均绝对百分比误差为13.27%)且具有较高的预测精度(平均绝对百分比误差为15.05%)。该模型的建立和成功应用对丰富隧道涌水量的预测方法和动态指导隧道防排水管理具有重要意义。
On the basis of analyzing the features of tunnel water inflow and precipitation response, a BP neural network model considering tile pulse effect, cumulative effect of the precipitation, and integration effect of groundwater system was built using the Tongluoshan tunnel as an example. The simulation results indicate that this model satisfactorily fits the training sample with a mean absolute percent error of 13.27% and has a relative accurate predication accuracy (mean absolute percent error of 15.05%).