A microseismic effective signal detection method combining u-net network and densenet network

Abstract

The present invention provides a kind of microseismic effective signal detection method combining U-net network and DenseNet network, comprising: (1) generating original data set; (2) calibration data set; (3) constructing MSNet network; (4) adjusting Network parameters; (5) Calibrate the first arrival point after signal learning. The present invention also provides a microseismic effective signal detection system combining U-net network and DenseNet network, including: original data set generation module, data set calibration module, MSNet network construction module, network parameter adjustment module, after learning point calibration module. The present invention is based on U-net network learning and extraction of signal features of CNN network, combined with the DenseNet network, to achieve the purpose of further optimizing the learning and extraction of signal features. The invention has the characteristics of deeper feature extraction and finer signal segmentation in microseismic monitoring, and can be widely used in the field of underground state monitoring.

Description

technical field [0001] The invention relates to a geophysical technology for underground state monitoring, in particular to a microseismic monitoring technology. [0002] technical background [0003] The effective signal energy of microseismic data is weak, the signal-to-noise ratio is low, and it is difficult to effectively detect the signal. The traditional signal detection technology includes the spectrum analysis of the signal through the fast Fourier transform, and the wavelet, curvelet and shearlet transform. Time-frequency conversion and other means to achieve the purpose of removing noise and retaining effective signals. However, if the traditional method is directly applied to microseismic data, it often cannot obtain satisfactory results, which will directly affect the quality and accuracy of microseismic monitoring. [0004] The signal monitoring technology based on deep learning has gradually attracted people's attention in recent years. The main reason is that ...

AI Technical Summary

Problems solved by technology

The characteristics of the strong learning ability of the CNN network make it widely used in the learning and extraction of signal features, but due to the loss of some important features when the traditional CNN network performs feature extraction, the U-net network - a network based on The new neural network of the FCN network architecture can more effectively restore some important details that CNN lost when learning features, so that the temporal and spatial characteristics of the signal will not be lost, but due to its small number of network layers, it cannot be extracted. deeper features

Images