摘要
在可视化测井中,深度对于判断油管缺陷位置至关重要,而现有的测深系统具有一定的深度误差。实际工程中,可通过识别油管接箍再参照油管数据表来准确标定仪器的深度。本文基于运动视频图像处理,提出了一种油管接箍自动识别方法。利用VideoLog可视化测井系统采集井下油管视频图像,通过对视频图像进行形态学处理、特征参数提取、接箍判决等过程来准确识别接箍。实验结果表明,同一个接箍在视频中会多次出现,也会被多次识别到,同一接箍平均识别率为86.9%,接箍计数的正确率为100%。方法已成功用于可视化测井视频解释处理中,取得了较好的工程应用效果。
In visual logging,depth is very important to judge the position of tubing defects,but the existing depth measurement systems have certain depth measurement error.In practical engineering,the depth can be accurately calibrated by identifying tubing couplings and referring to tubing data.An automatic identification method of tubing couplings is proposed based on processing of moving video image.The video image of downhole tubing is collected by VideoLog visualization logging system,and the couplings are identified accurately by morphological processing and feature parameter extraction of the video image.The experimental results show that the same coupling will appear and be recognized many times in the video.The average recognition rate of the same coupling is 86.9%,and the correct rate of coupling counting is 100%.The method has been successfully used in visual logging video interpretation and processing,and good engineering application effect has achieved.
作者
阚绍佑
巨亚锋
梁万银
姚强
吴银川
KAN Shaoyou;JU Yafeng;LIANG Wanyin;YAO Qiang;WU Yinchuan(Key Laboratory of Shaanxi Province for Gas-Oil Logging Technology,Xi'an Shiyou University,Xi'an,Shaanxi 710065,China;Oil and Gas Technology Research Institute,PetroChina Changqing Oilfield Company,Xi'an,Shaanxi 710018,China;Petroleum Engineering Technology Research Institute,SINOPEC Jianghan Oilfield,Wuhan,Hubei 430000,China)
出处
《西安石油大学学报（自然科学版）》
CAS
北大核心
2020年第6期115-118,123,共5页
Journal of Xi’an Shiyou University（Natural Science Edition）
基金
国家科技重大专项(2016ZX05060)
陕西省教育厅重点实验室项目“缺陷套管中电阻率测井响应特征研究”(15JS097)
陕西省教育厅重点实验室项目“过套管电阻率测井仪器刻度系统研究”(11JS051)
陕西省光电传感测井重点实验室开放基金(09JS042)。
关键词
接箍识别
视频图像处理
可视化测井
井深测量
测井解释
coupling identification
video image processing
visual logging
measurement of hole depth
logging interpretation
