智能油井管理系统设计与应用

doi:10.3969/j.issn.1672-9803.2019.02.017

摘要/Abstract

摘要：

针对当前油井管理效率低、成本高,管理人员不能实时、准确了解现场生产状况的问题,提出一种基于可视化智能监控、神经网络专家系统的自动分析智能油井管理系统。与传统油井管理系统相比,智能油井管理系统可实现现场生产数据实时传输,数据实时性、真实性提高;通过智能摄像装置对油井生产现场实时监控,油井生产安全性提高;现场生产出现故障时系统通过神经网络专家系统自动识别,智能开关井并通报现场人员及时处理,生产效率提高。智能油井管理系统已安装120余井次,现场应用表明,该系统可全面感知油田生产动态,实现油田的可视化智能监控,预测油气田变化趋势,持续优化油气田管理。

关键词: 油井管理, 可视化, 智能监控, 智能专家系统

Abstract:

In view of the inefficiency and high cost of current oil well management,administrators are not able to accurately know the on-site production status in real time,an automatic analysis intelligent oil well management system based on visual intelligent monitoring and neural network expert system is proposed. Compared with traditional oil well management system,intelligent oil well management system can realize real-time transmission of on-site production data,improving the real-time characteristic and authenticity of data. Real-time monitoring of oil well production site through intelligent camera device improves oil well production safety. When the on-site production fails,the system automatically recognizes it through the neural network expert system,intelligently opens and shuts in the well and informs the on-site personnel to dispose in time,improving the production efficiency. The system comprehensively perceives oilfield production performance and realizes visual intelligent monitoring of oilfields. The forecast of the trend of oil and gas fields continuously optimizes oil and gas field management. The intelligent oil well management system has been installed in more than 120 wells,the field application effect is good.

Key words: oil well management, visualization, intelligent monitoring, intelligent expert system

中图分类号:

TE132.1

陈勇. 智能油井管理系统设计与应用[J]. 录井工程, 2019, 30(2): 86-91.

Yong Chen. Design and application of intelligent oil well management system[J]. Mud Logging Engineering, 2019, 30(2): 86-91.

图/表 8

图1

图2

图3

图4

图5

表1

图6

表2

参考文献 14

[1]	王凯. 基于产生式规则系统的抽油泵故障诊断[J]. 石油勘探与开发,2010,37(1):116-120.
	WANG Kai.Fault diagnosis of rod-pumping unit based on production rules system[J]. Petroleum Exploration and Development,2010,37(1):116-120.
[2]	徐芃,徐士进,尹宏伟. 有杆抽油系统故障诊断的人工神经网络方法[J]. 石油学报,2006,27(2):107-110.
	XU Peng,XU Shijin,YIN Hongwei.Application of BP neural network and self-organizing competitive neural network to fault diagnosis of suck rod pumping system[J]. Acta Petrolei Sinica,2006,27(2):107-110.
[3]	贾爱林,郭建林. 智能化油气田建设关键技术与认识[J]. 石油勘探与开发,2012,39(1):118-122.
	JIA Ailin,GUO Jianlin.Key technologies and understandings on the construction of smart fields[J]. Petroleum Exploration and Development,2012,39(1):118-122.
[4]	贾德利,刘合,斐晓含,等. 游梁式抽油机井井下泵功图测试方法[J]. 石油勘探与开发,2015,42(1):111-116.
	JIA Deli,LIU He,FEI Xiaohan,et al.Test approach of downhole pump diagram for beam bumping wells[J]. Petroleum Exploration and Development,2015,42(1):111-116.
[5]	李敬元,陈国春,李子丰,等. 滤波技术在有杆泵抽油系统诊断中的应用[J]. 石油学报,2010,31(1):144-147.
	LI Jingyuan,CHEN Guochun,LI Zifeng,et al.Application of filter technique to diagnosis of sucker-rod pumping system[J]. Acta Petrolei Sinica,2010,31(1):144-147.
[6]	杜保东,李明山. 人工神经网络识别抽油机井示功图的研究[J]. 油气井测试,1998,7(1):27-29.
	DU Baodong,LI Mingshan.Research on identifying the diagram of rod pumping well by artificial neural network[J]. Well Testing,1998,7(1):27-29.
[7]	王文珍. 基于无线传感网络油田智能监控系统的设计[J]. 自动化仪表 2013,34(2):92-94.
	WANG Wenzhen.Design of the WSN-based intelligent monitoring system for oilfield[J]. Process Automation Instrumentation,2013,34(2):92-94.
[8]	王玉成,查建中,焦建新,等. 抽油机井集成化智能诊断系统的研究[J]. 石油学报,1994,15(4):125-132.
	WANG Yucheng,ZHA Jianzhong,JIAO Jianxin,et al.Integrated intelligent diagnosis system for sucker rod pumped wells[J]. Acta Petrolei Sinica,1994,15(4):125-132.
[9]	桂振文,吴侹,彭欣. 一种融合多传感器信息的移动图像识别方法[J]. 自动化学报,2015,41(8):1394-1404.
	GUI Zhenwen,WU Ting,PENG Xin.A novel recognition approach for mobile image fusing inertial sensors[J]. Acta Automatica Sinica,2015,41(8):1394-1404.
[10]	管皓,薛向阳,安志勇. 深度学习在视频目标跟踪中的应用进展与展望[J]. 自动化学报,2016,42(6):834-847.
	GUAN Hao,XUE Xiangyang,AN Zhiyong.Advances on application of deep learning for video object tracking[J]. Acta Automatica Sinica,2016,42(6):834-847.
[11]	朱煜,赵江坤,王逸宁,等. 基于深度学习的人体行为识别算法综述[J]. 自动化学报,2016,42(6):848-857.
	ZHU Yu,ZHAO Jiangkun,WANG Yining,et al.A review of human action recognition based on deep learning[J]. Acta Automatica Sinica,2016,42(6):848-857.
[12]	何信华,胡绍华,陈勇,等. 基于单幅二维图像的摄像机标定方法研究[J]. 计算机科学与应用,2013(3):23-29.
	HE Xinhua,HU Shaohua,CHEN Yong,et al.A camera calibration method study based on single two-dimensional image[J]. Computer Science and Application,2013(3):23-29.
[13]	胡绍华,陈勇,何信华. 实时目标跟踪研究[J]. 计算机科学与应用,2014(4):158-168.
	HU Shaohua,CHEN Yong,HE Xinhua.Study on real-time target tracking[J]. Computer Science and Application,2014(4):158-168.
[14]	何信华,陈勇,赵雷,等. 多遥测图像数据流的自动拼接与自动优选技术[J]. 遥测遥控,2017,38(3):50-58.
	HE Xinhua,CHEN Yong,ZHAO Lei,et al.Automatic splicing & optimization method on multiple telemetry image data streams[J]. Journal of Telemetry,Tracking and Command,2017,38(3):50-58.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

特征参数	释义	特征参数	释义
C₁	实测/理论示功图面积比	C₁₁	最大载荷到最大位移点损失示功图面积与固定阀关闭点到最大位移点损失示功图面积比
C₂	固定阀、游动阀开闭线载荷差与理论柱塞载荷差之比	C₁₂	最大位移点到最小载荷点损失示功图面积与最大位移到游动阀开启点损失示功图面积比
C₃	固定阀开闭载荷、泵上冲程平均载荷差与理论柱塞载荷差之比	C₁₃	抽吸压力损失比
C₄	游动阀开闭载荷、泵下冲程平均载荷差与理论柱塞载荷差之比	C₁₄	抽吸压力损失比
C₅	最大载荷、固定阀开闭载荷差与理论柱塞载荷差之比	C₁₅	抽油泵泵效
C₆	最大位移点与最大载荷点柱塞位移量与柱塞冲程比	C₁₆	相邻两点载荷跳变点数
C₇	游动阀开闭载荷、最小载荷差与理论柱塞载荷差之比	C₁₇	最小位移点到固定阀开启点柱塞位移量与柱塞冲程比
C₈	最小位移点与最小载荷点柱塞位移量与柱塞冲程比	C₁₈	最小位移点到游动阀关闭点柱塞位移量与柱塞冲程比
C₉	冲程损失比	C₁₉	柱塞面积内压力损耗
C₁₀	最大载荷点与最小载荷点柱塞位移量与柱塞冲程比	C₂₀	最大位移点到游动阀开启点柱塞位移量与柱塞冲程比

规则	规则条件	规则结论	规则	规则条件	规则结论
1	C₁₃≥0.8,C₁₅≥0.9	连抽带喷	10	C₁>0.35,C₂>0.6,C₁₈≥0.2	固定阀漏失
2	C₁≤0.35,C₂≤0.35,C₃≥-0.5, C₄≥0.5,C₁₅≤0.35	固定阀卡死	11	C₁>0.35,C₂>0.6,C₁₇≥0.2	游动阀漏失
3	C₁≤0.35,C₂≤0.35,C₃<-0.5, C₄≥0.5,C₁₅≤0.35	泵严重磨损	12	C₁>1.2,2.35>C₂>1.5,C₉>0.5	液体摩阻
4	C₁≤0.35,C₂≤0.35,C₃<-0.5, C₁₅<0.1	抽油杆断脱	13	C₁>0.32,C₂>0.6,C₅>0.35, C₇>0.35,C₁₀≤0.15,C₁₅>0.35	泵筒弯曲
5	C₁≤0.35,C₂>0.6,C₁₄>1.0, C₁₅≤0.1,C₁₉≥2.5	气锁	14	C₁>0.32,C₂>0.6,C₅>0.32, C₆<0.13	泵上碰
6	C₁≥0.35,C₂>0.6,C₁₉<2.0, C₂₀≥0.4	液击	15	C₁>0.32,C₂>0.6,C₇≥0.32, C₈<0.13	泵下碰
7	C₁≥0.35,C₂>0.6,C₁₂>0.44, C₁₉≥2.0	气体影响	16	C₂≥2.5,C₉≤0.5	卡泵
8	C₁>0.35,C₂>0.6,C₁₂>0.44, C₁₉<2.0,C₂₀<0.4	轻度液击	17	C₁>0.32,1.5≥C₂>0.6,C₅>0.2, C₇<0.2,C₉>0.5,C₁₇<0.2, C₁₈<0.2,C₁₉>0.2	正常
9	C₁>0.35,C₂>0.6,C₁₁≥1.5, C₁₂≥1.5	柱塞脱筒	18	C₁₆≥9	砂阻