Tunnel rock burst early warning method based on micro-seismic information and deep convolutional neural network

Abstract

The invention provides a tunnel rock burst early warning method based on micro-seismic information and a deep convolutional neural network, and relates to the technical field of rock burst early warning. The method comprises the following steps: firstly, establishing a rockburst case with a known rockburst level and a microseismic monitoring information sample library in the inoculation process ofthe rockburst case; and then, selecting the spatial range and the time span of the early warning unit, and exporting the multi-parameter micro-seismic monitoring information in the early warning unit; constructing a large number of rockburst-microseism information sample pairs through a fine tuning early warning unit; inputting the sample pair into the established deep convolutional neural network, and obtaining an optimal rock burst early warning model through learning, testing, debugging and the like; inputting the micro-seismic information in the early warning unit of the to-be-early warned area into the rockburst early warning model to obtain the level and probability of potential rockburst in the to-be-early warned area. The method provided by the invention has high practicability and accuracy, can realize intelligent real-time early warning of potential rock burst and levels thereof, and provides scientific basis for making targeted rock burst prevention and control measures.

Description

technical field [0001] The invention relates to the technical field of rockburst early warning, in particular to a tunnel rockburst early warning method based on microseismic information and a deep convolutional neural network. Background technique [0002] Rockburst is a dynamic phenomenon in which the elastic variable energy accumulated in the underground engineering rock mass is suddenly released under excavation or other external disturbances, causing the surrounding rock to burst and eject. With the gradual extension of mines, water conservancy and hydropower, traffic tunnels (roads) and other projects to the deep, the problem of rockburst disasters has become more and more prominent. The occurrence of rockburst often brings hazards such as casualties, economic losses and delays to the project. Scientific and effective early warning of rockburst is an important way to avoid or reduce these hazards. [0003] In recent years, experts and scholars at home and abroad have...

AI Technical Summary

Problems solved by technology

These two methods can only provide early warning for the possibility of rockburst, but cannot provide early warning for the level of potential rockburst

Images