PDF下载

[1]徐磊,侯磊,李雨,等.机器学习在油气管道的应用研究进展及展望[J].油气储运,2021,40(02):138-145.[doi:10.6047/j.issn.1000-8241.2021.02.003]
　XU Lei,HOU Lei,LI Yu,et al.Research progress and prospect of application of machine learning in oil and gas pipeline[J].Oil & Gas Storage and Transportation,2021,40(02):138-145.[doi:10.6047/j.issn.1000-8241.2021.02.003]

点击复制

机器学习在油气管道的应用研究进展及展望

《油气储运》[ISSN:1000-8241/CN:13-1093/TE] 卷: 40 期数: 2021年02期页码: 138-145 栏目: 出版日期: 2021-03-03

Title:: Research progress and prospect of application of machine learning in oil and gas pipeline

文章编号:: 1000-8241（2021）02-0138-08

作者:: 徐磊; 侯磊; 李雨; 朱振宇; 雷婷; 中国石油大学（北京）机械与储运工程学院·油气管道输送安全国家工程实验室·石油工程教育部重点实验室;

Author(s):: XU Lei; HOU Lei; LI Yu; ZHU Zhenyu; LEI Ting; College of Mechanical and Transportation Engineering, China University of Petroleum (Beijing)//National Engineering Laboratory for Pipeline Safety//MOE Key Laboratory of Petroleum Engineering

关键词:: 机器学习; 人工智能; 预测模型; 决策支持; 油气管道系统

Keywords:: machine learning; AI; prediction model; decision support; oil and gas pipeline system

分类号:: TE832

DOI:: 10.6047/j.issn.1000-8241.2021.02.003

文献标志码:: A

摘要:: 机器学习作为实现人工智能的主要手段，通过探索数据规律、建立预测模型来指导决策支持。在目前油气管道系统设备繁多、结构复杂、技术庞杂等背景下，引入机器学习是为了采用人工智能技术解决单纯依靠数学模型难以应对的问题，代替人工从事一些枯燥繁琐、危险程度较高的工作。结合油气管道系统各生产环节，重点阐述了深度学习、强化学习及迁移学习3类机器学习方法的应用研究进展，包括油气管道泄漏、多相流型识别、设备故障诊断及储罐目标检测等应用场景，构建了人工智能技术在油气管道系统的应用框架，指出深度学习、强化学习及迁移学习在该领域拥有较强的应用前景。最后，对机器学习在油气管道领域的应用进行了展望，以期为油气管道系统的智能化研究与发展提供参考。（图1，参43）

Abstract:: Machine learning is a major means to realize artificial intelligence (AI), which can provide support for decision making through exploration of data law and establishment of prediction model. Since the oil and gas pipeline system has the characteristics of numerous equipment, complicated structure and complex technology, machine learning is introduced to solve the problems that are hard to solve with pure mathematical models with AI technology and to replace personnel to complete some boring, tedious and dangerous tasks. Here, the application of 3 types of machine leaning, such as deep learning, reinforcement learning and transfer learning, were reviewed with reference to the production process of oil and gas pipeline system, covering the application scenarios like pipeline leakage, recognition of multi-phase flow pattern, equipment fault diagnosis and tank target detection. The application framework of AI technology in oil and gas pipeline systems was established, and it was also pointed out that the application of deep learning, reinforcement learning and transfer learning in this field was prospective. Finally, the application of machine learning in oil and gas pipelines was prospected, so as to provide references for the intelligent research and development of oil and gas pipeline systems. (1 Figure, 43 References)

参考文献/References:

[1] 中华人民共和国国务院.新一代人工智能发展规划[EB/OL].（2017-07-20）[2018-06-20]. http：//www.gov.cn/zhengce/content/2017-07/20/content_5211996.htm. State Council of the People’s Republic of China. Development plan of the new generation artificial intelligence[EB/OL]. (2017-07-20) [2018-06-20]. http://www.gov.cn/zhengce/content/2017-07/20/content_5211996.htm.
[2] 薛禹胜，赖业宁.大能源思维与大数据思维的融合（一）大数据与电力大数据[J].电力系统自动化，2016，40（1）：1-8. XUE Y S, LAI Y N. Integration of macro energy thinking and Big Data thinking (Ⅰ) Big Data and power Big Data[J]. Automation of Electric Power Systems, 2016, 40(1): 1-8.
[3] 李根生，宋先知，田守嶒.智能钻井技术研究现状及发展趋势[J].石油钻探技术，2020，48（1）：1-8. LI G S, SONG X Z, TIAN S C. Intelligent drilling technology research status and development trends[J]. Petroleum Drilling Techniques, 2020, 48(1): 1-8.
[4] 林伯韬，郭建成.人工智能在石油工业中的应用现状探讨[J].石油科学通报，2019，4（4）：403-413. LIN B T, GUO J C. Discussion on current application of artificial intelligence in petroleum industry[J]. Petroleum Science Bulletin, 2019, 4(4): 403-413.
[5] 杨平，詹仕凡，李明，李磊，郭锐，尚民强，等.基于梦想云的人工智能地震解释模式研究与实践[J].中国石油勘探，2020，25（5）：89-96. YANG P, ZHAN S F, LI M, LI L, GUO R, SHANG M Q, et al. Research and practice on artificial intelligence seismic interpretation mode based on E & P Dream Cloud[J]. China Petroleum Exploration, 2020, 25(5): 89-96.
[6] 国家发展改革委，国家能源局.中长期油气管网规划[EB/OL].（2017-05-19）[2018-06-20]. http：//www.gov.cn/xinwen/2017-07/12/content_5209925.htm. National Development and Reform Commission, National Energy Administration. Medium and long-term planning of oil and gas pipeline network[EB/OL]. (2017-05-19)[2018-06-20]. http://www.gov.cn/xinwen/2017-07/12/content_5209925.htm.
[7] 吴长春，左丽丽.关于中国智慧管道发展的认识与思考[J].油气储运，2020，39（4）：361-370. WU C C, ZUO L L. Understanding and thinking on the development of China’s intelligent pipeline[J]. Oil & Gas Storage and Transportation, 2020, 39(4): 361-370.
[8] 王振声，陈朋超，王巨洪.中俄东线天然气管道智能化关键技术创新与思考[J].油气储运，2020，39（7）：730-739. WANG Z S, CHEN P C, WANG J H. Key technological innovations and thinking of pipeline intelligence in China-Russia Eastern Gas Pipeline[J]. Oil & Gas Storage and Transportation, 2020, 39(7): 730-739.
[9] 姜昌亮.中俄东线天然气管道工程管理与技术创新[J].油气储运，2020，39（2）：121-129. JIANG C L. Management and technological innovation in China-Russia Eastern Gas Pipeline Project[J]. Oil & Gas Storage and Transportation, 2020, 39(2): 121-129.
[10] 宫敬，徐波，张微波.中俄东线智能化工艺运行基础与实现的思考[J].油气储运，2020，39（2）：130-139. GONG J, XU B, ZHANG W B. Thinking on the basis and realization of intelligent process operation of China-Russia Eastern Gas Pipeline[J]. Oil & Gas Storage and Transportation, 2020, 39(2): 130-139.
[11] 李阳，廉培庆，薛兆杰，戴城.大数据及人工智能在油气田开发中的应用现状及展望[J].中国石油大学学报（自然科学版）， 2020，44（4）：1-11. LI Y, LIAN P Q, XUE Z J, DAI C. Application status and prospect of Big Data and artificial intelligence in oil and gas field development[J]. Journal of China University of Petroleum (Edition of Natural Science), 2020, 44(4): 1-11.
[12] 高鹏，高振宇，刘广仁. 2019年中国油气管道建设新进展[J].国际石油经济，2020，28（3）：52-58. GAO P, GAO Z Y, LIU G R. New progress in China’s oil and gas pipeline construction in 2019[J]. International Petroleum Economics, 2020, 28(3): 52-58.
[13] 周志华.机器学习[M].北京：清华大学出版社，2016：10-13. ZHOU Z H. Machine learning[M]. Beijing: Tsinghua University Press, 2016: 10-13.
[14] 王金甲，陈浩，刘青玉.大数据下的深度学习研究[J].高技术通讯，2017，27（1）：27-37. WANG J J, CHEN H, LIU Q Y. The study of deep learning under Big Data[J]. Chinese High Technology Letters, 2017, 27(1): 27-37.
[15] 周念成，廖建权，王强钢，李春艳，李剑.深度学习在智能电网中的应用现状分析与展望[J].电力系统自动化，2019，43（4）：180-191. ZHOU N C, LIAO J Q, WANG Q G, LI C Y, LI J. Analysis and prospect of deep learning application in smart grid[J]. Automation of Electric Power Systems, 2019, 43(4): 180-191.
[16] KOBER J, BAGNELL J A, PETERS J. Reinforcement learning in robotics：a survey[J]. International Journal of Robotics Research, 2013, 32(11): 1238-1274.
[17] NAHUM-SHANI I, QIAN M, ALMIRALL D, PELHAM W, GNAGY B, FABIANO G A, et al. Q-learning: a data analysis method for constructing adaptive interventions[J]. Psychological Methods, 2012, 17(4): 478-494.
[18] VELUSAMY B, ANOUNCIA S M, ABRAHAM G. SaGe framework-mapping of SARSA to adaptive e-learning using learning styles[J]. International Technology Journal, 2013, 12(12): 2306-2314.
[19] 孟创纪.基于特征映射的深度迁移学习研究[D].兰州：兰州大学，2019：1-8. MENG C J. Research on deep transfer learning based on feature mapping[D]. Lanzhou: Lanzhou University, 2019: 1-8.
[20] FENG J, LI F M, LU S X, LIU J H, MA D Z. Injurious or noninjurious defect identification from MFL images in pipeline inspection using convolutional neural network[J]. IEEE Transactions on Instrumentation and Measurement, 2017, 66(7):1883-1892.
[21] 岳明星，杨理践，石萌.基于卷积神经网络的管道漏磁内检测焊缝识别方法[J].电子世界，2018（12）：49-50. YUE M X, YANG L J, SHI M. A method based on convolutional neural network for weld seam identification in pipeline magnetic flux leakage[J]. Electronics World, 2018(12):49-50.
[22] 樊旭然.基于卷积神经网络的压缩机缺陷检测方法的研究[D].广州：广州大学，2019：25-43. FAN X R. Research on compressor defect detection method based on convolutional neural network[D]. Guangzhou:Guangzhou University, 2019: 25-43.
[23] HU X G, ZHANG H G, MA D Z, WANG R. Status detection from spatial-temporal data in pipeline network using data transformation convolutional neural network[J]. Neurocomputing, 2019, 358(17): 401-413.
[24] 宁方立，韩鹏程，段爽，李航，韦娟.基于改进CNN的阀门泄漏超声信号识别方法[J].北京邮电大学学报，2020，43（3）：38-44. NING F L, HAN P C, DUAN S, LI H, WEI J. Identification method of valve leakage ultrasonic signal based on improved CNN[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(3): 38-44.
[25] 曹广华，宛立达，袁子龙，金树波.基于递归神经网络的游梁式抽油机振动故障诊断[J].长江大学学报（自然科学版），2010， 7（1）：57-59. CAO G H, WAN L D, YUAN Z L, JIN S B. Vibration fault diagnosis of beam pumping unit based on recurrent neural network[J]. Journal of Yangtze University (Natural Science Edition), 2010, 7(1): 57-59.
[26] 李少鹏.结合CNN和LSTM的滚动轴承剩余使用寿命预测方法研究[D].哈尔滨：哈尔滨理工大学，2019：17-29. LI S P. Research on remaining useful Life prediction method of a rolling bearing combination CNN and LSTM[D]. Harbin:Harbin University of Science and Technology, 2019: 17-29.
[27] SU H, ZIO E, ZHANG J J, CHI L X, LI X Y, ZHANG Z J. A systematic data-driven demand side management method for smart natural gas supply systems[J]. Energy Conversion and Management, 2019, 185: 368-383.
[28] XU P, DU R, ZHANG Z B. Predicting pipeline leakage in petrochemical system through GAN and LSTM[J]. Knowledge-Based Systems, 2019, 175: 50-61.
[29] ZHOU D J, HUANG D W, HAO J R, REN Y L, JIANG P, JIA X Y. Vibration-based fault diagnosis of the natural gas compressor using adaptive stochastic resonance realized by generative adversarial networks[J]. Engineering Failure Analysis, 2020, 116: 104759.
[30] 郭越，王晓峰，张恒振.基于人类感知的SAR图像海上溢油检测算法[J].武汉大学学报（信息科学版），2016，41（3）：395-401，407. GUO Y, WANG X F, ZHANG H Z. Oil spill detection by SAR images based on human perception[J]. Geomatics and Information Science of Wuhan University, 2016, 41(3):395-401, 407.
[31] 郎宪明.基于特征提取与信息融合的管道泄漏检测与定位研究[D].西安：西北工业大学，2018：51-69. LANG X M. Pipeline leak detection and localization based on feature extraction and information fusion[D]. Xi'an:Northwestern Polytechnical University, 2018: 51-69.
[32] 李颖.往复压缩机滑动轴承间隙复合故障诊断方法研究[D].大庆：东北石油大学，2019：33-56. LI Y. Research on fault diagnosis for sliding bearing clearance of reciprocating compressor with compound faults[D]. Daqing:Northeast Petroleum University, 2019: 33-56.
[33] 李晴晴，侯瑞春，丁香乾.基于改进堆叠自编码器的滚动轴承故障诊断[J].计算机工程与设计，2019，40（7）：2064-2070. LI Q Q, HOU R C, DING X Q. Roller bearing fault diagnosis based on improved stacked auto-encoder[J]. Computer Engineering and Design, 2019, 40(7): 2064-2070.
[34] 王新颖，宋兴帅，杨泰旺.深度学习神经网络在管道故障诊断中的应用研究[J].安全与环境工程，2018，25（1）：137-142，148. WANG X Y, SONG X S, YANG T W. Application of depth learning neural network in pipeline fault diagnosis[J]. Safety and Environmental Engineering, 2018, 25(1): 137-142, 148.
[35] 李器宇，张拯宁，柳建斌，郭峰，李明.无人机遥感在油气管道巡检中的应用[J].红外，2014，35（3）：37-42. LI Q Y, ZHANG Z N, LIU J B, GUO F, LI M. Application of UAV remote sensing in oil and gas pipeline inspection[J]. Infrared, 2014, 35(3): 37-42.
[36] 李朝阳.高分辨率遥感图像油库检测及提取[D].上海：上海交通大学，2017：9-17. LI Z Y. The oil depot detection and extraction from high resolution remote sensing images[D]. Shanghai: Shanghai Jiao Tong University, 2017: 9-17.
[37] LIN Z, LIU X L, LAO L Y, LIU H X. Prediction of two-phase flow patterns in upward inclined pipes via deep learning[J]. Energy, 2020, 210: 118541.
[38] 郑秋梅，商振浩，王风华，林超.基于深度神经网络和支持向量机的海底管线水合物生成预测模型[J].中国石油大学学报（自然科学版），2020，44（5）：46-51. ZHENG Q M, SHANG Z H, WANG F H, LIN C. Prediction model of submarine pipeline hydrate formation based on deep neural network and support vector machines[J]. Journal of China University of Petroleum (Edition of Natural Science), 2020, 44(5): 46-51.
[39] 王忠巍.自主海底管道机器人智能控制关键技术研究[D].上海：上海交通大学，2010：69-90. WANG Z W. Research on key technology of intelligent control for autonomous subsea in-pipe robot[D]. Shanghai: Shanghai Jiao Tong University, 2010: 69-90.
[40] WU Q, ZHU D, LIU Y, DU A, CHEN D, YE Z H. Comprehensive control system for gathering pipe network operation based on reinforcement learning[C]. Taipei: 2018 VII International Conference on Network， Communication and Computing, 2018: 34-39.
[41] HOURFAR F， BIDGOLY H J， MOSHIRI B， SALAHSHOOR K， ELKAMEL A. A reinforcement learning approach for waterflooding optimization in petroleum reservoirs[J]. Engineering Applications of Artificial Intelligence, 2019, 77: 98-116.
[42] 黄祖浩.基于深度强化学习的车用液化天然气自动加注系统研究[D].广州：广东工业大学，2019：21-40. HUANG Z H. Research on automated filling system of vehicle liquefied natural gas based on deep reinforcement learning[D]. Guangzhou: Guangdong University of Technology, 2019: 21-40.
[43] PAN S J, YANG Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10):1345-1359.

相似文献/References:

[1]张海峰,蔡永军,李柏松,等.智慧管道站场设备状态监测关键技术[J].油气储运,2018,37(8):841.[doi:10.6047/j.issn.1000-8241.2018.08.001]
　ZHANG Haifeng,CAI Yongjun,LI Baisong,et al.Key technologies of equipment condition monitoring at the station of intelligent pipeline[J].Oil & Gas Storage and Transportation,2018,37(02):841.[doi:10.6047/j.issn.1000-8241.2018.08.001]
[2]蔡永军　蒋红艳　王继方　王潇潇　李莉　陈国群　张海峰.智能化管道建设关键技术研究进展[J].油气储运,2018,37(预出版):1.
　CAI Yongjun,JIANG Hongyan,WANG Jifang,et al.Research progress on key construction technologies of intelligent pipelines[J].Oil & Gas Storage and Transportation,2018,37(02):1.
[3]蔡永军,蒋红艳,王继方,等.智慧管道总体架构设计及关键技术[J].油气储运,2019,38(02):121.[doi:10.6047/j.issn.1000-8241.2019.02.001]
　CAI Yongjun,JIANG Hongyan,WANG Jifang,et al.The overall architecture design and key construction technologies of intelligent pipelines[J].Oil & Gas Storage and Transportation,2019,38(02):121.[doi:10.6047/j.issn.1000-8241.2019.02.001]
[4]唐善华,杨毅,张麟,等.天然气管网智能调控初探[J].油气储运,2021,40(09):991.[doi:10.6047/j.issn.1000-8241.2021.09.004]
　TANG Shanhua,YANG Yi,ZHANG Lin,et al.Preliminary study on intelligent control of natural gas pipeline networks[J].Oil & Gas Storage and Transportation,2021,40(02):991.[doi:10.6047/j.issn.1000-8241.2021.09.004]
[5]张鑫儒,侯磊,徐磊,等.仿真与DBSCAN算法融合的管输数据生成与验证方法[J].油气储运,2022,41(02):146.[doi:10.6047/j.issn.1000-8241.2022.02.003]
　ZHANG Xinru,HOU Lei,XU Lei,et al.Generation and verification method of pipeline transportation data based on integration of simulation and DBSCAN algorithm[J].Oil & Gas Storage and Transportation,2022,41(02):146.[doi:10.6047/j.issn.1000-8241.2022.02.003]

备注/Memo

徐磊，男，1990年生，在读博士生，2017年硕士毕业于长江大学油气储运工程专业，现主要从事大数据和机器学习在油气管道系统的应用研究工作。地址：北京市昌平区府学路18号， 102249。电话：18810062565。Email：18810062565@163.com通信作者：侯磊，男，1966年生，教授，博士生导师，2006年博士毕业于中国石油大学（北京）油气储运工程专业，现主要从事油气管道输送与油气田集输相关技术的研究工作。地址：北京市昌平区府学路18号，102249。电话：13810368969。Email：houleicup@126.com
（收稿日期：2020-11-19；修回日期：2020-12-28；编辑：刘朝阳）

更新日期/Last Update: 2021-03-03