Home

Quick Links

Search

 
A Deep Learning Approach for Acoustic Emission Event DetectionNormal access

Authors: Q. Xue, Y. Wang and X. Chang
Event name: 80th EAGE Conference and Exhibition 2018
Session: Poster: Micro-seismicity and Passive A
Publication date: 11 June 2018
DOI: 10.3997/2214-4609.201801217
Organisations: EAGE
Language: English
Info: Extended abstract, PDF ( 1Mb )
Price: € 20

Summary:
Over the last decades, the volume of rock physics experiment data has increased exponentially, creating a need for efficient algorithms to reliably detect the data produce during the rock physics experiment. Today’s most elaborate methods scan through the plethora of continuous waveform records, searching for the valid signals. In this work, we leverage the recent advances in artificial intelligence and present a highly scalable convolutional neural network for valid signals detection from a single waveform. We apply our method to study the sandstone hydraulic fracturing rock physics experiment. Our approach has a higher degree of accuracy than the traditional approach, and can distinguish the data type from valid data.


Back to the article list