Automatic microseismic signal arrival time picking method based on depth belief neural network

Abstract

The invention discloses an automatic microseismic signal arrival time picking method based on a depth belief neural network. According to the method, each microseismic record is sampled according unified fixed dimensions, the signal arrival time of partial records is manually picked and is taken as the label information of the corresponding records; the information-picked records and labels of the information-picked records are taken as a total data set during network construction, including a training data set, a verification data set and a test data set; through inputting the data to the depth belief neural network for training and testing, the depth belief neural network is constructed; the actually-acquired to-be-processed data is inputted to the trained network model to carry out microseismic signal identification and automatic arrival time picking, and the network output is an arrival time point of the microseismic data.

Description

technical field [0001] The invention belongs to the technical field of geophysical detection, and relates to a method for automatically picking up microseismic signals when they arrive, based on a deep belief neural network. Background technique [0002] Microseisms are earthquakes whose magnitude is greater than one and less than three. Such small magnitude earthquakes are difficult for people to detect and can only be monitored with instruments. But even a small underground vibration will generate corresponding excitation to the underground medium, and such excitation may change the mechanical state of the underground medium. In the field of mine safety monitoring, microseisms are a precursor to mine dynamic disasters, and real-time monitoring of microseisms can effectively predict and prevent dynamic disasters. In addition, in the exploration and development of unconventional oil and gas such as shale gas and coalbed methane, the fracture monitoring technology based on m...

AI Technical Summary

Problems solved by technology

[0006] The present invention aims to solve the problem that the traditional short-long time window energy ratio method needs certain human intervention during the picking process when picking up the microseismic signal, which leads to the problem that the performance of the picking method is not robust enough.

Images