[1]马云路,郑坚钦,梁永图.基于特征提取的输油管道泄漏系数预测*[J].中国安全生产科学技术,2022,18(10):130-135.[doi:10.11731/j.issn.1673-193x.2022.10.019]
MA Yunlu,ZHENG Jianqin,LIANG Yongtu.Prediction on leakage coefficient of oil pipeline based on feature extraction[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(10):130-135.[doi:10.11731/j.issn.1673-193x.2022.10.019]
点击复制
基于特征提取的输油管道泄漏系数预测*
MA Yunlu,ZHENG Jianqin,LIANG Yongtu.Prediction on leakage coefficient of oil pipeline based on feature extraction[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(10):130-135.[doi:10.11731/j.issn.1673-193x.2022.10.019]
《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]
- 卷:
- 18
- 期数:
- 2022年10期
- 页码:
- 130-135
- 栏目:
- 职业安全卫生管理与技术
- 出版日期:
- 2022-10-31
文章信息/Info
- Title:
- Prediction on leakage coefficient of oil pipeline based on feature extraction
- 文章编号:
- 1673-193X(2022)-10-0130-06
- Keywords:
- pipeline leakage detection; feature extraction; machine learning; multi-layer perceptron; random forest
- 分类号:
- X937
- 文献标志码:
- A
- 摘要:
- 为准确预测管道泄漏系数，估计管道泄漏量，以基于瞬变流方法的模拟数据为例，建立多个管道泄漏系数预测模型(多层感知机、长短期记忆网络、随机森林、支持向量机以及K近邻回归)，综合考虑管道流量和压力数据特点，提出序列提取法和均值提取法2种管道时序数据预处理方法，模型评价指标为相关系数（R2）和平均绝对百分比误差（MAPE）。研究结果表明：随机森林和多层感知机的抗噪性较强，在5%的噪声影响下，模型准确度下降幅度较小；均值提取法去噪功能较好，可在一定程度上降低噪声影响；基于均值提取法的多层感知机模型效果相对较好，R2为0.997 5，MAPE为1.599%，研究结果可为准确预测管道泄漏系数、估计泄漏量提供指导。
- Abstract:
- In order to accurately predict the leakage coefficient of pipeline and estimate the leakage amount of pipeline,taking the simulation data based on transient flow method as an example,multiple prediction models for the leakage coefficient of pipeline (multi-layer perceptron,long short-term memory network,random forest,support vector machine,K nearest neighbor regression) were established.Considering the data characteristics of pipeline flow rate and pressure comprehensively,two preprocessing methods of pipeline time series data,including the sequence extraction method and mean extraction method,were proposed.The model evaluation indicators were the correlation coefficient (R2) and the mean absolute percentage error (MAPE).The results showed that the random forest and multi-layer perceptron were more resistant to the noise,and the accuracy of models did not decrease much under the influence of 5% noise.The mean extraction method was powerful in denoising,which could reduce the influence brought by noise to a certain extent.The multi-layer perceptron model based on the mean extraction method worked the best with R2 of 0.997 5 and MAPE of 1.599%.The results have the guidance significance for the accurate prediction of pipeline leakage coefficient and the estimation of leakage amount.
参考文献/References:
［1］中国管道运输面面观［J］.中国水运，2007(3):60.
［2］ZHENG J Q,DU J,LIANG Y T,et al.Deeppipe:a semi-supervised learning for operating condition recognition of multi-product pipelines［J］.Process Safety and Environmental Protection,2021,150:510-521.
［3］ZHENG J Q,DU J,LIANG Y T,et al.Deeppipe:theory-guided LSTM method for monitoring pressure after multi-product pipeline shut down［J］.Process Safety and Environmental Protection,2021,155:518-531.
［4］郭凌云,周晶.外表面轴向裂纹管道失效评估误差对比分析［J］.防灾减灾工程学报,2022,42(3):586-596.
GUO Lingyun,ZHOU Jing.Comparative analysis of failure assessment errors of pipelines with axial cracks on the external surface［J］.Chinese Journal of Disaster Prevention and Mitigation Engineering,2022,42(3):586-596.
［5］马福明,石仁委.东黄管道腐蚀泄漏事故剖析［J］.石油化工腐蚀与防护,2018,35(6):44-46.
MA Fuming,SHI Renwei.Analysis of Donghuang pipeline corrosion and leakage accident［J］.Petrochemical Corrosion and Protection,2018,35(6):44-46.
［6］张春梅.埋地金属管道的瞬变电磁腐蚀检测方法研究［D］.重庆：重庆大学,2020.
［7］徐永莉.基于事故树分析“11·22”输油管道泄漏爆炸事故［J］.安全,2015(7):34-37.
XU Yongli.“11·22” oil pipeline leakage and explosion accident based on fault tree analysis［J］.Safety,2015(7):34-37.
［8］池洪建.黄岛管道爆炸启示录［J］.中国石油石化，2014(22):27-33.
CHI Hongjian.Apocalypse from Huangdao pipeline explosion［J］.China Petroleum & Petrochemical,2014(22):27-33.
［9］王欣.长输管道打孔盗油案件的侦查与防范策略［J］.四川警察学院学报，2016，28(6):31-36.
WANG Xin.Investigation and prevention strategies of oil theft cases by drilling holes in long distance pipelines［J］.Journal of Sichuan Police College,2016,28(6):31-36.
［10］刘文山,廖鸿,唐俊冰，等.海底长输天然气管道泄漏监测定位方法应用［J］.中国设备工程,2022(5):169-170.
LIU Wenshan,LIAO Hong,TANG Junbing,et al.Application of leakage monitoring and positioning method of submarine long-distance natural gas pipeline［J］.China Equipment Engineering,2022(5):169-170.
［11］方丽萍,殷布泽,孟令雅，等.气液混输管道段塞流泄漏声波产生机理研究［J］.振动与冲击,2022,41(12):229-237.
FANG Liping,YIN Buze,MENG Lingya,et al.Study on the mechanism of slug leakage of gas-liquid mixed transmission pipeline［J］.Vibration and Shock,2022,41(12):229-237.
［12］支焕.井区集输管线动态模拟法漏点检测的研究［D］.西安：西安石油大学,2012.
［13］闫骁瑾.输气管道泄漏检测技术及其发展趋势［J］.石油工业技术监督,2022,38(1):42-45.
YAN Xiaojin.Gas pipeline leak detection technology and its development trend［J］.Technical Supervision of Petroleum Industry,2022,38(1):42-45.
［14］周桂久,姜明,马文敏，等.输气管道泄漏声场特性分析及检测系统研究［J］.昆明理工大学学报(自然科学版),2022,47(1):128-138.
ZHOU Guijiu,JIANG Ming,MA Wenmin,et al.Field characteristics analysis and detection system of gas pipeline leakage［J］.Journal of Kunming University of Science and Technology (Natural Science Edition),2022,47(1):128-138.
［15］WANG C,ZHENG J Q,LIANG Y T,et al.Deeppipe:a hybrid model for multi-product pipeline condition recognition based on process and data coupling［J］.Computers & Chemical Engineering,2022,160：107733.
［16］ABDULLA M B,HERZALLAH R O，HAMMAD M A.Pipeline leak detection using artificial neural network:experimental study［J］.2013 5th International Conference on Modelling,Identification and Control (ICMIC),2013,21：328-332.
［17］KAYAALP F,ZENGIN A,KARA R,et al.Leakage detection and localization on water transportation pipelines:a multi-label classification approach［J］.Neural Comput & Applic，2017，28：2905-2914.
［18］ZHANG H R,LIANG Y T,ZHANG W,et al.Improved PSO-based method for leak detection and localization in liquid pipelines［J］.IEEE Transactions on Industrial Informatics,2018,14(7):3143-3154.
［19］ZHENG J Q,LIANG Y T,XU N,et al.Deeppipe:a customized generative model for estimations of liquid pipeline leakage parameters［J］.Computers & Chemical Engineering,2021,149:107290.
［20］ZHENG J Q,DAI Y H,LIANG Y T,et al.An online real-time estimation tool of leakage parameters for hazardous liquid pipelines［J］.International Journal of Critical Infrastructure Protection,2020,31:100389.
相似文献/References:
[1]刘恩斌,温櫂荣,郭冰燕,等.基于声信号特征分析的燃气管道探测识别方法*[J].中国安全生产科学技术,2022,18(4):61.[doi:10.11731/j.issn.1673-193x.2022.04.009]
LIU Enbin,WEN Zhaorong,GUO Bingyan,et al.Detection and recognition methods of gas pipelines based on acoustic signal feature analysis[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(10):61.[doi:10.11731/j.issn.1673-193x.2022.04.009]
备注/Memo
- 备注/Memo:
-
收稿日期： 2021-12-16
* 基金项目： 国家自然科学基金项目(51874325)
作者简介： 马云路，硕士研究生，主要研究方向为油气管道智能化储运。
通信作者： 郑坚钦，博士研究生，主要研究方向为智能化管道与油气田集输。
