Abnormal production-events recognition of offshore oil and gas wells based on SPC control charts and weighted decision tree

LI Wei; CHEN Jianhua; WU Shaowei; XIA Rujun; CHEN Xiaoquan

doi:10.16028/j.1009-2722.2021.289

2022 Vol. 38, No. 12

Article Contents

Article navigation > Marine Geology Frontiers > 2022 > 38(12): 84-91

Next Article Previous Article

LI Wei, CHEN Jianhua, WU Shaowei, XIA Rujun, CHEN Xiaoquan. Abnormal production-events recognition of offshore oil and gas wells based on SPC control charts and weighted decision tree[J]. Marine Geology Frontiers, 2022, 38(12): 84-91. doi: 10.16028/j.1009-2722.2021.289

Citation:

LI Wei, CHEN Jianhua, WU Shaowei, XIA Rujun, CHEN Xiaoquan. Abnormal production-events recognition of offshore oil and gas wells based on SPC control charts and weighted decision tree[J]. Marine Geology Frontiers, 2022, 38(12): 84-91. doi: 10.16028/j.1009-2722.2021.289

Abnormal production-events recognition of offshore oil and gas wells based on SPC control charts and weighted decision tree

1.
Zhanjiang Branch of CNOOC (China) Ltd., Zhanjiang 524057, China
2.
Advanced Research Institute ，China University of Geosciences (Wuhan), Wuhan 430074，China
3.
Hainan Branch of CNOOC (China) Ltd., Haikou 570100, China

Received Date: 11 November 2021

Publish Date: 28 December 2022

Abstract

Abstract

Many offshore oil fields in China have entered the middle or late stage of exploitation, the equipment and facilities are generally aging, and the breakdown probability is increasing. Due to the high cost of production and maintenance of offshore oil and gas wells, it is very important to identify the potential breakdown of oil and gas wells accurately. By optimizing the standard SPC (statistical process control) chart, we established an appropriate early warning model with production parameter for offshore oil and gas wells, by which to the abnormal production parameters of offshore oil and gas wells can be judged dynamically. At the same time, combined with the business experts experience, we proposed a fault diagnosis model to predict the breakdown types based on weighted decision tree and multi-parameter combination. The early warning model improved the timeliness and accuracy of breakdown identification of offshore oil and gas wells. Application of the model in oil and gas wells in the western South China Sea shortened the response time to the countermeasure by at least 8.4 days, and the success rate of early warning reached 91.18%. Therefore, the model can realize the intelligent identification of oil and gas well production abnormalities and breakdownof oil-and-gas wells, and ensure the high and stable production of offshore oil and gas wells.
- control charts /
- decision tree /
- parameter abnormality /
- early warning system

FullText(HTML)

References

[1]	常彦荣,李允,彭炎,等. 油田生产产量监控体系及预警系统[J]. 西南石油学院学报,2006,28(3):34-37. Google Scholar
[2]	蒋能记,韩力,张亚顺,等. 基于实时数据库的油气处理诊断预警系统设计[J]. 石油规划设计,2011,22(4):49-51. Google Scholar
[3]	杜喜昭,石秀华,赵立强. 油田抽油机数据采集实时监控系统[J]. 测控技术,2010,29(9):51-53. doi: 10.3969/j.issn.1000-8829.2010.09.014 CrossRef Google Scholar
[4]	张乃禄,孙换春,郭永宏,等. 基于示功图的油井工况智能分析[J]. 油气田地面工程,2011,30(4):7-9. doi: 10.3969/j.issn.1006-6896.2011.4.003 CrossRef Google Scholar
[5]	魏军. 油田预警分析模型的研究与设计[J]. 电脑知识与技术,2014,10(25):6011-6014. doi: 10.14004/j.cnki.ckt.2014.0295 CrossRef Google Scholar
[6]	汪旭颖. 基于支持向量回归机的油田异常井预警模型研究[D]. 大庆: 东北石油大学, 2015. Google Scholar
[7]	邴绍强. 基于人工智能的抽油机井结蜡预警方法[J]. 石油钻探技术,2019,47(4):97-103. doi: 10.11911/syztjs.2019093 CrossRef Google Scholar
[8]	周临风,冷建成,魏立新. 基于监测数据的油气管道预警技术[J]. 压力容器,2019,36(5):55-60. doi: 10.3969/j.issn.1001-4837.2019.05.009 CrossRef Google Scholar
[9]	田学民,曹玉苹. 统计过程控制的研究现状及展望[J]. 中国石油大学学报(自然科学版),2008,32(5):175-180. Google Scholar
[10]	余忠华,吴昭同. 控制图模式及其智能识别方法[J]. 浙江大学学报(工学版),2001,35(5):521-525. Google Scholar
[11]	WESTGARD J O,BARRY P L,HUNT M R,et al. A multi-rule Shewhart chart for quality control in clinical chemistry[J]. Clinical Chemistry,1981,27(3):493-501. doi: 10.1093/clinchem/27.3.493 CrossRef Google Scholar
[12]	HOSSAIN A,CHOUDHURY Z A. Statistical process control of an industrial process in real time[J]. IEEE Transactions on Industry Applications,1996,32(2):243-249. doi: 10.1109/28.491471 CrossRef Google Scholar
[13]	林小春,陈向东. 在宝钢炼钢现场使用SPC(统计过程控制)的探讨[J]. 冶金标准化与质量,2001,39(5):29-33. doi: 10.3969/j.issn.1003-0514.2001.05.009 CrossRef Google Scholar
[14]	JOHN S. Oakland. Statistical process control（fifth edition）[M]. Oxford: Butterworth-Heinemann, 2003. Google Scholar
[15]	刘非非,周超,李飞,等. 基于SPC控制图原理的接触式突出预测技术[J]. 煤矿安全,2011,42(10):18-21. doi: 10.13347/j.cnki.mkaq.2011.10.038 CrossRef Google Scholar
[16]	沈晓杰,李郡. 基于制造执行系统的统计过程控制在质量管理上的应用[J]. 工业控制计算机,2012,25(9):108-109. doi: 10.3969/j.issn.1001-182X.2012.09.047 CrossRef Google Scholar
[17]	国家质量技术监督局. GB/T 4091-2001 常规控制图[S]. 北京: 中国标准出版社, 2004. Google Scholar
[18]	国家市场监督管理总局, 国家标准化管理委员会. GB/T 17989.2-2020 控制图第2部分: 常规控制图[S]. 北京: 中国标准出版社, 2020.. Google Scholar
[19]	WOODALL W H. Controversies contradictions in statistical process control[J]. Journal of Quality Technology, 2000, 32(4): 341-351. Google Scholar
[20]	杨静. 标准差控制图的改进[D]. 秦皇岛: 燕山大学, 2018. Google Scholar
[21]	陈婷婷. 涪陵气田辅助决策系统的生产预警应用[J]. 重庆科技学院学报(自然科学版),2018,20(6):98-101. doi: 10.3969/j.issn.1673-1980.2018.06.023 CrossRef Google Scholar
[22]	韩家炜, Micheline Kamber. 数据挖掘: 概念与技术 [M]. 范明, 等译. 北京: 机械工业出版社, 2001: 188-193. Google Scholar
[23]	杨学兵,张俊. 决策树算法及其核心技术[J]. 计算机技术与发展,2007,17(1):43-45. doi: 10.3969/j.issn.1673-629X.2007.01.015 CrossRef Google Scholar
[24]	BANFIELD R E,HALL L O,BOWYER K W. A comparison of decision tree ensemble creation techniques[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,29(1):173-180. Google Scholar
[25]	张琼声,陈晓伟,李春华,等. 一种基于属性加权的决策树算法[J]. 微计算机应用,2010,31(1):58-63. Google Scholar
[26]	张毅,梅挺. 基于加权决策树的蛋白质序列分类算法研究[J]. 计算机与数字工程,2012,40(5):7-9. doi: 10.3969/j.issn.1672-9722.2012.05.003 CrossRef Google Scholar
[27]	陈晓琳,李盛乐,刘坚,等. 基于局部加权的决策树算法在孔隙度预测中的应用[J]. 工程地球物理学报,2014,11(5):736-742. doi: 10.3969/j.issn.1672-7940.2014.05.030 CrossRef Google Scholar
[28]	李庆显,赵美刚,张新政,等. 基于工作流技术实现采油异常井管理[J]. 油气田地面工程,2009,28(3):69-70. Google Scholar
[29]	孙钿奇,赵艳霞. 工作流技术在海洋地质资料归档中的应用[J]. 海洋地质前沿,2017,33(012):66-70. Google Scholar
[30]	孙淮宁,胡学钢. 一种基于属性贡献度的决策树学习算法[J]. 合肥工业大学学报:自然科学版,2009,32(8):1137-1141. Google Scholar
[31]	CHOI J S,CHOI J Y,CHO Y Y. Context-aware workflow model for supporting composite workflows[J]. Journal of Measurement ence & Instrumentation,2010,1(2):161-165. Google Scholar
[32]	李伟,杨元明. 油井措施增产效果评价方法研究[J]. 科学技术与工程,2012,12(31):8370-8378. Google Scholar