基于MWSPCA-CBR的智能预警方法研究及其在石化工业中的应用

doi:10.11949/j.issn.0438-1157.20181340

化工学报 ›› 2019, Vol. 70 ›› Issue (2): 572-580.DOI: 10.11949/j.issn.0438-1157.20181340

基于MWSPCA-CBR的智能预警方法研究及其在石化工业中的应用

耿志强^1,²(),景邵星^1,²,白菊^1,²,王仲凯^1,²,朱群雄^1,²,韩永明^1,²()

1. 北京化工大学信息科学与技术学院，北京 100029
2. 智能过程系统工程教育部工程研究中心，北京 100029

收稿日期:2018-11-15 修回日期:2018-11-22 出版日期:2019-02-05 发布日期:2019-02-05
通讯作者: 韩永明
作者简介:<named-content content-type="corresp-name">耿志强</named-content>（1973—），男，博士，教授，<email>gengzhiqiang@mail.buct.edu.cn</email>|韩永明（1987—），男，博士，副教授，<email>hanym@mail.buct.edu.cn</email>
基金资助:
国家自然科学基金项目(61673046，61374166);国家重点研发计划项目(2018YFB0803501);中央高校基本科研业务费专项资金(XK1802-4)

Improved intelligent warning method based on MWSPCA-CBR and its application in petrochemical industries

Zhiqiang GENG^1,²(),Shaoxing JING^1,²,Ju BAI^1,²,Zhongkai WANG^1,²,Qunxiong ZHU^1,²,Yongming HAN^1,²()

1. College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
2. Engineering Research Center of Intelligent PSE, Ministry of Education, Beijing 100029, China

Received:2018-11-15 Revised:2018-11-22 Online:2019-02-05 Published:2019-02-05
Contact: Yongming HAN

摘要/Abstract

摘要：

石油钻井是一项高风险性、耗资巨大的系统工程。为了智能预警石油钻井过程中的异常，缩短非生产时间，降低相关风险，提出一种基于移动窗稀疏主元分析法（MWSPCA）的案例推理（CBR）异常智能预警方法（MWSPCA-CBR）。首先利用MWSPCA算法分析钻井过程中的实时数据，快速定位出异常可能发生的时间，然后使用基于案例推理方法分析异常数据，确定可能的异常类型，并为实时监控专家提供相关异常的处理方法。所提方法应用到石油钻井过程异常预警中，实验结果验证了所提方法的可行性和有效性，为钻井过程降低风险成本提供了新思路。

关键词: 主元分析, 基于案例推理, 智能预警方法, 石油钻井过程, 过程控制, 模型预测控制

Abstract:

The petroleum drilling project is a high-risk and costly system project. To effectively scan for potential problems of drilling, reduce non-productive time and lower related risks, this paper proposes an improved intelligent warning method based on moving window sparse principal component analysis (MWSPCA) integrating case-based reasoning (CBR) (MWSPCA-CBR). First, the MWSPCA is used to analyze the real-time data in the drilling process, and the time of occurrence of the anomaly is quickly located. Then the abnormal data is analyzed by using the CBR method to give possible exception types, and the associated handling methods are provided for monitoring experts. Finally, the proposed method is applied to intelligent warn abnormal problems of the petroleum drilling, the experimental results verify the feasibility and effectiveness of the proposed method and provide new ideas for reducing risks and costs during the petroleum drilling process.

Key words: principal component analysis, case-based reasoning, intelligent warning method, petroleum drilling process, process control, model-predictive control

中图分类号:

TP 29

耿志强, 景邵星, 白菊, 王仲凯, 朱群雄, 韩永明. 基于MWSPCA-CBR的智能预警方法研究及其在石化工业中的应用[J]. 化工学报, 2019, 70(2): 572-580.

Zhiqiang GENG, Shaoxing JING, Ju BAI, Zhongkai WANG, Qunxiong ZHU, Yongming HAN. Improved intelligent warning method based on MWSPCA-CBR and its application in petrochemical industries[J]. CIESC Journal, 2019, 70(2): 572-580.

图/表 9

图1 移动窗稀疏PCA的异常检测流程

Fig.1 Flow chart of anomaly detection based on MWSPCA

图2 基于MWPCA-CBR的智能化异常预警流程

Fig.2 Flow chart of intelligent warning anomaly based on MWPCA-CBR

图3 TE过程中的故障4的数据变化

Fig.3 Data changing graph of Fault 4 in TE process

图4 TE过程中的故障4的统计量检测结果

Fig.4 Statistics result of Fault 4 in TE process

表1 卡钻故障的案例描述

Table 1 Case description of pipe-sticking

名称	内容
案例时间	2014/01/10 19:25
异常名称	悬重参数异常
异常类型	工程异常
异常地层	馆陶组
异常井深	1489.21 m
异常描述	2014年1月10日19:25时正常钻进至井深1489.21 m，迟深1489.00 m。测斜后下钻过程中钻头位置到达1479.65 m时，大钩下放时悬重由正常的480 kN下降至260 kN，大钩上提时悬重由正常的480 kN上升至660 kN，出现粘卡现象。当班人员立即通知井队当班干部及工程监督。
关键词	钻进，下钻，大钩下放，大钩负荷下降，大钩上提，大钩负荷上升
异常结论	粘卡（属卡钻中的一种）

图5 钻井过程中的卡钻的数据变化

Fig.5 Data changing graph of pipe-sticking in drilling process

图6 钻井过程中的卡钻的统计量检测结果

Fig.6 Statistics result of pipe-sticking in drilling process

图7 异常时间段856～975时刻各个指标对异常的贡献度

Fig.7 Contributing degree of indices during abnormal time 856—975

表2 异常时间段与案例库中的案例相似度

Table 2 Similarity between current anomaly and cases in case base

关键词相似度	井深相似度	数据相似度	总相似度	案例名
0.82	0.76	0.86	0.49	案例1
0.82	0.51	0.85	0.45	案例9
0.77	0.55	0.85	0.44	案例8
0.82	0.45	0.87	0.44	案例4
0.82	0.45	0.86	0.44	案例5
0.77	0.46	0.87	0.43	案例2
0.77	0.57	0.75	0.42	案例7
0.77	0.46	0.75	0.40	案例3
0.82	0.45	0.69	0.40	案例6

参考文献 33

1	张正选, 梅大成, 高杰, 等. 钻井工程异常预警方法研究[J]. 计算机光盘软件与应用, 2014, 17(4): 152-152.
	ZhangZ X, MeiD C, GaoJ, et al. Research on abnormity warning method in drilling engineering [J]. Computer CD Software and Applications, 2014, 17(4): 152-152.
2	GaoF, ZhaoX H, LiuH S, et al. The study of drilling safe monitoring system based on multi agent group [C]// Advanced Materials Research. Trans. Tech. Publications, 2012, 512: 2565-2569.
3	王林. 钻井故障诊断专家系统的研究与实现[D]. 成都: 电子科技大学, 2013.
	WangL. The research and implementation of drilling fault diagnosis expert system [D]. Chengdu: University of Electronic Science and Technology of China, 2013.
4	胡睿. 钻井复杂情况与事故诊断专家系统研究[D]. 青岛: 中国石油大学(华东), 2010.
	HuR. Research on drilling complex incidents and accident diagnosis based on expert system [D].Qingdao: China University of Petroleum, 2010.
5	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.
	ZhangX H, LiQ. Risk pre-warning method of well leakage based on case reasoning [J]. Fault-Block Oil & Gas Field, 2017, 24(2): 255-258, 263.
6	徐术国. 基于录井数据的钻井事故预警专家系统[D].北京: 中国石油大学(北京), 2011.
	XuS G. Drilling accident warning expert system based on logging data [D]. Beijing: China University of Petroleum, 2011.
7	马鹏鹏, 周英操, 蒋宏伟, 等. 钻井风险控制系统关键技术[J]. 石油钻探技术, 2014, 42(3): 16-21.
	MaP P, ZhouY C, JiangH W, et al. Key technology for drilling risk control system [J]. Petroleum Drilling Techniques, 2014, 42(3): 16-21.
8	FerreiroS, SierraB, IrigoienI, et al. Data mining for quality control: Burr detection in the drilling process[J]. Computers & Industrial Engineering, 2011, 60(4): 801-810.
9	袁俊和. 钻井过程中的故障诊断方法研究[D]. 青岛: 中国石油大学(华东), 2008.
	YuanJ H. Study of fault diagnosis methods in well drilling process [D]. Qingdao: China University of Petroleum, 2008.
10	张东海, 席继强. 国外钻井技术发展现状[J]. 断块油气田, 2000, 7(5): 64-68.
	ZhangD H, XiJ Q. Development status of foreign drilling technology [J]. Fault-Block Oil & Gas Field, 2000, 7(5): 64-68.
11	RamamurthiK, ShaverD P, AgoginoA M. Real time expert system for predictive diagnostics and control of drilling operation[C]//Artificial Intelligence Applications, 1990. Sixth Conference on. IEEE, 1990: 62-69.
12	LaiZ, LengY. Weak-signal detection based on the stochastic resonance of bistable Duffing oscillator and its application in incipient fault diagnosis[J]. Mechanical Systems and Signal Processing, 2016, 81: 60-74.
13	KedadoucheM, ThomasM, TahanA. A comparative study between empirical wavelet transforms and empirical mode decomposition methods: application to bearing defect diagnosis [J]. Mechanical Systems and Signal Processing, 2016, 81: 88-107.
14	连晓圆. 钻井过程中故障检测与诊断方法的研究[D]. 大连: 大连理工大学, 2013.
	LianX Y. Fault detection and diagnosis method in drilling process[D]. Dalian: Dalian University of Technology, 2013.
15	孙正义, 高兴坤. 钻井卡钻事故预测及诊断专家系统模型的建立与实现[J]. 石油钻采工艺, 1996, 18(1): 20-23.
	SunZ Y, GaoX K. The establishment and implementation of drilling accident prediction and the model of diagnosis expert system [J]. Oil Drilling & Production Technology, 1996, 18(1): 20-23.
16	王宝毅, 张宝生, 费沿光, 等. 基于案例推理的钻井复杂情况专家系统[J]. 石油大学学报(自然科学版), 2005, 29(6): 123-126.
	WangB Y, ZhangB S, FeiY G, et al. A drilling troubles expert system based on case-based reasoning [J]. Journal of China University of Petroleum(Edition of Natural Science), 2005, 29(6): 123- 126.
17	郭建明, 李琪, 徐英卓. 基于实例和规则集成推理的钻井事故诊断处理系统[J]. 石油钻探技术, 2007, 35(3): 15-18.
	GuoJ M, LiQ, XuY Z. Drilling accident diagnosis and treatment system based on case and rule integration reasoning [J]. Petroleum Drilling Techniques, 2007, 35(3): 15-18.
18	高晓荣, 徐英卓, 李琪. 基于CBR的井下复杂情况与事故智能诊断和处理系统[J]. 计算机应用研究, 2008, (5): 1446-1449.
	GaoX R, XuY Z, LiQ. Intelligent diagnosis and processing system of complex situation in well and accident based on CBR [J]. Computer Application and Research, 2008, (5): 1446-1449.
19	郭伟伟. 基于故障树技术的远程故障诊断专家系统的研究[D]. 西安: 西北工业大学, 2007.
	GuoW W. Research on remote fault diagnosis expert system based on fault tree technology [D]. Xi an: Northwestern Polytechnical University, 2007.
20	倪绍徐, 张裕芳, 易宏, 等. 基于故障树的智能故障诊断方法[J]. 上海交通大学学报, 2008, 42(8): 1372-1375.
	NiS X, ZhangY F, YiH, et al. Intelligent fault diagnosis method based on fault tree [J]. Journal of Shanghai Jiao Tong University, 2008, 42(8): 1372-1375.
21	郭建明, 王彦平. 基于钻井工艺过程的事故诊断智能分析模型研究[J]. 西安石油大学学报(自然科学版), 2012, 27(3): 50-53.
	GuoJ M, WangY P. Research on accident diagnosis intelligent analysis model based on drilling process [J]. Journal of Xi an Petroleum University, 2012, 27(3): 50-53.
22	JolliffeI T. Principal component analysis and factor analysis [M]//Principal Component Analysis. New York: Springer, 1986: 115-128.
23	董顺, 李益国, 孙栓柱, 等. 基于状态空间主成分分析网络的故障检测方法[J]. 化工学报, 2018, 69(8): 3528-3536.
	DongS, LiY G, SunS Z, et al. Fault detection method based on state space-PCANet [J]. CIESC Journal, 2018, 69(8): 3528-3536.
24	CuiK, GaoQ, ZhangH, et al. Merging model-based two-dimensional principal component analysis[J]. Neurocomputing, 2015, 168: 1198-1206.
25	张媛媛, 韩少廷, 耿志强, 等. 自适应移动窗递推 PCA 过程监测方法研究[J]. 计算机与应用化学, 2011, (8): 1022-1026.
	ZhangY Y, HanS T, GengZ Q, et al. Study on adaptive moving window recursive principal component analysis for process monitoring [J]. Computers and Applied Chemistry, 2011, (8): 1022-1026.
26	胡云鹏. 基于主元分析的传感器故障检测盲区预测[J]. 化工学报, 2017, 68(4): 1510-1515.
	HuY P. Blind zone prediction for PCA-based sensor fault detection [J].CIESC Journal, 2017, 68(4): 1510-1515.
27	彭必灿, 张正道. 基于稀疏主元分析的过程监控研究[J]. 计算机工程与应用, 2014, (18): 240-245.
	PengB C, ZhangZ D. Process monitoring research based on sparse principal component analysis [J]. Computer Engineering and Applications, 2014, (18): 240-245.
28	赵忠盖, 刘飞. 基于稀疏核主元分析的在线非线性过程监控[J]. 化工学报, 2008, 59(7): 1773-1777.
	ZhaoZ G, LiuF. Online nonlinear process monitoring based on sparse kernel principal component analysis [J]. Journal of Chemical Industry and Engineering(China), 2008, 59(7): 1773-1777.
29	ZassR, ShashuaA. Nonnegative sparse PCA [C]// Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems. Vancouver, British Columbia, Canada, 2006.
30	阮跃. 基于案例, 规则和模型推理的电站智能诊断系统[J]. 电站系统工程, 1998, 14(3): 45-47.
	RuanY. Intelligent diagnosis system of power plant based on case, rule and inferential model [J]. Power System Engineering, 1998, 14(3): 45-47.
31	张琦, 孙劭文, 李文鸿, 等. 基于案例推理的机械故障诊断方法探讨[J]. 解放军理工大学学报(自然科学版), 2004, 5(5): 42-45.
	ZhangQ, SunS W, LiW H, et al. Case-based reasoning for mechanical fault diagnosis [J]. Journal of PLA University of Science and Technology (Natural Science Edition), 2004, 5(5): 42-45.
32	李亚宁, 王学雷, 谭杰. 基于 PCR-多案例融合的焦化烟气脱硝过程指标优化设定[J]. 化工学报, 2018, 69(3): 998-1007.
	LiY N, WangX L, TanJ. PCR-multi-case fusion method for setting optimal process indices of coking flue gas denitration [J]. CIESC Journal, 2018, 69(3): 998-1007.
33	柳玉, 贲可荣. 案例推理的故障诊断技术研究综述[J].计算机科学与探索, 2011, 5(10): 865-879.
	LiuY, BenK R. Survey of fault diagnosis based on case reasoning [J]. Journal of Frontiers of Computer Science and Technology, 2011, 5(10): 865-879.

[1]	曹跃, 余冲, 李智, 杨明磊. 工业数据驱动的加氢裂化装置多工况切换过渡状态检测[J]. 化工学报, 2023, 74(9): 3841-3854.
[2]	康飞, 吕伟光, 巨锋, 孙峙. 废锂离子电池放电路径与评价研究[J]. 化工学报, 2023, 74(9): 3903-3911.
[3]	王光, 单发顺, 钱禹丞, 焦建芳. 基于集成学习传递熵的化工过程微小故障检测方法[J]. 化工学报, 2023, 74(7): 2967-2978.
[4]	苏晓丹, 朱干宇, 李会泉, 郑光明, 孟子衡, 李防, 杨云瑞, 习本军, 崔玉. 湿法磷酸半水工艺考察与石膏结晶过程研究[J]. 化工学报, 2023, 74(4): 1805-1817.
[5]	张中秋, 李宏光, 石逸林. 基于人工预测调控策略的复杂化工过程多任务学习方法[J]. 化工学报, 2023, 74(3): 1195-1204.
[6]	张江淮, 赵众. 碳三加氢装置鲁棒最小协方差约束控制及应用[J]. 化工学报, 2023, 74(3): 1216-1227.
[7]	赵涛岩, 曹江涛, 李平, 冯琳, 商瑀. 区间二型模糊免疫PID在环己烷无催化氧化温度控制系统中的应用[J]. 化工学报, 2022, 73(7): 3166-3173.
[8]	周乐, 沈程凯, 吴超, 侯北平, 宋执环. 深度融合特征提取网络及其在化工过程软测量中的应用[J]. 化工学报, 2022, 73(7): 3156-3165.
[9]	王琨, 侍洪波, 谭帅, 宋冰, 陶阳. 局部时差约束邻域保持嵌入算法在故障检测中的应用[J]. 化工学报, 2022, 73(7): 3109-3119.
[10]	王建松, 许锋, 罗雄麟. 化工过程多回路PID控制系统模式切换参数自整定[J]. 化工学报, 2022, 73(4): 1647-1657.
[11]	刘立邦, 杨颂, 王志坚, 贺欣欣, 赵文磊, 刘守军, 杜文广, 米杰. 基于改进WOA-LSTM的焦炭质量预测[J]. 化工学报, 2022, 73(3): 1291-1299.
[12]	张成, 潘立志, 李元. 基于加权统计特征KICA的故障检测与诊断方法[J]. 化工学报, 2022, 73(2): 827-837.
[13]	张兴硕, 罗雄麟, 许锋. 催化裂化装置反再系统动态模拟精细化与控制系统“工艺优先”配对设计[J]. 化工学报, 2022, 73(2): 747-758.
[14]	卢道铭, 唐钊艇, 范怡平, 卢春喜. 大差异颗粒分级再生设备的性能研究[J]. 化工学报, 2021, 72(8): 4184-4195.
[15]	李元, 杨东昇, 赵丽颖, 张成. 层次变分高斯混合模型与主多项式分析的故障检测策略[J]. 化工学报, 2021, 72(3): 1616-1626.

基于MWSPCA-CBR的智能预警方法研究及其在石化工业中的应用

Improved intelligent warning method based on MWSPCA-CBR and its application in petrochemical industries

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 33

相关文章 15

编辑推荐

Metrics

本文评价