Tunnel advanced geological prediction method and computer readable storage medium

Abstract

The invention discloses a tunnel advanced geological prediction method and a computer readable storage medium. The tunnel advanced geological prediction method comprises the steps: arranging a three-dimensional observation system on a tunnel face to realize three-dimensional seismic wave excitation and reception, and processing acquired data based on a deep learning algorithm to obtain the position of an abnormal body, wherein the step of processing the data based on the deep learning algorithm comprises the following sub-steps: rejecting bad track data from the acquired data based on an AlexNet convolutional neural network model algorithm, and filtering; identifying the first arrival wave based on a UNet convolutional neural network model algorithm, and estimating a direct wave speed; carrying out linear dynamic correction on the original data without the bad track data; carrying out equal travel time profile superposition on the data after linear dynamic correction; and carrying outreflection layer pickup on the superposed data. According to the tunnel advanced geological prediction method and the computer readable storage medium, the detection efficiency and the detection accuracy of the abnormal body can be improved.

Description

technical field [0001] The invention relates to the technical field of tunnel engineering, in particular to a method for advanced geological prediction of tunnels and a computer-readable storage medium. Background technique [0002] Tunnel advance prediction technology is a technical method to detect the geological environment and geological structure in front of the tunnel face before and during the construction of the tunnel. Among them, the advanced tunnel prediction technology based on seismic detection detects the surrounding rock information in front of the tunnel face according to the elastic wave field of the tunnel surrounding rock, which has a large detection depth and high detection accuracy, and is one of the main advanced prediction technologies. According to the different detection methods, the existing tunnel advance prediction technology based on seismic detection can be roughly divided into two-dimensional detection technology and quasi-three-dimensional det...

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the present invention, the inventors found that the advance prediction technology based on seismic detection often has the problems of misdetection or missed detection, low detection efficiency, long data processing period, and strong multi-solution of interpretation results.

[0004] Specifically, the inventors found that although the observation systems of two-dimensional detection technologies such as HSP and TSP technology have a certain spatial distribution, due to the limitation of the tunnel space, the seismic wave excitation and reception angle is extremely small, and the imaging quality is poor, making it difficult to obtain accurate geological data. Abnormal body information

Compared with two-dimensional observation technology, quasi-three-dimensional detection technologies such as TRT, TST, and TSWD have improved the wave velocity analysis accuracy and the imaging accuracy of unfavorable geological bodies. Due to the influence of the subsurface, it is difficult to arrange the shot point and the receiver point in all directions, and it is easy to lose part of the phase data, so it is difficult to realize the real three-dimensional detection; secondly, the abnormal body reflection signal received on the tunnel wall is easily affected by the tunnel surrounding rock surface wave, The signal-to-noise ratio is low due to the interference of strong non-reflection information such as converted waves and horizontal strata parallel to the tunnel axis; at the same time, the existing seismic data for advance prediction of tunnels is mostly processed manually, which has a long period and high cost, and the processing results are subject to external influences. Factors and technical personnel's professional knowledge have a great influence, and imaging has strong multi-solutions, and the tunnel advance prediction method based on manual methods cannot directly compare the tunnel advance prediction seismic data of different tunnel construction locations

Images