Active Learning Method for Abnormal Operating Conditions of Natural Gas Gathering System

doi:10.11885/j.issn.1674-5086.2020.05.12.08

Abstract

Abstract: Various abnormal operating conditions in natural gas gathering system pose a threat to safe production. This paper proposes an intelligent processing system model for abnormal operating conditions. The abnormal operating conditions classification prediction module of the model adopts the active learning method, which can classify the abnormal type in real time and accurately, and provide a basis for the system to recommend appropriate processing schemes to experts. Firstly, use the SCADA system to monitor data in real time and perform abnormal conditions warning. Secondly, we use the active learning algorithm to classify the early warning of abnormal operating conditions. The classification results provide support for constructing the abnormal working condition inference engine, and then implement intelligent decision-making assistance. The experimental results show that the proposed method can save the cost of experts, identify the types of abnormal operating conditions, and propose a reasonable solution.

Key words: active learning, classification, abnormal operating conditions, natural gas gathering system, artificial intelligence, expert system

CLC Number:

TE863

FANG Yu, CAO Xuemei, LI Binqian, MIN Fan, QIAO Ying. Active Learning Method for Abnormal Operating Conditions of Natural Gas Gathering System[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2020, 42(6): 124-132.

0
/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: http://journal15.magtechjournal.com/Jwk_xnzk/EN/10.11885/j.issn.1674-5086.2020.05.12.08

http://journal15.magtechjournal.com/Jwk_xnzk/EN/Y2020/V42/I6/124

References

[1] 孟令雅,刘翠伟,刘超,等. 基于特征量提取的输气管道微泄漏检测[J]. 中国石油大学学报(自然科学版), 2014, 38(6):153-160. doi:10.3969/j.issn.1673-5005.2014.06.023 MENG Lingya, LIU Cuiwei, LIU Chao, et al. Characteristics extraction of acoustic leakage signal for natural gas pipelines[J]. Journal of China University of Petroleum (Edition of Natural Science), 2014, 38(6):153-160. doi:10.3969/j.issn.1673-5005.2014.06.023
[2] 张卫兵,杜明俊,佟倡,等. 基于声波法的输气管道泄漏检测技术研究[J]. 化学工程与装备, 2018(1):246-248, 259. doi:10.19566/j.cnki.cn35-1285/tq.2018.01.085 ZHANG Weibing, DU Mingjun, TONG Chang, et al. Research on gas pipeline leak detection technology based on acoustic wave method[J]. Chemical Engineering & Equipment, 2018(1):246-248, 259. doi:10.19566/j.cnki.cn35-1285/tq.2018.01.085
[3] 张子涛,殷存志,杨毅,等. 气田集气站安全监测数据异常值识别研究[J]. 油气田地面工程, 2015, 34(10):7-9. doi:10.3969/j.issn.1006-6896.2015.10.001 ZHANG Zitao, YIN Cunzhi, YANG Yi, et al. Research on abnormal value identification of safety monitoring data in gas field gas station[J]. Oil-Gasfield Surface Engineering, 2015, 34(10):7-9. doi:10.3969/j.issn.1006-6896.2015.10.001
[4] 胡瑾秋,郭放,张来斌. 基于趋势分析的间歇过程异常工况超早期报警研究[J]. 石油学报(石油加工), 2018, 34(1):101-107. doi:10.3969/j.issn.1001-8719.2018.01.014 HU Jinqiu, GUO Fang, ZHANG Laibin. Study on abnormal situation ultra-early warning of batch process based on trend analysis[J]. Acta Petrolei Sinica (Petroleum Processing Section), 2018, 34(1):101-107. doi:10.3969/j.issn.1001-8719.2018.01.014
[5] 李悦,王建伟. 天然气管道振动原因分析及应对措施[J]. 清洗世界, 2019, 35(1):24-25. doi:10.3969/j.issn.1671-8909.2019.01.009 LI Yue, WANG Jianwei. Cause analysis and countermeasures for vibration of natural gas pipeline[J]. Cleaning World, 2019, 35(1):24-25. doi:10.3969/j.issn.1671-8909.2019.01.009
[6] 刘恩斌,匡建超,吕留新,等. 大型天然气管道稳态运行优化研究[J]. 西南石油大学学报(自然科学版), 2019, 41(5):150-160. doi:10.11885/j.issn.1674-5086.2018.12.12.01 LIU Enbin, KUANG Jianchao, LÜ Liuxin, et al. Optimization of steady operation of large scale natural gas pipelines[J]. Journal of Southwest Petroleum University (Science & Technology Edition), 2019, 41(5):150-160. doi:10.11885/j.issn.1674-5086.2018.12.12.01
[7] 张继燕,欧莹元,张起荣. 基于实时数据库的油气处理故障诊断系统[J]. 油气田地面工程, 2015, 34(3):33-35. doi:10.3969/j.issn.1006-6896.2015.3.018. ZHANG Jiyan, OU Yingyuan, ZHANG Qirong. Oil and gas processing fault diagnosis system based on realtime database[J]. Oil-Gasfield Surface Engineering, 2015, 34(3):33-35. doi:10.3969/j.issn.1006-6896.2015.3.018.
[8] 陈敬龙,赵江平,席晨睿. 基于自适应支持向量回归机的集输系统压力监测异常值识别[J]. 油气田地面工程, 2017, 36(2):6-9. doi:10.3969/j.issn.1006-6896.2017.2.002 CHEN Jinglong, ZHAO Jiangping, XI Chenrui. Anomaly detection in pressure monitoring data of natural gas gathering system based on adaptive support vector regression[J]. Oil-Gasfield Surface Engineering, 2017, 36(2):6-9. doi:10.3969/j.issn.1006-6896.2017.2.002
[9] 吴高昌,刘强,柴天佑,等. 基于时序图像深度学习的电熔镁炉异常工况诊断[J]. 自动化学报, 2019, 45(8):1475-1485. doi:10.16383/j.aas.c180453 WU Gaochang, LIU Qiang, CHAI Tianyou, et al. Abnormal condition diagnosis through deep learning of image sequences for fused magnesium furnaces[J]. Acta Automatica Sinica, 2019, 45(8):1475-1485. doi:10.16383/j.aas.c180453
[10] 涂思羽,彭平安,蒋元建. 基于深度学习的井下环境异常工况智能识别技术研究[J]. 中国安全生产科学技术, 2018, 14(11):60-65. doi:10.11731/j.issn.1673-193x.2018.11.009 TU Siyu, PENG Pingan, JIANG Yuanjian. Research on intelligent recognition technology of abnormal operating conditions in underground environment based on deep learning method[J]. Journal of Safety Science and Technology, 2018, 14(11):60-65. doi:10.11731/j.issn.1673-193x.2018.11.009
[11] 华丽,于海晨,邵诚,等. 基于SVM-BOXPLOT的乙烯生产过程异常工况监测与诊断[J]. 化工学报,2018,69(3):1053-1063. doi:10.11949/j.issn.0438-1157.20170907 HUA Li, YU Haichen, SHAO Cheng, et al. Monitoring and diagnosis of abnormal condition in ethylene production process based on SVM-BOXPLOT[J]. CIESC Journal, 2018, 69(3):1053-1063. doi:10.11949/j.issn.0438-1157.20170907
[12] 贾桥龙,朱景贺,余睿宏. 浅析天然气集输系统管理与维修[J]. 当代化工研究, 2017(3):157-158. doi:10.3969/j.issn.1672-8114.2017.03.089 JIA Qiaolong, ZHU Jinghe, YU Ruihong. Analysis of the management and maintenance for natural gas gathering and transportation[J]. Modern Chemical Research, 2017(3):157-158. doi:10.3969/j.issn.1672-8114.2017.03.089
[13] 张翔,仝心,王鼎玺. 天然气集输系统数字化分析[J]. 中国化工贸易, 2019, 11(6):13. ZHANG Xiang, TONG Xin, WANG Dingxi. Digital analysis of natural gas gathering and transportation system[J]. China Chemical Trade, 2019, 11(6):13.
[14] HUANG Shenjun, RONG Jin, ZHOU Zhihua. Active learning by querying informative and representative examples[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(10):1936. doi:10.1109/TPAMI.2014.2307881
[15] 柳锡淼. 天然气长输管网SCADA系统的应用及其优化[J]. 石油工程建设, 2011, 37(1):31-33. doi:10.3969/j.issn.1001-2206.2011.01.008 LIU Ximiao. SCADA system application and optimization for long-distance natural gas pipeline[J]. Petroleum Engineering Construction, 2011, 37(1):31-33. doi:10.3969/j.issn.1001-2206.2011.01.008
[16] 何婷婷. 基于案例推理的焦炉加热过程异常工况智能预报系统研究[D]. 武汉:武汉科技大学, 2010. HE Tingting. Digitalization of natural gas gathering and transportation system[J]. Wuhan:Wuhan University of Science and Technology, 2010.
[17] WU Yanxue, MIN Xueyang, MIN Fan, et al. Costsensitive active learning with a label uniform distribution model[J]. International Journal of Approximate Reasoning, 2019, 105:49-65. doi:10.1016/j.ijar.2018.11.004
[18] 李健,赖平. 埋地管道典型异常事件信号特征提取方法研究[J]. 传感技术学报, 2010, 23(7):74-78. doi:10.3969/j.issn.1004-1699.2010.07.016 LI Jian, LAI Ping. Study on feature extraction method for typical abnormal events of buried pipelines[J]. Chinese Journal of Sensors and Actuators, 2010, 23(7):74-78. doi:10.3969/j.issn.1004-1699.2010.07.016
[19] 周志华. 机器学习[M]. 北京:清华大学出版社, 2016. ZHOU Zhihua. Machine learning[M]. Beijing:Tsinghua University Press, 2016.
[20] 王志娟,刘飞飞,赵小兵,等. 基于置信度的藏文人名识别的主动学习模型研究[J]. 中文信息学报, 2019, 33(8):53-59. doi:10.3969/j.issn.1003-0077.2019.08.007 WANG Zhijuan, LIU Feifei, ZHAO Xiaobing, et al. Confidence based active learning model for tibetan person name recognition[J]. Journal of Chinese Information Processing, 2019, 33(8):53-59. doi:10.3969/j.issn.1003-0077.2019.08.007
[21] HUANG Ruizhang, LAM Wai. An active learning framework for semi-supervised document clustering with language modeling[J]. Data & Knowledge Engineering, 2009, 68(1):49-67. doi:10.1016/j.datak.2008.08.008
[22] DEMIR B, MINELLO L, BRUZZONE L. A cost-sensitive active learning technique for the definition of effective training sets for supervised classifiers[C]. Munich, Germany:IEEE International Geoscience and Remote Sensing Symposium, 2012. doi:10.1109/IGARSS.2012.6351169
[23] WANG Min, ZHANG Yingyi, MIN Fan. Active learning through multi-standard optimization[J]. IEEE Access, 2019, 7:56772-56784.
[24] RODRIGUEZ A, LAIO A. Clustering by fast search and find of density peaks[J]. Science, 2014, 344(6191):1492-1496. doi:10.1126/science.1242072
[25] WANG Min, MIN Fan, ZHANG Zhiheng, et al. Active learning through density clustering[J]. Expert Systems with Applications, 2017, 85(5):305-317. doi:10.1016/j.eswa.2017.05.046
[26] BLAKE C, MERZ C J. UCI repository of machine learning databases[C]. Oakland:University of California, 1998.
[27] HAN J W, KAMBER M. Data mining concept and techniques[M]. Amsterdam, The Netherlands:Elsevier, 2001.
[28] XIANG Zhuoyuan, ZHANG Lei. Research on an optimized C4.5 algorithm based on rough set theory[C]. Management of e-Commerce and e-Government (ICMeCG), 2012. doi:10.1109/ICMeCG.2012.74
[29] QUINLAN J R. Bagging, boosting, and C4.5[C]. AAAI, 1996:725-730.
[30] RUAN Yuxun, LIN Hsuantien, TSAI Mingfeng. Improving ranking performance with cost-sensitive ordinal classification via regression[J]. Information Retrieval, 2014, 17(1):1-20. doi:10.1007/s10791-013-9219-2
[31] LIAW A, WIENER M. Classification and regression by random forest[J]. R News, 2002, 2/3:18-22.
[32] CAI Yudong, FENG Kaiyan, LU Wencong, et al. Using logit boost classifier to predict protein structural classes[J]. Journal of Theoretical Biology, 2006, 238(1):172-176. doi:10.1016/j.jtbi.2005.05.034