| 利用BP神经网络模型动态预测隧道涌水量——以铜锣山隧道为例 |
| |
| 引用本文： | 刘建,刘丹.利用BP神经网络模型动态预测隧道涌水量——以铜锣山隧道为例[J].现代隧道技术,2012,49(3):62-66. |
| |
| 作者姓名： | 刘建 刘丹 |
| |
| 作者单位： | 西南交通大学地球科学与环境工程学院,成都,610031 |
| |
| 基金项目： | 铁道部科技研究开发计划重点课题 |
| |
| 摘 要： | 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。
|
| 关 键 词： | 隧道涌水井 BP神经网络 预测 响应 降雨量 |
Dynamic Predication of Tunnel Water Inflow Based on BP Neural Network:A Case Study of the Tongluoshan Tunnel |
| |
| Liu Jian
,
Liu Dan.Dynamic Predication of Tunnel Water Inflow Based on BP Neural Network:A Case Study of the Tongluoshan Tunnel[J].Modern Tunnelling Technology,2012,49(3):62-66. |
| |
| Authors: | Liu Jian Liu Dan |
| |
| Institution: | Liu Jian Liu Dan(Faculty of Geosciences and Environmental Engineering,Southwest Jiaotong University,Chengdu 610031) |
| |
| Abstract: | On the basis of analyzing the features of tunnel water inflow and precipitation response,a BP neural network model considering the 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%). |
| |
| Keywords: | Tunnel water inflow BP neural network Predication Response Precipitation |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
