Characterization of fractures and vugs by electrical imaging based on image region segmentation and convolutional neural network
ZHANG Hao1,2, WANG Liang2,3, SIMA Liqiang1,2, FAN Ling4, GUO Yuhao1,2, GUO Yifan1,2
1. School of Geoscience and Technology, Southwest Petroleum University, Chengdu, Sichuan 610500, China; 2. State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Chengdu, Sichuan 610500, China; 3. College of Energy, Chengdu University of Technology, Chengdu, Sichuan 610059, China; 4. Central Sichuan Oil and Gas Field, PetroChina Southwest Oil and Gas Field Company, Suining, Sichuan 629000, China
Abstract：The processing and interpretation of electrical imaging are confronted by problems including the difficulty in characterizing fractures and vugs and the dependence on manual operation. Manual ope-ration is not only inefficient but also introduces human errors which are difficult to eliminate. Therefore, this paper proposes a electrical imaging approach based on image region segmentation and the convolutional neural network to automatically identify fractures and vugs. It relies on electrical imaging data and combines with the Otsu algorithm and the average segmentation threshold to separate the fractures and vugs from the stratum background. Also, the independent fracture and vug individuals in connected domains are extracted with the connected domain pixel labeling method. Then, the automatic recognition of fractures and vugs is realized by building and training the improved LeNet-5 network model with the training sample sets based on the image features of various geological structures. Finally, according to the conventional logging curves, the recognition results of the trained model are employed to classify the images, and quantitative evaluation parameters, including effective surface porosity, are calculated accurately on the basis of identified and extracted fractures and vugs. The applicability and rationality of the proposed method are verified by the test model and actual data. At the same time, compared with the manual processing method of electrical imaging, this method can improve the accuracy (by avoiding human errors) and processing speed (15s/m), and the prediction accuracy of the trai-ning model for the test set reaches 97. 8%, providing an algorithm for the fine logging interpretation of fractured-vuggy reservoirs.
王璐,杨胜来,彭先,等.缝洞型碳酸盐岩气藏多类型储集层孔隙结构特征及储渗能力——以四川盆地高石梯-磨溪地区灯四段为例[J].吉林大学学报(地球科学版),2019,49(4):947-958.WANG Lu,YANG Shenglai,PENG Xian,et al.Pore structure characteristics and storage-seepage capability of multi-type reservoirs in fracture-cavity carbonate gas reservoirs:A case study of Deng-4 member in Gaoshiti-Moxi area,Sichuan basin[J].Journal of Jilin University(Earth Science Edition),2019,49(4):947-958.
[2]
刘丹,潘保芝,房春慧,等.利用成像测井评价储层孔隙空间的二维非均质性[J].世界地质,2014,33(3):640-646.LIU Dan,PAN Baozhi,FANG Chunhui,et al.Evaluate of 2D heterogeneity of reservoir's pore space based on imaging logging[J].World Geology,2014,33(3):640-646.
[3]
高树生,刘华勋,任东,等.缝洞型碳酸盐岩储层产能方程及其影响因素分析[J].天然气工业,2015,35(9):48-54.GAO Shusheng,LIU Huaxun,REN Dong,et al.Deliverability equation of fracture-cave carbonate reservoirs and its influential factors[J].Natural Gas Industry,2015,35(9):48-54.
[4]
杨海军,李世银,邓兴梁,等.深层缝洞型碳酸盐岩凝析气藏勘探开发关键技术——以塔里木盆地塔中Ⅰ号气田为例[J].天然气工业,2020,40(2):83-89.YANG Haijun,LI Shiyin,DENG Xingliang,et al.Key technologies for exploration and development of deep fractured vuggy carbonate condensate gas reservoir:a case study of Tazhong I gas field in Tarim Basin[J].Natural Gas Industry,2020,40(2):83-89.
[5]
卫平生,张虎权,王宏斌,等.塔中地区缝洞型碳酸盐岩储层的地球物理预测方法[J].天然气工业,2009,29(3):38-40.WEI Pingsheng,ZHANG Huquan,WANG Hongbin,et al.Geophysical prediction method for fractured vuggy carbonate reservoirs in Tazhong area[J].Natural Gas Industry,2009,29(3):38-40.
[6]
吴一全,樊军,吴诗婳.改进的二维Otsu法阈值分割快速迭代算法[J].电子测量与仪器学报,2011,25(3):24-31.WU Yiquan,FAN Jun,WU Shiya.Fast iterative algorithm for image segmentation based on an improved two-dimensional Otsu thresholding[J].Journal of Electronic Measurement and Instrument,2011,25(3):24-31.
[7]
柯式镇,许淑霞.井壁电成像测井资料定量评价方法研究[J].天然气工业,2006,26(9):62-64.KE Shizhen,XU Shuxia.A method study on quantitatively evaluating sidewall imaging well logging data[J].Natural Gas Industry,2006,26(9):62-64.
[8]
闫建平,梁强,李尊芝,等.连通域标识法在FMI图像溶洞信息定量拾取中的应用[J].地球物理学报,2016,59(12):4759-4770.YAN Jianping,LIANG Qiang,LI Zunzhi,et al.A connected domain identification method and its application in quantitatively pickup information of caves using electric imaging logging[J].Chinese Journal of Geophysics,2016,59(12):4759-4770.
[9]
李曦宁,沈金松,李振苓,等.用多尺度形态学方法实现成像测井电导率图像的缝洞参数表征[J].中国石油大学学报(自然科学版),2017,41(1):69-77.LI Xining,SHEN Jinsong,LI Zhenling,et al.Characterization of fracture and cavity parameters in imaging logging conductivity image using multi-scale morphological method[J].Journal of China University of Petroleum (Natural Science Edition),2017,41(1):69-77.
[10]
李振苓,沈金松,李曦宁,等.用形态学滤波从电导率图像中提取缝洞孔隙度谱[J].吉林大学学报(地球科学版),2017,47(4):1295-1307.LI Zhenling,SHEN Jinsong,LI Xining,et al.Estimating porosity spectrum of fracture and karst cave from conductivity image by morphological filtering[J].Journal of Jilin University (Earth Science Edition),2017,47(4):1295-1307.
[11]
Liu G,Reda F A,Shih K J,et al.Image inpainting for irregular holes using partial convolutions[C].European Conference on Computer Vision,Springer,Cham,2018,89-105.
[12]
张国标,李信,陆伟.基于深度卷积神经网络的生物医学混合图像检测[J].现代情报,2020,40(7):74-81.ZHANG Guobiao,LI Xin,LU Wei.Biomedical hybrid image detection based on deep convolution neural network[J].Journal of Modern Information,2020,40(7):74-81.
[13]
Zhang C,Yue X,Wang R,et al.Study on traffic sign recognition by optimized Lenet-5 algorithm[J].International Journal of Pattern Recognition and Artificial Intelligence,2020,34(1):2055003.
[14]
Kim G Y,Narantsetseg B.Fractures and breakouts analysis from borehole image logs:Preliminary results for interpretation of stress history and in situ stress state[J].Marine Georesources & Geotechnology,2015,33(6):579-585.
[15]
Voet E,Ben L,Rombaut B,et al.Fracture characteristics of Lower Carboniferous carbonates in northern Belgium based on FMI log analyses[J].Netherlands Journal of Geosciences,2020,99(8):1-15.
[16]
孙建孟,赵建鹏,赖富强,等.电测井图像空白条带填充方法[J].测井技术,2011,35(6):532-537.SUN Jianmeng,ZHAO Jianpeng,LAI Fuqiang,et al.Methods to fill in the gaps between pads of electrical logging images[J].Well Logging Technology,2011,35(6):532-537.
[17]
何旭,李忠伟,刘昕,等.应用卷积神经网络识别测井相[J].石油地球物理勘探,2019,54(5):1159-1165.HE Xu,LI Zhongwei,LIU Xin,et al.Log facies re-cognition based on convolutional neural network[J].Oil Geophysical Prospecting,2019,54(5):1159-1165.
[18]
王维波,徐西龙,盛立,等.卷积神经网络微地震事件检测[J].石油地球物理勘探,2020,55(5):939-949.WANG Weibo,XU Xilong,SHENG Li,et al.Detection of microseismic events based on convolutional neural network[J].Oil Geophysical Prospecting,2020,55(5):939-949.
[19]
Li X N,Shen J S,Yang W Y,et al.Automatic fracture-vug identification and extraction from electric i-maging logging data based on path morphology[J].Petroleum Science,2018,16(1):58-76.
[20]
张晓峰,潘保芝.二维小波变换在成像测井识别裂缝中的应用研究[J].石油地球物理勘探,2012,47(1):173-176.ZHANG Xiaofeng,PAN Baozhi.Application of 2D wavelet transform in fracture identification by imaging logging[J].Oil Geophysical Prospecting,2012,47(1):173-176.
[21]
魏伯阳,潘保芝,殷秋丽,等.基于条件生成对抗网络的成像测井图像裂缝计算机识别[J].石油物探,2020,59(2):295-302.WEI Boyang,PAN Baozhi,YIN Qiuli,et al.Identification of image logging data based on conditional gener-ation adversarial network[J].Geophysical Prospecting for Petroleum,2020,59(2):295-302.
[22]
Zhang H J,Zhang Z N,Lin D M,et al.A novel image denoising algorithm combined PCNN with morphology[C].Intelligent Signal Processing and Communication Systems,2007,208-211.
[23]
Bauer J F,Krumbholz M,Meier S,et al.Predictability of properties of a fractured geothermal reservoir:the opportunities and limitations of an outcrop analogue study[J].Geothermal Energy,2017,5(1),24.http://doi.org/10.1186/s40517-017-0081-0.
[24]
肖小玲,靳秀菊,张翔,等.基于常规测井与电成像测井多信息融合的裂缝识别[J].石油地球物理勘探,2015,50(3):542-547.XIAO Xiaoling,JIN Xiuju,ZHANG Xiang,et al.Fracture identification based on information fusion of conventional logging and electrical imaging logging[J].Oil Geophysical Prospecting,2015,50(3):542-547.
[25]
Aghli G,Moussavi-Harami R,Ruhangiz M,et al.Re-servoir heterogeneity and fracture parameter determination using electrical image logs and petrophysical data(a case study,carbonate Asmari Formation,Zagros Basin,SW Iran)[J].Petroleum Science,2020,17(1):51-69.
[26]
Ebadati N.Fractures effect in reservoir quality of Ilam and Sarvak formations in Hengam oilfield using imaging logs[J].Journal of the Geological Society of India,2018,92(4):491-497.
