Microseismic source automatic localization method based on deep belief network and scanning superposition

Abstract

The invention discloses a microseismic automatic positioning method based on a deep belief network and scanning superposition, which randomly selects the data of a three-component geophone, uses the deep belief network to pick up the time of arrival of microseismic events on the data, and detects the microseismic Then, based on the obtained time of arrival and event type, the microseismic data received by all three-component geophones are used to perform scanning stacking positioning imaging. In the image, the spatial position representing the strongest superimposed energy can be considered as the real spatial position of the microseismic event, which realizes the automatic and precise positioning of the microseismic event.

Description

technical field [0001] The invention relates to the technical field of microseismic monitoring, positioning and inversion methods, and more specifically relates to a microseismic automatic positioning method based on a deep belief network and scanning superposition. Background technique [0002] In the process of resource extraction and monitoring of subsurface stress conditions, microseismic monitoring is required to quantitatively describe the rupture location of subsurface media. As an important part of microseismic monitoring, microseismic location is not only related to the description of the spatial location of the hypocenter, but also affects the correct inversion and calculation of the focal mechanism and magnitude. Therefore, the accuracy of microseismic location is very important for microseismic monitoring. [0003] The microseismic location algorithm based on Geiger theory is a simple and efficient location algorithm. The positioning algorithm based on Geiger th...

AI Technical Summary

Problems solved by technology

However, the algorithm based on Geiger theory has two disadvantages: one is that the positioning result is very sensitive to the microseismic wave arrival picking results, and the inaccurate arrival time picking will affect the positioning results

However, the positioning algorithm based on scanning and stacking also has the following disadvantages: First, the positioning algorithm based on scanning and stacking needs to divide the monitoring area into a grid, and the time of microseismic occurrence is unknown, so the process of positioning and stacking imaging is actually a four-dimensional space search for

Most of the existing positioning algorithms based on scanning and stacking manually judge the type of seismic event, which makes the positioning algorithm unable to perform automatic positioning

Images