基于随机森林算法的井下原油含水率软测量方法

doi:10.3969/j.issn.1000-1158.2019.05.16

Abstract
Figure/Table
References (25)
Related Citation (15)

Download: PDF (1124 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Real time measurement of wellbore output fluid is a key step in obtaining information from the downhole liquid production and an important prerequisite for the realization of intelligent well. However, there is no better way to measure the content of each component of the output liquid, because of the complexity of downhole environment and the uncertainty of oil-water mixture state. Aimed at the problem of mixed measurement of oil and water in the downhole, a soft sensing method for water cut of crude oil based on machine learning algorithm was presented. Combined with the needs of oil production engineering, water cut of crude oil was divided into 11 categories at 10% intervals. Taking physical properties corresponding to different water cut of crude oil as measurement object, the relationship between physical properties and water cut of crude oil was obtained and then the purpose of measuring the water cut of crude oil was realized, by learning and classifying known samples using random forest algorithm. Finally, the soft sensing method was verified by a designed indoor experiment. The results show that the predicted results by using the mentioned method agree with the experimental values , which can preliminarily meet the requirement of engineering for measuring water cut of underground crude oil and providing a new concept for downhole measurement.

Key words： metrology water cut of crude oil downhole measurement soft sensing random forest algorithm

Received: 10 July 2018 Published: 01 September 2019

PACS:

TB937

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	WANG Peng
	GONG Pan
	FENG Ding
	TU Yi-liu

Cite this article:

WANG Peng,GONG Pan,FENG Ding, et al. Soft Sensing Method for Water Cut of Crude Oil Based on Random Forest Algorithm[J]. Acta Metrologica Sinica, 2019, 40(5): 835-841.

URL:

http://jlxb.china-csm.org:81/Jwk_jlxb/EN/10.3969/j.issn.1000-1158.2019.05.16 OR http://jlxb.china-csm.org:81/Jwk_jlxb/EN/Y2019/V40/I5/835

［1］冯定, 尹松, 王鹏.井下流量实时计量与控制技术研究进展［J］. 石油天然气学报, 2007, 29(4): 148-150.
Feng D, Yin S, Wang P. Research progress of downhole flow measurement and controlling technique ［J］. Journal of Oil and Gas Technology, 2007, 29(4): 148-150.
［2］马文涛, 郭文阁, 雍振, 等.原油含水率测量技术综述［J］. 重庆科技学院学报(自然科学版), 2016, 18(3): 46-49.
Ma W T, Guo W G, Yong Z, et al. Study on development of measuring technique for water content of crude oil ［J］. Journal of Chongqing University of Science and Technology(Natural Sciences Edition), 2016, 18(3): 46-49.
［3］李清玲, 彭军, 唐德东, 等.原油含水率测量技术综述［J］.重庆科技学院学报(自然科学版), 2014, 16(5): 89-92.
Li Q L, Peng J, Tang D D, et al. Technique status and development trends of measuring water content in crude Oil ［J］. Journal of Chongqing University of Science and Technology(Natural Sciences Edition), 2014, 16(5): 89-92.
［4］冯定, 徐冠军, 袁咏心, 等.多相流量计的现状以及发展趋势［J］.机械与电子, 2010,(2): 77-79.
Feng D, Xu G J, Yuan Y X, et al. The current status and development of downhole multiphase flow ［J］. Machinery & Electronics, 2010,(2): 77-79.
［5］孙妍, 张琳.原油含水率测量方法的研究［J］.计算机与数字工程, 2013, 41(7): 1207-1209.
Sun Y, Zhang L. Crude oil moisture content measurement methods ［J］. Computer g-Digital Engineering, 2013, 41(7): 1207-1209.
［6］马文涛.高频电磁波测量原油含水率技术研究［D］.西安: 西安石油大学, 2016.
［7］屈远.电磁电导法测量原油含水率的研究［D］.沈阳: 沈阳工业大学, 2013.
［8］黄芬.基于微波传输特性的原油含水率测量方法研究［D］.西安: 西安电子科技大学, 2015.
［9］杜怀栋, 王春光.电容和电阻法原油含水率快速测量仪的研制［J］. 自动化仪表, 2015, 36(4): 63-67.
Du H D, Wang C G. Development of the high speed measuring instrument for water content of crude oil by using capacitance and resistance method ［J］. Process Automation Instrumentation, 2015, 36(4): 63-67.
［10］贺国强, 党瑞荣, 雷蕾, 等.基于射频法的原油含水率在线测量系统［J］. 油气田地面工程, 2016, 35(8): 78-81.
He G Q, Dang R R, Lei L, et al. Water content in crude oil online measurement system based on radio frequency method ［J］. Oil-Gas Field Surface Engineering, 2016, 35(8): 78-81.
［11］徐耀忠, 王守波.一种原油含水率的微波测量原理［J］.安徽电子信息职业技术学院学报, 2015, (1): 40-43.
Xu Y Z, Wang S B. A theory of microwave measurement of crude oil watercut ［J］. Journal of Anhui Vocational College of Electronics & Information Technology, 2015, (1): 40-43.
［12］黄家才, 石要武, 周欣.高精度石油水分在线测量技术的研究［J］. 计量学报, 2006, 27(2): 175-178.
Huang J C, Shi Y W, Zhou X. Study on precision on-line measurement of petroleum moisture ［J］. Acta Metrologica Sinica, 2006, 27(2): 175-178.
［13］Li Y, Yang W, Wu Z, et al. Gas/oil/water flow measurement by electrical capacitance tomography ［J］. Measurement science and technology,2013, 24(7):1-12.
［14］陈冬.基于BP神经网络的原油含水率测量研究［D］. 沈阳:沈阳工业大学, 2016.
［15］王进旗, 强锡富, 于英华. 基于相位法原油含水率仪的实验研究［J］. 计量学报, 2004, 25(4): 366-368.
Wang J Q, Qiang X F, Yu Y H. Test study of water cut tool in oil well based on phase method ［J］. Acta Metrologica Sinica, 2004, 25(4): 366-368.
［16］马龙博, 张宏建, 周洪亮, 等.基于差压法的油水两相流的流量测量［J］. 浙江大学学报(工学版), 2007, 41(2): 365-368.
Ma L B, Zhang H J, Zhou H L, et al. Oil water twe phase flow measurement based on differential pressure ［J］. Journal of Zhejiang University(Engineering Science), 2007, 41(2): 365-368.
［17］张勇军, 庄欣莉, 宋佳民.基于优化神经网络预报的原油含水率测量［J］. 系统工程理论与实践, 2011, 31(6): 1112-1117.
Zhang Y J, Zhuang X L, Song J M. Prediction method of water content ratio of crude oil based on optimized artificial neural network ［J］. Systems Engineering-Theory & Practice, 2011, 31(6): 1112-1117.
［18］张晓钟, 孟凡芹, 宋生奎.基于神经网络的超声波轻质燃油质量流量测量方法研究［J］. 计量学报, 2017, 38(2): 205-208.
Zhang X Z, Meng F Q, Song S K. The ultrasonic mass flow measurement method of light fuel based on the artificial neural network model ［J］. Acta Metrologica Sinica, 2017, 38(2): 205-208.
［19］Webster M, Richardson S, Gabard-Cuoq C, et al. Multiphase well surveillance with a permanent downhole flowmeter ［C］ //Society of Petroleum Engineers. Technical Conference and Exhibition.Houston, Texas, 2004:1-8.
［20］关玉慧.井下文丘里流量计内油水两相流数值分析及实验验证［D］. 广州:华南理工大学, 2012.
［21］张志浩, 徐冠军, 冯定.基于电测法与文丘里管的井下多相流混相测量技术［J］. 科技传播, 2014,(1):169,180.
Zhang Z H, Xu G J, Feng D. Downhole multiphase flow miscible measurement technology based on electrical measurement and Venturi tube ［J］. Public Communication of Science & Technology, 2014,(1):169,180.
［22］王奕森, 夏树涛.集成学习之随机森林算法综述［J］. 信息通信技术, 2018,(1):49-55.
Wang Y S, Xia S T. A survey of random forests algorithms ［J］. Information and Communications Technologies, 2018, (1):49-55.
［23］贺彦林, 王晓, 朱群雄.基于主成分分析-改进的极限学习机方法的精对苯二甲酸醋酸含量软测量［J］. 控制理论与应用, 2015, 32(1): 80-85.
He Y L, Wang X, Zhu Q X. Modeling of acetic acid content in purified terephthalic acid solvent column using principal component analysis based improved extreme learning machine ［J］. Control Theory & Applications, 2015, 32(1): 80-85.
［24］罗凡.基于原油实时性质的常减压蒸馏装置数据处理和优化研究［D］.南京: 东南大学, 2017.
［25］宋园, 朱丽琴, 程泽凯.基于随机森林的学生成绩评价研究［J］. 齐齐哈尔大学学报(自然科学版), 2017, 33(6): 1-5.
Song Y, Zhu L Q, Cheng Z K. Research on student performance evaluation based on random forest ［J］. Journal of Qiqihar University(Natural Science Edition), 2017, 33(6): 1-5.