检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:汤清源 房伟 刘统亮 杜宇成 盖志亮 袁翔 梁建龙 Tang Qingyuan;Fang Wei;Liu Tongliang;Du Yucheng;Gai Zhiliang;Yuan Xiang;Liang Jianlong(Jianghan Machinery Research Institute Limited Company of CNPC;CCDC Downhole Service Company;Hainan Branch of CNOOC(China)Co.,Ltd.)
机构地区:[1]中石油江汉机械研究所有限公司 [2]中国石油集团川庆钻探工程有限公司井下作业公司 [3]中海石油(中国)有限公司海南分公司
出 处:《石油机械》2024年第5期132-137,共6页China Petroleum Machinery
基 金:中国石油工程技术研究院有限公司产业基金项目“连续管作业分析软件”(CPETCY202308);中石油江汉机械研究所有限公司科研项目“井下可视化定量分析系统研究”(2022JJYSJ004)。
摘 要:国内外油气田开采过程中,针对页岩油、页岩气体积压裂,需要对压裂体系效果和产能进行辅助评价,利用井下电视获取井下静态图像或运动图像,可以直接视觉呈现井内真实状况,利用软件定量分析炮眼个数及尺寸,在压裂后产层评价应用领域具有其他测井手段所不具备的独特优势。针对连续管井下电视作业及压裂后需计算进砂量、进行产能评价的问题,研发了连续管井下电视作业地面配套设备,包含钻磨、洗井和井下电视测井3种重要组成工艺及其井下工具配套方案。采用Python+OpenCV识别技术进行相机标定、图像增强、偏心矫正等图像预处理模块开发,同时利用YOLOv5+Deepsort神经网络形成了特征目标检测及跟踪技术,并结合炮眼冲蚀理论及进砂量分析,使用C#开发了一套含基础组件、炮眼定量分析工程、报告输出为一体的压裂进砂评价系统,实现可视化、定量分析算法。研究结果可为页岩油气产能评价提供一定技术支撑。Volume fracturing is often conducted for shale oil and shale gas in the process of oil and gas field development both in China and other countries,and auxiliary evaluation needs to be performed on the fracturing system effect and deliverability.The use of downhole television to obtain downhole static or kinetic images can directly visually present the real situation in the well,and the use of software to quantitatively analyze the number and size of perforations has unique advantages in the post-fracturing pay formation evaluation that other logging methods do not have.In order to address the issues such as coiled tubing downhole television operation,calculation of sand injection volume and deliverability evaluation after fracturing,a set of coiled tubing downhole television operation ground supporting equipment was developed,including 3 important technologies of milling,flushing and downhole television logging as well as downhole tool supporting scheme.The python+OpenCV recognition technology was used to develop image preprocessing modules such as camera calibration,image enhancement and eccentricity correction.Meanwhile,the YOLOv5+Deepsort neural network was used to form feature object detection and tracking technology;finally,combined with perforation erosion theory and sand injection volume analysis,the C#was used to develop a set of fracturing sand injection evaluation system including basic components,perforation quantitative analysis project and report output.The research results provide certain technical support for the evaluation of shale oil and gas deliverability.
分 类 号:TE377[石油与天然气工程—油气田开发工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.49