基于数据模型协作的海上钻井溢流早期预测预警

doi:10.16265/j.cnki.issn1003-3033.2024.04.1390

中国安全科学学报 ›› 2024, Vol. 34 ›› Issue (4): 93-100.doi: 10.16265/j.cnki.issn1003-3033.2024.04.1390

基于数据模型协作的海上钻井溢流早期预测预警

杨向前¹(), 张苹茹², 武胜男²^,^**(), 张来斌², 李中¹, 冯桓榰¹

¹ 中海石油(中国)有限公司北京研究中心,北京 100028
² 中国石油大学(北京) 安全与海洋工程学院,北京 102249
³ 油气生产安全与应急技术应急管理部重点实验室,北京 102249

收稿日期:2023-10-13 修回日期:2024-01-29 出版日期:2024-04-28
通讯作者:
**武胜男(1986—),女,山西大同人,博士,副教授,主要从事复杂油气开采及关键安全装备风险评估、预警、可靠性与测试维护等方面的研究。E-mail: wushengnan@cup.edu.cn。
作者简介:
杨向前 (1970—),男,陕西西安人,本科,高级工程师,从事海洋石油钻机和修井机的技术发展规划、方案论证和新技术开发等工作。E-mail: yangxq15@cnooc.com.cn。
张来斌教授
基金资助:
国家重点研发计划资助项目(2022YFC2806504); 中海石油(中国)有限公司北京研究中心科研资助项目(CCL2022RCPS2008XNN)

Early prediction and warning of offshore drilling overflow based on data model collaboration

YANG Xiangqian¹(), ZHANG Pingru², WU Shengnan²^,^**(), ZHANG Laibin², LI Zhong¹, FENG Huanzhi¹

¹ Beijing Research Center of CNOOC, Beijing 100028, China
² School of Safety and Ocean Engineering, China University of Petroleum (Beijing),Beijing 102249, China
³ Key Laboratory of Oil and Gas Production Safety and Emergency Technology Emergency Management,Beijing 102249, China

Received:2023-10-13 Revised:2024-01-29 Published:2024-04-28

摘要/Abstract

摘要：

为防止海上钻井过程中井喷事故的发生,提出基于数据模型协作的海上钻井溢流早期预测预警方法。首先,建立基于粒子群优化(PSO)-最小二乘支持向量机(LSSVM)(PSO-LSSVM)的溢流风险预测模型,预测钻井监测参数未来时长内的趋势,并分析溢流事件与表征参数之间的关联关系;然后,建立基于朴素贝叶斯方法的钻井单参数溢流概率估算模型,并通过优化的D-S方法融合多个钻井参数的概率,分级预警溢流事件。结果表明:基于PSO-LSSVM的预测模型所得的溢流表征参数,预测误差较低;因对溢流事件的敏感度不同,单钻井参数所表征的溢流事件概率存在一定偏差;融合后的预警模型能够解决单参数的预警时间不一致的问题,排除误报警的可能。

关键词: 数据模型协作, 钻井溢流, 早期预测, 粒子群优化(PSO)-最小二乘支持向量机(LSSVM)(PSO-LSSVM), 预警模型

Abstract:

An early prediction and warning method of offshore drilling overflow based on data model collaboration was proposed to prevent blowout accidents during offshore drilling. Firstly, an overflow risk prediction model based on PSO-LSSVM was established to predict the trend of drilling monitoring parameters in the future, and analyze the correlation between overflow events and characterization parameters. Then, a single-parameter overflow probability estimation prediction model was proposed based on the Naive Bayesian method, and the probabilities of multiple drilling parameters were integrated through the optimized D-S method to realize a hierarchical early warning of overflow events. The results indicated that the overflow characterization parameters simulated by the PSO-LSSVM model had low prediction errors. The overflow event probability represented by a single drilling parameter showed discrepancies due to different sensitivities. The fused early warning model can address the issues of inconsistent early warning times of single parameters and eliminate the possibility of false alarms.

Key words: data model collaboration, drilling overflow, early prediction, particle swarm optimization(PSO)-least squares support vector machines(LSSVM)(PSO-LSSVM), early warning models

中图分类号:

X937

杨向前, 张苹茹, 武胜男, 张来斌, 李中, 冯桓榰. 基于数据模型协作的海上钻井溢流早期预测预警[J]. 中国安全科学学报, 2024, 34(4): 93-100.

YANG Xiangqian, ZHANG Pingru, WU Shengnan, ZHANG Laibin, LI Zhong, FENG Huanzhi. Early prediction and warning of offshore drilling overflow based on data model collaboration[J]. China Safety Science Journal, 2024, 34(4): 93-100.

图/表 10

图1

图2

图3

表1

图4

表2

图5

表3

表4

图6

参考文献 18

[1]	朱敬宇, 陈国明, 吕寒, 等. 深水钻井井喷事故风险控制决策方法[J]. 中国安全科学学报, 2020, 30(2):113-118. doi: 10.16265/j.cnki.issn1003-3033.2020.02.018
	ZHU Jingyu, CHEN Guoming, LYU Han, et al. Research on risk control decision method for deepwater drilling blowout[J]. China Safety Science Journal, 2020, 30(2):113-118. doi: 10.16265/j.cnki.issn1003-3033.2020.02.018
[2]	LIANG Haibo, LIU Gang, GAO Jianchang, et al. Overflow remote warning using improved fuzzy c-means clustering in IoT monitoring system based on multiaccess edge computing[J]. Neural Computing and Applications, 2020, 32(19):15 399-15 410.
[3]	闫铁, 许瑞, 刘维凯, 等. 中国智能化钻井技术研究发展[J]. 东北石油大学学报, 2020, 44(4):15-21.
	YAN Tie, XU Rui, LIU Weikai, et al. Research and development of intelligent drilling technology in china[J]. Journal of Northeast Petroleum University, 2020, 44(4):15-21.
[4]	SU Kanhua, GUAN Zhichuan, ZHOU Guangchen. Error analysis of standpipe pressure control and prediction of surface casing pressure for horizontal well killing process[J]. Journal of China University of Petroleum. Edition of Natural Science, 2008, 59(32):51-55.
[5]	吴君达, 李治平, 孙妍, 等. 基于神经网络的剩余油分布预测及注采参数优化[J]. 油气地质与采收率, 2020, 27(4):85-93.
	WU Junda, LI Zhiping, SUN Yan, et al. Neural network-based prediction of remaining oil distribution and optimization of injection-production parameters[J]. Petroleum Geology and Recovery Efficiency, 2020, 27(4):85-93.
[6]	刘巍, 刘威, 谷建伟, 等. 利用卡尔曼滤波和人工神经网络相结合的油藏井间连通性研究[J]. 油气地质与采收率, 2020, 27(2):118-124.
	LIU Wei, LIU Wei, GU Jianwei, et al. Research on interwell connectivity of oil reservoirs based on Kalman filter and artificial neural network[J]. Petroleum Geology and Recovery Efficiency, 2020, 27(2):118-124.
[7]	王泽龙, 刘先贵, 唐海发, 等. 基于多次数据吸收集合平滑算法的自动油藏历史拟合研究[J]. 特种油气藏, 2021, 28(3):99-105. doi: 10.3969/j.issn.1006-6535.2021.03.015
	WANG Zelong, LIU Xiangui, TANG Haifa, et al. Study on automatic reservoir history matching based on ES-MDA algorithm[J]. Special Oil and Gas Reservoirs, 2021, 28(3):99-105.
[8]	葛景凯. 综合录井参数在钻井工程异常预警中的应用探讨[J]. 信息系统工程, 2020(3):97-98.
	GE Jingkai. Discussion on the application of comprehensive logging parameters in abnormal early warning of drilling engineering[J]. Information System Engineering, 2020(3):97-98.
[9]	LIANG Haibo, TANG Yongqiang, XIANG Li, et al. Research on drilling kick and loss monitoring method based on bayesian classification[J]. Pakistan Journal of Statistics, 2014, 30(6):1251-1266.
[10]	WU Shengnan, ZHANG Laibin, ZHENG Wenpei, et al. A DBN-based risk assessment model for prediction and diagnosis of offshore drilling incidents[J]. Journal of Natural Gas Science and Engineering, 2016, 34:139-158.
[11]	LIANG Haibo, WANG Zhi. Application of an intelligent early-warning method based on DBSCAN clustering for drilling overflow accident[J]. Cluster Computing-The Journal of Networks Software Tools and Applications, 2019, 22(5):12 599-12 608.
[12]	徐振华. 基于云计算的控压钻井溢流监测诊断系统研究与设计[D]. 成都: 西南石油大学, 2019.
	XU Zhenhua. Research and design of overflow monitoring and diagnosis system for MPD based on cloud computing[D]. Chengdu: Southwest Petroleum University, 2019.
[13]	李玉飞, 张博, 孙伟峰. 基于SVM和D-S证据理论的早期溢流智能识别方法[J]. 钻采工艺, 2020, 43(5):27-30,6. doi: 10.3969/J. ISSN.1006-768X.2020.05.08
	LI Yufei, ZHANG Bo, SUN Weifeng. Intelligent identification method of early overflow based on SVM and D-S evidence theory[J]. Drilling and Production Technology, 2020, 43(5):27-30,6. doi: 10.3969/J. ISSN.1006-768X.2020.05.08
[14]	SUN Wenfeng, LI Maoran, LIU Chunyang, et al. Experimental research on lost circulation and overflow monitoring system for drilling engineering based on the requirements of safe and efficient oil and gas drilling[J]. Fresenius Environmental Bulletin, 2021, 30(2):1511-1517.
[15]	李福祥, 王建敏, 梁建创, 等. 离散属性的朴素贝叶斯分类算法的优化[J]. 小型微型计算机系统, 2022, 43(5):897-901.
	LI Fuxiang, WANG Jianmin, LIANG Jianchuang, et al. Optimization of naive Bayesian classification algorithm for discrete attributes[J]. Journal of Chinese Computer Systems, 2022, 43(5):897-901.
[16]	罗福星, 刘卫国. 一种朴素贝叶斯分类增量学习算法[J]. 微计算机应用, 2008, 29(6):107-112.
	LUO Fuxing, LIU Weiguo. An incremental learning algorithm for Naive Bayesian classification[J]. Microcomputer Applications, 2008, 29(6):107-112.
[17]	宋英华, 吴昊, 刘丹, 等. 基于D-S证据理论的地震应急救援群决策[J]. 中国安全科学学报, 2020, 30(5):163-168. doi: 10.16265/j.cnki.issn1003-3033.2020.05.025
	SONG Yinghua, WU Hao, LIU Dan, et al. Group decision-making for earthquake emergency rescue plan based on D-S evidence theory[J]. China Safety Science Journal, 2020, 30(5):163-168. doi: 10.16265/j.cnki.issn1003-3033.2020.05.025
[18]	彭会萍, 曹晓军. 基于决策距离测量的D-S证据理论冲突处理方法[J]. 计算机应用与软件, 2011, 28(4):174-176,179.
	PENG Huiping, CAO Xiaojun. D-S evidence theory conflict handling method based on decision distance measurement[J]. Computer Applications and Software, 2011, 28(4):174-176,179.

特征参数	表征规律
钻速	增加
立管压力	降低
大钩负载	增加

数据	动态阈值下限	动态阈值上限	朴素贝叶斯标记	事件类型
-0.194	-0.072	0.428	-1	溢流
-0.296	-0.129	0.371	-1	溢流
-0.364	-0.199	0.301	-1	溢流
-0.376	-0.266	0.234	-1	溢流
-0.294	-0.305	0.195	0	正常
-0.110	-0.288	0.212	0	正常
0.171	-0.195	0.305	0	正常
0.586	-0.004	0.496	+1	溢流

参数名称	漏标占比	虚标占比
立管压力	0.8	0.57
钻速	1.1	1.1
大钩负载	0.5	0.8

基于数据模型协作的海上钻井溢流早期预测预警

Early prediction and warning of offshore drilling overflow based on data model collaboration

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 18

相关文章 10

编辑推荐

Metrics

本文评价

[1]	段在鹏, 李帆, 郭进, 李炯. 城市易涝区房屋结构安全集成预警模型[J]. 中国安全科学学报, 2023, 33(7): 173-180.
[2]	段在鹏, 李炯, 李帆, 刘碧强. 农村改造房屋结构安全预警模型[J]. 中国安全科学学报, 2023, 33(4): 100-106.
[3]	李红霞, 徐浩冉, 田水承. 基于随机森林的矿工不安全行为预测预警模型[J]. 中国安全科学学报, 2022, 32(12): 10-18.
[4]	石娟, 常丁懿, 郑鹏. 基于BP神经网络的建筑工人不安全行为预警模型[J]. 中国安全科学学报, 2022, 32(1): 27-33.
[5]	刘名强, 李英攀, 王芳, 陈晓, 李瑞格, 李晓喆. 基于RVM的装配式建筑吊装作业安全预警模型[J]. 中国安全科学学报, 2018, 28(4): 109-114.
[6]	刘新宇，赵恺，胡虓，余玉欢. 港口物流枢纽危险货物重大危险源预警方法研究[J]. 中国安全科学学报, 2013, 23(5): 82-.
[7]	雷勋平，Robin Qiu，吴杨. 基于供应链和可拓决策的食品安全预警模型及其应用[J]. 中国安全科学学报, 2011, 21(11): 136-.
[8]	尹贻林，林广利，付聪，陈伟珂. 基于GIS天津市燃气管网预警系统的构建研究[J]. 中国安全科学学报, 2009, 19(6): 104-.
[9]	张鸿，刘优平，黎剑华，栾建平，荣耀. 基于模糊理论的隧道施工安全预警模型研究及应用[J]. 中国安全科学学报, 2009, 19(4): 5-.
[10]	杨玉中，冯长根，吴立云. 基于可拓理论的煤矿安全预警模型研究[J]. 中国安全科学学报, 2008, 18(1): 40-.

预测方法	MSE/%
PSO-LSSVM	4.1
优化的PSO-LSSVM	0.3