An Efficient Neural-Network-Based Microseismic Monitoring Platform for Hydraulic Fracture on an Edge Computing Architecture

被引:16
作者
Zhang, Xiaopu [1 ,2 ]
Lin, Jun [1 ,2 ]
Chen, Zubin [1 ,2 ]
Sun, Feng [1 ,2 ,3 ]
Zhu, Xi [3 ]
Fang, Gengfa [3 ]
机构
[1] Jilin Univ, Coll Instrumentat & Elect Engn, Changchun 130061, Jilin, Peoples R China
[2] Jilin Univ, Minist Educ, Key Lab Geophys Explorat Equipment, Changchun 130061, Jilin, Peoples R China
[3] Univ Technol Sydney, Sch Elect & Data Engn, Sydney, NSW 2007, Australia
关键词
microseismic monitoring; event detection; edge computing; neural networks; probabilistic inference; PICKING; NOISE;
D O I
10.3390/s18061828
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Microseismic monitoring is one of the most critical technologies for hydraulic fracturing in oil and gas production. To detect events in an accurate and efficient way, there are two major challenges. One challenge is how to achieve high accuracy due to a poor signal-to-noise ratio (SNR). The other one is concerned with real-time data transmission. Taking these challenges into consideration, an edge-computing-based platform, namely Edge-to-Center LearnReduce, is presented in this work. The platform consists of a data center with many edge components. At the data center, a neural network model combined with convolutional neural network (CNN) and long short-term memory (LSTM) is designed and this model is trained by using previously obtained data. Once the model is fully trained, it is sent to edge components for events detection and data reduction. At each edge component, a probabilistic inference is added to the neural network model to improve its accuracy. Finally, the reduced data is delivered to the data center. Based on experiment results, a high detection accuracy (over 96%) with less transmitted data (about 90%) was achieved by using the proposed approach on a microseismic monitoring system. These results show that the platform can simultaneously improve the accuracy and efficiency of microseismic monitoring.
引用
收藏
页数:19
相关论文
共 41 条
  • [1] A review and appraisal of arrival-time picking methods for downhole microseismic data
    Akram, Jubran
    Eaton, David W.
    [J]. GEOPHYSICS, 2016, 81 (02) : KS71 - KS91
  • [2] Alexander T., 2011, Schlumberger, V23, P40
  • [3] [Anonymous], HYDRAULICALLY FRACTU
  • [4] [Anonymous], 2016, EC UNCONVENTIONAL SH
  • [5] [Anonymous], 1997, Neural Computation
  • [6] Baig Adam, 2010, Leading Edge, V29, P320, DOI 10.1190/1.3353729
  • [7] Calvez J.L., 2016, Oilfield Review, V28, P16
  • [8] RETRACTED: Automatic microseismic event picking via unsupervised machine learning (Publication with Expression of Concern. See vol. 221, pg. 2051, 2020) (Retracted article. See vol. 222, pg. 1896, 2020)
    Chen, Yangkang
    [J]. GEOPHYSICAL JOURNAL INTERNATIONAL, 2018, 212 (01) : 88 - 102
  • [9] A comparative performance analysis of different activation functions in LSTM networks for classification
    Farzad, Amir
    Mashayekhi, Hoda
    Hassanpour, Hamid
    [J]. NEURAL COMPUTING & APPLICATIONS, 2019, 31 (07) : 2507 - 2521
  • [10] High-speed download of seismographs using private cloud technology and a proportional integral derivative controller
    Gao, Ning
    Zheng, Fan
    Wang, Xin
    Jiang, Xiaoxue
    Lin, Jun
    [J]. INSTRUMENTATION SCIENCE & TECHNOLOGY, 2016, 44 (01) : 12 - 22