• 全国中文核心期刊
  • 中国科技核心期刊
  • 美国工程索引(EI)收录期刊
  • Scopus数据库收录期刊
王天宁, 王利宁, 薛亚东, 张越, 张东明, 黄宏伟. 山岭隧道收敛变形无线感知及预测方法[J]. 岩土工程学报, 2020, 42(S1): 224-228. DOI: 10.11779/CJGE2020S1044
引用本文: 王天宁, 王利宁, 薛亚东, 张越, 张东明, 黄宏伟. 山岭隧道收敛变形无线感知及预测方法[J]. 岩土工程学报, 2020, 42(S1): 224-228. DOI: 10.11779/CJGE2020S1044
WANG Tian-ning, WANG Li-ning, XUE Ya-dong, ZHANG Yue, ZHANG Dong-ming, HUANG Hong-wei. Wireless sensing and prediction method for convergence deformation of mountain tunnels[J]. Chinese Journal of Geotechnical Engineering, 2020, 42(S1): 224-228. DOI: 10.11779/CJGE2020S1044
Citation: WANG Tian-ning, WANG Li-ning, XUE Ya-dong, ZHANG Yue, ZHANG Dong-ming, HUANG Hong-wei. Wireless sensing and prediction method for convergence deformation of mountain tunnels[J]. Chinese Journal of Geotechnical Engineering, 2020, 42(S1): 224-228. DOI: 10.11779/CJGE2020S1044

山岭隧道收敛变形无线感知及预测方法

Wireless sensing and prediction method for convergence deformation of mountain tunnels

  • 摘要: 隧道施工过程中围岩的变形规律是施工安全的关键,目前钻爆法施工隧道断面的变形检测多基于全站仪展开,检测数据点数据量难以精细分析变形规律。借助无线传感网络(wireless sensors network),可以实现隧道重点部位的长时间连续监测。在营盘山隧道布设了基于微机电系统(micro electro mechanical system)传感器的WSN监测设备,并构建了基于广域网(Web)的隧道施工安全风险动态管控系统平台,实现隧道关键位置变形的连续监测,所得变形时间序列,通过长短时记忆(long short-term memory)网络,更准确地预测隧道断面收敛变形值。实际工程应用结果证明了该方法的有效性。

     

    Abstract: Mastering the deformation laws of the surrounding rock during tunnelling is the key to the safety of construction. At present, the deformation detection of the tunnel section in the drilling and blasting method is mostly based on the total stations. Nevertheless, the amount of monitoring data applied in the detection was difficult to complete the fine analysis of convergence deformation. The wireless wensors network (WSN) is employed to realize the long-term continuous monitoring of key regions of the rock tunnel. Meanwhile, by setting up WSN monitoring equipment based on micro-electrical mechanical system sensors, a dynamic risk management and control system platform during tunnel construction based on Web is developed in Yingpanshan tunnel, Yunnan, China. Thus, the continuous monitoring of the deformation at the key region of the tunnel is realized. In addition, in accordance with the time series of deformation, the convergence deformation value of tunnel section is then predicted more accurately by the long short-term memory network. In summary, the performance of practical engineering application proveds the effectiveness of the proposed method.

     

/

返回文章
返回