Abstract:Conventional detection methods for microseismic events are almost based on calculating the features of signals.The accuracy of events detection depends on the parameters of algorithms,so it is greatly affected by the changes in the features of signals and signal-to-noise ratio.This paper proposes a method for microseismic event detection based on a convolutional neural network(CNN).To train and test the CNN,a sample set is constructed on the microseismic data monitored by multiple stations in an oil well that was hydraulically fractured.The data consist of effective event signals and ineffective background noises and their classifications.Then the CNN is trained and tested by the sample data set,and an optimal CNN model is obtained with best accuracy of event detection.To test the performance of the CNN model,synthesized microseismic signals with different signal-to-noise ratios,and actual microseismic signals from several oil and gas wells are fed into the CNN model.The processing results demonstrate that the CNN model can automatically and effectively detect microseismic events.It has good abilities for noise suppressing and generalization.
段银鹿,李倩,姚韦萍.水力压裂微地震裂缝监测技术及其应用[J].断块油气田,2013,20(5):644-648.DUAN Yinlu,LI Qian,YAO Weiping.Microseismic fracture monitoring technology of hydraulic fracturing and its application[J].Fault-Block Oil & Gas Field,2013,20(5):644-648.
[2]
赵博雄,王忠仁,刘瑞,等.国内外微地震监测技术综述[J].地球物理学进展,2014,29(4):1882-1888.ZHAO Boxiong,WANG Zhongren,LIU Rui,et al.Review of microseismic monitoring technology research[J].Progress in Geophysics,2014,29(4):1882-1888.
[3]
储仿东,焦亚军,杨立峰,等.利用微地震识别水力压裂井旁天然裂缝[J].石油地球物理勘探,2018,53(增刊2):143-147.CHU Fangdong,JIAO Yajun,YANG Lifeng,et al.Natural fracture identification at hydraulic fracturing wells with microseismic[J].Oil Geophysical Prospecting,2018,53(S2):143-147.
唐杰,方兵,蓝阳,等.压裂诱发的微地震震源机制及信号传播特性[J].石油地球物理勘探,2015,50(4):643-649.TANG Jie,FANG Bing,LAN Yang,et al.Focal mechanism of micro-seismic induced by hydrofracture and its signal propagation characteristics[J].Oil Geophysical Prospecting,2015,50(4):643-649.
[6]
宋维琪,冯超.微地震有效事件自动识别与定位方法[J].石油地球物理勘探,2013,48(2):283-288.SONG Weiqi,FENG Chao.Automatic identification and localization of microseismic effective events[J].Oil Geophysical Prospecting,2013,48(2):283-288.
[7]
刘翰林,吴庆举.地震自动识别及震相自动拾取方法研究进展[J].地球物理学进展,2017,32(3):1000-1007.LIU Hanlin,WU Qingju.Developments of research on earthquake detection and seismic phases picking[J]. Progress in Geophysics,2017,32(3):1000-1007.
[8]
Wang H,Li M,Shang X F.Current developments on micro-seismic data processing[J].Journal of Natural Gas Science and Engineering,2016,32(5):521-537.
[9]
张唤兰,朱光明,王云宏.基于时窗能量比和AIC的两步法微震初至自动拾取[J].物探与化探,2013,37(2):269-273.ZHANG Huanlan,ZHU Guangming,WANG Yunhong.Automatic microseismic event detection and picking method[J].Geophysical and Geochemical Exploration,2013,37(2):269-273.
[10]
Shang X Y,Li X B,Esteban A M,et al.An improved P-phase arrival picking method S/L-K-A with an application to the Yongshaba mine in China[J].Pure and Applied Geophysics,2018,175(6):2121-2139.
[11]
曹俊海,顾汉明,尚新民.基于局部相关谱约束的多道匹配追踪算法识别微地震信号[J].石油地球物理勘探,2017,52(4):704-714.CAO Junhai,GU Hanming,SHANG Xinmin.Microseismic signal identification with multichannel ma-tching pursuit based on local coherence spectrum constraint[J].Oil Geophysical Prospecting,2017,52(4):704-714.
[12]
陈润航,黄汉明,柴慧敏.地震和爆破事件源波形信号的卷积神经网络分类研究[J].地球物理学进展,2018,33(4):1331-1338.CHEN Runhang,HUANG Hanming,CHAI Huimin.Study on the discrimination of seismic waveform signals between earthquake and explosion events by convolutional neural network[J].Progress in Geophy-sics,2018,33(4):1331-1338.
[13]
赵明,陈石,Yuen D.基于深度学习卷积神经网络的地震波形自动分类与识别[J].地球物理学报,2019,62(1):380-388.ZHAO Ming,CHEN Shi,Yuen D.Waveform classification and seismic recognition by convolution neural network[J].Chinese Journal of Geophysics,2019,62(1):380-388.
[14]
Bi L,Xie W,Zhao J J.Automatic recognition and classification of multi-channel microseismic waveform based on DCNN and SVM[J].Computers & Geosciences,2019,123(2):111-120.
宋维琪,杨晓东.基于射线追踪的微地震多波场正演模拟[J].地球物理学进展,2012,27(4):1501-1508.SONG Weiqi,YANG Xiaodong.The multi-wave field forward simulation of microseismic based on ray tra-cing[J].Progress in Geophysics,2012,27(4):1501-1508.
[21]
于子叶,储日升,盛敏汉.深度神经网络拾取地震P和S波到时[J].地球物理学报,2018,61(12):4873-4886.YU Ziye,CHU Risheng,SHENG Minhan.Pick onset time of P and S phase by deep neural network[J].Chinese Journal of Geophysics,2018,61(12):4873-4886.