An Early Intelligent Kick Detection Method Based on Variation Trend of Engineering Parameters
-
摘要:
由于溢流数据样本量稀缺、不同钻井工况及溢流后不同时期钻井参数响应规律差异等因素，现有溢流检测方法鲁棒性差，难以应用于钻井全过程。为此，基于随机森林算法（random forest，RF）建立了钻井工况智能识别模型，结合物理模型消除钻井工况对溢流特征参数的影响；提取并融合特征参数趋势值，构建溢流风险指数（kick risk index，KRI）自适应计算方法，形成了基于工程参数变化趋势的溢流早期智能检测方法。3口井的溢流数据验证结果表明，钻井工况智能识别模型的准确率为96.5%，相比人工坐岗预警，平均预警提前时间为8.3 min。研究表明，该方法适用于钻井全过程溢流检测和部分特征参数测量失效的场景，对于保障钻井安全、缩短钻井周期具有一定的指导作用。
Abstract:Due to the scarcity of kick data samples, variations in different drilling conditions, and differences in the response rules of drilling parameters during different stages after a kick, existing kick detection methods exhibit poor robustness and are difficult to apply throughout the drilling process. By using the random forest (RF) algorithm, an intelligent recognition model for drilling conditions was established. This model combined a physical model to eliminate the impact of drilling conditions on kick characteristic parameters, extracting and integrating the trend values of these parameters to construct an adaptive calculation method for the kick risk index (KRI). In addition, a method for early intelligent kick detection based on the variation trend of engineering parameters was proposed. The proposed method was validated by using kick data from three wells, and the results showed that the accuracy of the intelligent recognition model for drilling conditions was 96.5%. Compared to manual warning methods, the average early warning time is 8.3 min in advance. The research demonstrates that this method is suitable for kick detection throughout the drilling process and for scenarios where some characteristic parameter measurements may fail. It has significant guiding implications for ensuring drilling safety and shortening drilling cycles.
-
Keywords:
- kick /
- intelligent detection /
- drilling conditions /
- random forest /
- kick risk index
-
-
![]()
图 1 训练集与测试集各钻井工况样本量分布
Figure 1. Sample size distribution for each drilling condition in training set and test set
![]()
图 2 不同决策树数量和树深度组合下模型的准确率
Figure 2. Model accuracy under different combinations of decision tree number and tree depth
![]()
图 3 钻井工况智能识别模型可视化结果
Figure 3. Visualization results of intelligent recognition model for drilling conditions
![]()
图 4 钻井工况智能识别模型测试结果
0.下钻；1.下钻（开泵）；2.划眼；3.干划眼；4.起钻；5.起钻（开泵）；6.倒划眼；7.干倒划眼；8.原地旋转；9.原地循环；10.原地循环（旋转）；11.静止；12.复合钻进；13.滑动钻进
Figure 4. Test results of intelligent recognition model for drilling conditions
![]()
图 7 井1实时钻井数据及溢流风险指数计算结果
Figure 7. Real-time drilling data and KRI calculation results of Well 1
![]()
图 8 井2实时钻井数据及溢流风险指数计算结果
Figure 8. Real-time drilling data and KRI calculation results of Well 2
![]()
图 9 溢流特征参数权重随时间变化的结果
Figure 9. Variation of weight of kick characteristic parameters with time
![]()
图 10 井3实时钻井数据及溢流风险指数计算结果
Figure 10. Real-time drilling data and KRI calculation results of Well 3
表 1 不同钻井工况下发生溢流时特征参数及其响应规律
Table 1 Characteristic parameters and response rules of kick under different drilling conditions
钻井工况 溢流特征参数 响应规律 静止、原地旋转 出口流量、总池液面高度 井口有钻井液流出，总池液面升高 原地循环、原地循环（旋转）、复合钻进、滑动钻进 出口流量、总池液面高度、
立管压力、出口密度入口流量大于出口流量，总池液面升高，立管压力和出口密度降低 起钻、干倒划眼 总池液面高度 钻井液灌入量小于起出钻具体积 起钻（开泵）、倒划眼 出口流量和密度、总池液面高度 出口流量大于入口流量，钻井液注入量小于起出钻具体积，出口密度降低 下钻、干划眼 总池液面高度 钻井液返出量大于下入钻具体积 下钻（开泵）、划眼 出口流量和密度、总池液面高度 出口流量大于入口流量，钻井液返出量大于下入钻具体积，出口密度降低 
下载: 导出CSV
表 2 不同方法检测到的溢流时间对比
Table 2 Kick time detected by different methods
井号 特征参数序列
窗口大小入口流量序列
趋势阈值特征参数序列
趋势阈值工况类型 现场检测到
溢流时间溢流方法检测
到溢流时间预警提前时间/min 1 60 0.001 0.001 复合钻进 13:26 13:18 8 2 60 0.001 0.005 原地循环 23:37 23:28 9 3 60 0.001 0.001 复合钻进 01:50 01:42 8
下载: 导出CSV
-
[1] 徐进,胡大梁,任茂,等. 川西深井井下复杂情况及故障预防与处理[J]. 石油钻探技术,2010,38(4):22–25. XU Jin, HU Daliang, REN Mao, et al. Prevention and treatment of complicated downhole conditions and accidents of deep wells in western Sichuan[J]. Petroleum Drilling Techniques, 2010, 38(4): 22–25.
[2] 史亚红,夏宏泉,彭梦,等. 一种准确预测钻井液安全密度窗口的新方法[J]. 断块油气田,2019,26(2):248–252. SHI Yahong, XIA Hongquan, PENG Meng, et al. New accurate prediction method of safe window of drilling fluid density[J]. Fault-Block Oil & Gas Field, 2019, 26(2): 248–252.
[3] 王建云,杨晓波,王鹏,等. 顺北碳酸盐岩裂缝性气藏安全钻井关键技术[J]. 石油钻探技术,2020,48(3):8–15. WANG Jianyun, YANG Xiaobo, WANG Peng, et al. Key technologies for the safe drilling of fractured carbonate gas reservoirs in the Shunbei Oil and Gas Field[J]. Petroleum Drilling Techniques, 2020, 48(3): 8–15.
[4] 高永德,董洪铎,胡益涛,等. 深水高温高压井钻井液当量循环密度预测模型及应用[J]. 特种油气藏,2022,29(3):138–143. GAO Yongde, DONG Hongduo, HU Yitao, et al. Prediction model of equivalent circulating density of drilling fluid in deep HPHT wells and its application[J]. Special Oil & Gas Reservoirs, 2022, 29(3): 138–143.
[5] 陶振宇,樊洪海,刘玉含,等. 基于地层溢流能量的压井方式选择方法[J]. 石油钻采工艺,2023,45(4):424–431. TAO Zhenyu, FAN Honghai, LIU Yuhan, et al. The method for well-killing selection considering the formation overflow energy[J]. Oil Drilling & Production Technology, 2023, 45(4): 424–431.
[6] 张来斌,谢仁军,殷启帅. 深水油气开采风险评估及安全控制技术进展与发展建议[J]. 石油钻探技术,2023,51(4):55–65. ZHANG Laibin, XIE Renjun, YIN Qishuai. Technical progress and development suggestions for risk assessment and safety control of deep-water oil and gas exploitation[J]. Petroleum Drilling Techniques, 2023, 51(4): 55–65.
[7] 王志远,梁沛智,陈科杉,等. 深部地层智能压井多解性分析与优化策略[J]. 石油钻探技术,2024,52(2):136–145. WANG Zhiyuan, LIANG Peizhi, CHEN Kesha, et al. Multi-solution analysis and optimization strategy for intelligent well killing in deep formation[J]. Petroleum Drilling Techniques, 2024, 52(2): 136–145.
[8] 孙甫南. 用关基井随钻综合录井曲线判断溢流信息[J]. 天然气工业,1986,8(4):50–54. SUN Funan. Judging overflow information by composite log curves while drilling in guan key well[J]. Natural Gas Industry, 1986, 8(4): 50–54.
[9] SCHAFER D M, LOEPPKE G E, GLOWKA D A, et al. An evaluation of flowmeters for the detection of kicks and lost circulation during drilling[R]. SPE 23935, 1992.
[10] CAYEUX E, DAIREAUX B. Insights into the physical phenomena that influence automatic gain/loss detection during drilling operations[J]. SPE Drilling & Completion, 2017, 32(1): 13–24.
[11] 刘书杰,杨向前,郭华,等. 井控溢流快速判断方法研究[J]. 煤炭技术,2017,36(5):296–298. LIU Shujie, YANG Xiangqian, GUO Hua, et al. Research for judgment method of well control overflow[J]. Coal Technology, 2017, 36(5): 296–298.
[12] 王健,陈颖,张军阳,等. 钻井液循环系统减缓液面波动装置研发与应用[J]. 石油钻探技术,2017,45(5):48–52. WANG Jian, CHEN Ying, ZHANG Junyang, et al. Development and application of a device for alleviating liquid level fluctuation to be used in drilling fluid circulation system[J]. Petroleum Drilling Techniques, 2017, 45(5): 48–52.
[13] 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. QU Junbo, CHEN Ping, MA Tianshou, et al. Design and test of down-hole micro-flow device for monitoring overflow[J]. Petroleum Drilling Techniques, 2012, 40(5): 106–110.
[14] 史肖燕,周英操,赵莉萍,等. 基于随机森林的溢漏实时判断方法研究[J]. 钻采工艺,2020,43(1):9–12. SHI Xiaoyan, ZHOU Yingcao, ZHAO Liping, et al. Study on how to determine kicks and losses in real time on basis of random forest method[J]. Drilling & Production Technology, 2020, 43(1): 9–12.
[15] 孙伟峰,刘凯,张德志,等. 结合钻井工况与Bi-GRU的溢流与井漏监测方法[J]. 石油钻探技术,2023,51(3):37–44. SUN Weifeng, LIU Kai, ZHANG Dezhi, et al. A kick and lost circulation monitoring method combining Bi-GRU and drilling conditions[J]. Petroleum Drilling Techniques, 2023, 51(3): 37–44.
[16] DUAN Shiming, SONG Xianzhi, CUI Yi, et al. Intelligent kick warning based on drilling activity classification[J]. Geoenergy Science and Engineering, 2023, 222: 211408. doi: 10.1016/j.geoen.2022.211408
[17] 杨红满,卢世浩,徐高军,等. 西北油田智能监测溢流预警系统建立与应用效果评价[J]. 化工设计通讯,2017,43(7):90–92. YANG Hongman, LU Shihao, XU Gaojun, et al. Establishment and application of intelligent monitoring overflow warning system in Northwest Oilfield[J]. Chemical Engineering Design Communications, 2017, 43(7): 90–92.
[18] TANG Hewei, ZHANG Shang, ZHANG Feifei, et al. Time series data analysis for automatic flow influx detection during drilling[J]. Journal of Petroleum Science and Engineering, 2019, 172: 1103–1111. doi: 10.1016/j.petrol.2018.09.018
[19] MAO Youli, ZHANG Peng. An automated kick alarm system based on statistical analysis of real-time drilling data[R]. SPE 197275, 2019.
[20] 晏琰,段慕白,黄浩. 基于趋势线法的钻井风险预警技术研究[J]. 钻采工艺,2023,46(2):170–174. YAN Yan, DUAN Mubai, HUANG Hao. Research on drilling risk early warning technology based on trend line method[J]. Drilling & Production Technology, 2023, 46(2): 170–174.
[21] 董师师,黄哲学. 随机森林理论浅析[J]. 集成技术,2013,2(1):1–7. DONG Shishi, HUANG Zhexue. A brief theoretical overview of random forests[J]. Journal of Integration Technology, 2013, 2(1): 1–7.
[22] 李欣海. 随机森林模型在分类与回归分析中的应用[J]. 应用昆虫学报,2013,50(4):1190–1197. LI Xinhai. Using “random forest” for classification and regression[J]. Chinese Journal of Applied Entomology, 2013, 50(4): 1190–1197.
[23] SLEITI A K, TAKALKAR G, EL-NAAS M H, et al. Early gas kick detection in vertical wells via transient multiphase flow modelling: A review[J]. Journal of Natural Gas Science and Engineering, 2020, 80: 103391. doi: 10.1016/j.jngse.2020.103391
[24] 田野,蒋东雷,马传华,等. 钻柱偏心旋转对环空摩阻压降影响的数值模拟研究[J]. 石油钻探技术,2022,50(5):42–49. TIAN Ye, JIANG Donglei, MA Chuanhua, et al. Numerical simulation of the effects of eccentric rotation of the drill string on annular frictional pressure drop[J]. Petroleum Drilling Techniques, 2022, 50(5): 42–49.
-
期刊类型引用(10)
1. 张启龙，张明，陈玲，刘鹏，孙龙飞，谢宗财. 连续油管喷砂射孔管柱校核方法研究与应用. 当代化工. 2023(07): 1604-1609 . 
百度学术
2. 王思凡，张安康，胡东锋. 连续油管打捞砂埋节流器技术研究与现场试验. 石油钻探技术. 2021(05): 108-113 . 本站查看
3. 韩超，刘峰，余建生，王晓，陈玉山. 渤海A油田水力喷砂射孔压裂增产技术. 油气井测试. 2020(04): 56-62 . 百度学术
4. 李凌川. 致密砂岩气藏水平井全通径分段压裂改造实践及认识. 钻采工艺. 2019(05): 62-65+10 . 百度学术
5. 闫吉曾. 泾河油田非均质储层三维水平井钻井技术. 石油机械. 2018(06): 13-19 . 百度学术
6. 杨同玉，魏辽，冯丽莹，马兰荣，朱玉杰. 水平井趾端压裂关键工具设计与试验. 石油钻探技术. 2018(04): 54-58 . 本站查看
7. 陈晓华，王翔，冯永超，牛萌萌，闫吉曾. 泾河油田裂缝性致密油藏防漏堵漏技术. 断块油气田. 2017(02): 297-300 . 百度学术
8. 郑子君，余成. 重复射孔对套管强度的影响. 石油机械. 2017(12): 100-105 . 百度学术
9. 李建山. 泾河油田水平井固井难点与对策研究. 石油钻探技术. 2017(06): 19-23 . 本站查看
10. 朱新春. 泾河油田分段多簇压裂起裂机理分析及参数设计. 断块油气田. 2016(02): 226-229 . 百度学术
其他类型引用(4)
计量
- 文章访问数: 174
- HTML全文浏览量: 43
- PDF下载量: 87
- 被引次数: 14
