基于BP神经网络方法的岩溶隧道突涌水风险预测  

Risk Prediction of Water Inrush of Karst Tunnels Based on BP Neural Network

作　　者：杨卓[1] 马超[1] 

机构地区：[1]解放军理工大学爆炸冲击防灾减灾国家重点实验室,江苏南京210007

出　　处：《隧道建设》2016年第11期1337-1342,共6页Tunnel Construction

基　　金：国家重点基础研究发展计划(973计划)项目(2013CB036005)

摘　　要：为了准确预测岩溶隧道突涌水风险等级,以降低隧道施工过程中突涌水事故的风险,在参考相关文献的基础上,统计研究及综合分析岩溶隧道水文地质条件,选取不良地质、地层岩性、地下水位、地形地貌、岩层倾角和围岩裂隙6个主要因素作为岩溶隧道突涌水风险评价指标。在不同水文地质条件下,影响因素的权重有较大差异,为避开影响因素权重分析,运用BP神经网络方法对岩溶隧道突涌水风险进行评估。在对突涌水风险评估基础上,结合超前地质预报,优化隧道施工开挖支护方案。在工程应用中,运用BP神经网络方法,对某隧道进行突涌水风险评估,结果与实际施工情况较一致,并结合超前预报提出合理的支护方案,避免了隧道突涌水事故的发生,以期为岩溶隧道突涌水风险预测提供借鉴。The hydrogeological conditions of karst tunnel is statistically studied and comprehensively analyzed; and the main factors for the risk evaluation of water inrush of karst tunnel,i. e. geology,ground lithology,groundwater level,topography,strata inclination and surrounding rock fracture,are selected,so as to evaluate the water inrush risk of karst tunnel precisely and further reduce the water inrush risk. Due to the great difference among influencing factors under different hydrogeological conditions,the risk prediction of water inrush of karst tunnels based on BP neural network is adopted. The application results of above-mentioned risk prediction method coincide with the actual situation. The above-mentioned method is rational and can be used for reference.

关 键 词：岩溶隧道 突涌水 BP神经网络 风险预测 超前预报 

分 类 号：U45[建筑科学—桥梁与隧道工程]