Real-time early warning of pipe sticking based on abnormal diagnosis of engineering parameter change trend

SHENG Yanan

doi:10.12143/j.ztgc.2024.01.009

2024 Vol. 51, No. 1

Article Contents

Article navigation > DRILLING ENGINEERING > 2024 > 51(1): 68-74

Next Article Previous Article

SHENG Yanan. 2024. Real-time early warning of pipe sticking based on abnormal diagnosis of engineering parameter change trend. DRILLING ENGINEERING, 51(1): 68-74. doi: 10.12143/j.ztgc.2024.01.009

Citation:

SHENG Yanan. 2024. Real-time early warning of pipe sticking based on abnormal diagnosis of engineering parameter change trend. DRILLING ENGINEERING, 51(1): 68-74. doi: 10.12143/j.ztgc.2024.01.009

Real-time early warning of pipe sticking based on abnormal diagnosis of engineering parameter change trend

SHENG Yanan¹

Drilling Engineering and Technology Research Institute, Zhongyuan Petroleum Engineering Co., Ltd.,SINOPEC, Puyang Henan 457001, China

Received Date: 16 June 2023

Revised Date: 22 August 2023

Abstract

Abstract

South Sichuan work area is a key shale gas exploration and development area of Sinopec. The high formation pressure coefficient and harsh drilling geological conditions in this work area lead to complex drilling and frequent failures， among which sticking fault is the most prominent which seriously restricts the safe and efficient development of shale gas in South Sichuan. There are some problems in the existing technology， such as poor comprehensive utilization of monitoring information， not timely risk warning and strong subjectivity. In this paper， through the analysis of the expert knowledge judgment of sticking fault in the drilling process， the key characterization parameters corresponding to the risk of sticking are determined， the change trend of the key characterization parameters at the location of sticking is studied and the corresponding change rules are obtained. On this basis， a real-time early warning method for sticking fault based on abnormal diagnosis of engineering parameter change trend is established. Well WY-XX is selected as an example for analysis， as a result， the warning results by this software is consistent with the actual downhole risk which verified the correctness and reliability of the model with the success rate of 83%.
- shale gas exploration and development /
- sticking /
- risk early warning /
- real-time warning /
- VDX parameterinstrument /
- South Sichuan work area

FullText(HTML)

References

[1]	蒋希文.钻井事故与复杂问题（第2版）［M］.北京：石油工业出版社，2006：72-80.JIANG Xiwen. Drilling Accidents and Complex Problems （Second Edition）［M］. Beijing： Petroleum Industry Press， 2006：72-80． Google Scholar
[2]	[2] 李紫璇，张菲菲，祝钰明，等.钻井模型与机器学习耦合的实时卡钻预警技术［J］.石油机械，2022，50（4）：15-21，93. Google Scholar LI Zixuan， ZHANG Feifei， ZHU Yuming， et al. Real time stuck drilling warning technology coupled with drilling model and machine learning［J］. Petroleum Machinery， 2022，50（4）：15-21，93. Google Scholar
[3]	[3] 刘海龙，李彤，张奇志.基于自适应遗传算法改进的BP神经网络卡钻事故预测［J］.现代电子技术，2021，44（15）：149-153. Google Scholar LIU Hailong， LI Tong， ZHANG Qizhi. BP neural network based on adaptive genetic algorithm improvement for predicting stuck drill accidents［J］. Modern Electronic Technology， 2021，44（15）：149-153. Google Scholar
[4]	[4] 朱硕，宋先知，李根生，等.钻柱摩阻扭矩智能实时分析与卡钻趋势预测［J］.石油钻采工艺，2021，43（4）：428-435. Google Scholar ZHU Shuo， SONG Xianzhi， LI Gensheng， et al. Intelligent real time analysis of drill string friction and torque and prediction of stuck trend［J］. Petroleum Drilling and Production Technology， 2021，43（4）：428-435. Google Scholar
[5]	[5] Khakzad N.， Khan F.， Amyotte P. Quantitative risk analysis of offshore drilling operations： A Bayesian approach［J］. Safety Science， 2013，57（3）：108-117. Google Scholar
[6]	[6] 苏晓眉，张涛，李玉飞，等.基于K-Means聚类算法的沉砂卡钻预测方法研究［J］.钻采工艺，2021，44（03）：5-9. Google Scholar SU Xiaomei， ZHANG Tao， LI Yufei， et al. Research on the prediction method of sand sticking based on K-Means clustering algorithm［J］. Drilling and Production Technology， 2021，44（3）：5-9. Google Scholar
[7]	[7] 魏纳，李蜀涛，陈亮，等.AD401-7井定向井卡钻复杂事故的处理及分析［J］.探矿工程（岩土钻掘工程），2018，45（4）：10-16. Google Scholar WEI Na， LI Shutao， CHEN Liang， et al. AD 4017 directional well’s processing and analysis of drilling complex accident［J］. Exploration Engineering （Rock & Soil Drilling and Tunneling）， 2018，45（4）：10-16. Google Scholar
[8]	[8] 翟育峰，赵辉，王鲁朝，等.湘南3000 m科学深钻孔内事故处理及对策［J］.钻探工程，2023，50（4）：32-40.ZHAI Yufeng， ZHAO Hui， WANG Luzhao， et al. Down-hole incident treatment and prevention for the 3000m scientific deep borehole in southern Hunan［J］. Drilling Engineering， 2023，50（4）：32-40.. Google Scholar
[9]	[9] 朱迪斯，赵洪波，刘恩然，等.长江下游（安徽）地区页岩气钻井工程难点及对策分析［J］.钻探工程，2022，49（5）：11-21.ZHU Disi， ZHAO Hongbo， LIU Enran， et al. Shale gas drilling difficulties and their solutions in the lower reach of the Yangtze River （Anhui）［J］. Drilling Engineering， 2022，49（5）：11-21.. Google Scholar
[10]	[10] 陈庭根，管志川.钻井工程理论与技术［M］.东营：中国石油大学出版社，2006： 51-54. Google Scholar CHEN Tinggen， GUAN Zhichuan. Theory and Technology of Drilling Engineering［M］. Dongying： Petroleum University Press， 2000：51-54. Google Scholar
[11]	[11] Jahanbakhshi R， Keshavarzi R， Shoorehdeli M A， et al. Intelligent prediction of differential pipe sticking by support vector machine compared with conventional artificial neural networks： An example of Iranian Offshore Oil Fields［J］. SPE Drilling & Completion， 2012，27（4）：586-595. Google Scholar
[12]	[12] 赵虎.数据采集中的未确知有理数滤波方法［J］.自动化仪表，2008（8）：12-14. Google Scholar ZHAO Hu. Unascertained rational number filtering method in data acquisition［J］. Automatic Instrument， 2008，14（8）：12-14. Google Scholar
[13]	[13] 柳小桐.BP神经网络输入层归一化［J］.机械工程与自动化，2010，11（3）：122-126. Google Scholar LIU Xiaotong. Input layer normalization of BP neural network ［J］. Mechanical Engineering and Automation， 2010，11（3）：122-126. Google Scholar