4/6/2025, 1:35:51 PM 星期日
Research on lost circulation prediction and diagnosis theoretical model based on machine learning algorithm
CSTR:
Author:
Affiliation:

Institute of Exploration Techniques, CAGS, Langfang Hebei 065000, China

Clc Number:

P634

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference [37]
  • |
  • Related
  • | | |
  • Comments
    Abstract:

    The lost circulation incident in drilling operation has the characteristics of sudden occurrence and difficulty in treatment, which leads to low success rate of plugging and high cost. In order to solve this kind of problem quickly, accurately and efficiently, we must accurately predict lost circulation and put forward plugging measures. In this paper, the gradient boosted decision tree algorithm (GBDT) is used to study the loss circulation prediction model with the feasibility of GBDT as a lost circulation prediction model verified by analyzing some machine learning algorithms. The lost circulation case decision base is established by using case-based reasoning technology, and the Euclidean algorithm and LB_Keogh algorithm are used to search lost circulation cases to put forward corresponding lost circulation treatment measures. The reliability of similarity calculation has been verified through field cases.

    Table 3 Characteristic parameters of lost circulation in Chuan-6B1 and Chuan-6B2 wells
    Fig.1 AHP weighting results
    Table 1 Value scale of characteristic parameters
    Reference
    [1] Kulikov S, Veliev G, Bakhtin A, et al. “Secure Drilling” services for safe and effective drilling[C]//SPE Arctic and Extreme Environments Technical Conference and Exhibition, 2013.
    [2] Raja H, Sørmo F, Vinther M L. Case-based reasoning: Predicting real-time drilling problems and improving drilling performance[C]//SPE Middle East Oil and Gas Show and Conference, 2011.
    [3] 贾爱贵.ALS-K井涌井漏快速探测系统[J].录井技术,1998(2):48-52.
    [4] 姜永,白生平,赵书滨,等.综合录井技术在钻井工程上的应用[J].石油钻采工艺,2009,31(S2): 79-82.
    [5] 李治伟.塔里木井控装备配套技术研究[D].成都:西南石油大学,2011.
    [6] 苟开海,胡泽,葛亮.基于DSP的井底微流量测量系统设计[J].计量与测试技术,2011,38(9):17-19.
    [7] 屈俊波,陈平,马天寿,等.精确监测井底溢流的井下微流量装置设计与试验[J].石油钻探技术,2012,40(5):106-110.
    [8] 王海彪.井漏智能识别及处理决策研究[D].成都:西南石油大学,2017.
    [9] 李雪松,张骁,管震,等.基于图像识别技术的钻井井漏溢流智能报警系统开发[J].世界石油工业,2021,28(1):48-54.
    [10] 和鹏飞,刘晓宾,陈真,等.基于深度神经网络模型的钻井井漏预测研究[J].天津科技,2019,46(S1):21-23.
    [11] 谢平,蒋丽雯,赵尧,等.基于神经网络的井涌井漏实时预测方法研究[J].现代计算机(专业版),2018(11):23-28.
    [12] 李克智,袁本福.红河油田井漏风险实时识别研究与应用[J]. 钻采工艺,2013,36(4):20-22,134.
    [13] 徐哲,李建,王兵,等.基于贝叶斯网络的钻井井漏问题研究[J].石油天然气学报,2013,35(12):125-129,8-9.
    [14] 张正,赖旭芝,陆承达,等.基于贝叶斯网络的钻进过程井漏井涌事故预警[J].探矿工程(岩土钻掘工程),2020,47(4):114-121,144.
    [15] 李晓桐,徐英卓,何坤鹏,等.钻井异常智能预警系统研究[J]. 福建电脑,2013,29(4):1-3.
    [16] 刘彪,李窚晓,李双贵,等.基于支持向量回归的井漏预测[J]. 钻采工艺,2019,42(6):17-20,1-2.
    [17] 谷宇峰,张道勇,鲍志东,等.利用梯度提升决策树(GBDT)预测渗透率——以姬塬油田西部长4+5段致密砂岩储层为例[J].地球物理学进展,2021,36(2):585-594.
    [18] 韩启迪,张小桐,申维.基于梯度提升决策树(GBDT)算法的岩性识别技术[J].矿物岩石地球化学通报,2018,37(6): 1173-1180.
    [19] 石运良,罗宇,陈正科.基于GBDT算法的焊缝背面熔宽预测[J].热加工工艺,2021,50(17):110-114.
    [20] 贾南,何昌原,段海鹏.基于集成算法的森林火灾风险预警模型研究[J].武警学院学报,2021,37(12):5-9.
    [21] 徐安.基于机器学习的慢性疾病预测关键技术研究[D].成都:电子科技大学, 2019.
    [22] 龚谊承,都承华,张艳娜,等.基于主成分和GBDT对血糖值的预测[J].数学的实践与认识,2019,49(14):116-122.
    [23] 黄沼沣,薛旺星,蔡铭,等.基于梯度提升算法的道路交通噪声预测模型研究[J].环境科学与技术,2020,43(4):46-53.
    [24] 翁剑成,付宇,林鹏飞,等.基于梯度推进决策树的日维度交通指数预测模型[J].交通运输系统工程与信息,2019,19(2): 80-85,93.
    [25] 廖璐,张亚东,葛晓程,等.基于GBDT的列车晚点时长预测模型研究[J].铁道标准设计,2021,65(8):149-154,176.
    [26] 陈宏,邓芳明,吴翔,等.基于梯度提升决策树的电力电子电路故障诊断[J].测控技术,2017,36(5):9-12,20.
    [27] 刘金硕,刘必为,张密,等.基于GBDT的电力计量设备故障预测[J].计算机科学,2019,46(S1):392-396.
    [28] 苏兴华,孙俊明,高翔,等.基于GBDT算法的钻井机械钻速预测方法研究[J].计算机应用与软件,2019,36(12):87-92.
    [29] 杜青才.准噶尔南缘复杂构造地质力学分析与井下复杂机理研究[D].成都:西南石油学院,2004.
    [30] 金衍,卢运虎,李再均.一种井漏层位钻前风险预测新方法[J].石油钻采工艺,2008(3):24-28.
    [31] 胡莎莎.压力衰竭地层井漏预测技术研究[D].东营:中国石油大学(华东),2013.
    [32] 刘寿军.钻井液液面监测与自动灌浆装置的研制[J].石油机械,2006(2):29-30,78.
    [33] Denhiere G. Dynamic memory, a theory of reminding and learning in computers and people-schank, RC[J]. Annee Psychologique, 1985,85(4):607-608.
    [34] 张学洪,李黔.基于案例推理的井漏风险预警方法[J].断块油气田,2017,24(2):255-258,263.
    [35] 谷淑娟,高学东,孙冉.一种改进的CBR案例检索相似性度量模型[J].中国管理信息化,2011,14(9):50-55.
    [36] 郭双双.基于模型算法的网络艺术考级研究分析[D].杭州:浙江大学,2018.
    [37] Bassily H. A comparative fault diagnosis methodology based on time series analysis of system’s signals[D]. Clemson: Clemson University, 2007.
    Related
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation
Share
Article Metrics
  • Abstract:876
  • PDF: 908
  • HTML: 1314
  • Cited by: 0
History
  • Received:November 12,2021
  • Revised:January 18,2022
  • Adopted:January 26,2022
  • Online: April 29,2022
  • Published: March 10,2022
Article QR Code