<p>The rockburst of deep buried tunnel rock mass seriously threatens the safety of underground engineering, but the traditional monitoring and analysis method has insufficient ability to analyze small sample nonlinear microseismic data. To effectively reduce the risk of rockburst disasters, a microseismic multi-parameter monitoring method based on the PSO-GRNN model is proposed. Meanwhile, a field sound and light alarm system is independently developed to provide real-time feedback on the prediction results. In this method, the characteristic parameters of microseismic signals are collected in real time, and the dynamic comprehensive risk index <i>W</i><sub><i>Z</i></sub>(<i>t</i>) (the quantitative value of rockburst risk based on the correlation degree of time series multi-parameters) is constructed by combining the grey correlation method to form a multi-parameter early warning criterion, which effectively solves the problems of nonlinear microseismic data and small sample size in deep buried tunnels. The method and system are applied in the field of DJ tunnel in western China, and the accuracy of early warning is 92.8%. A complete closed loop of data collection-intelligent analysis-multi-level early warning- emergency response is constructed, providing valuable references for on-site rockburst early warning.</p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Real-time rockburst warning using microseismic multi-feature parameters based on the PSO-GRNN model

  • Wen Xuan Dong,
  • Qing He Zhang,
  • Xiao Rui Wang,
  • He Peng Dong,
  • Chuan Bing Wang,
  • Sheng tao Wang

摘要

The rockburst of deep buried tunnel rock mass seriously threatens the safety of underground engineering, but the traditional monitoring and analysis method has insufficient ability to analyze small sample nonlinear microseismic data. To effectively reduce the risk of rockburst disasters, a microseismic multi-parameter monitoring method based on the PSO-GRNN model is proposed. Meanwhile, a field sound and light alarm system is independently developed to provide real-time feedback on the prediction results. In this method, the characteristic parameters of microseismic signals are collected in real time, and the dynamic comprehensive risk index WZ(t) (the quantitative value of rockburst risk based on the correlation degree of time series multi-parameters) is constructed by combining the grey correlation method to form a multi-parameter early warning criterion, which effectively solves the problems of nonlinear microseismic data and small sample size in deep buried tunnels. The method and system are applied in the field of DJ tunnel in western China, and the accuracy of early warning is 92.8%. A complete closed loop of data collection-intelligent analysis-multi-level early warning- emergency response is constructed, providing valuable references for on-site rockburst early warning.