|本期目录/Table of Contents|

[1]虞丹阳,玉建军,靳新迪.2种基于模式识别的环状燃气管网泄漏检测方法[J].中国安全生产科学技术,2017,13(1):187-192.[doi:10.11731/j.issn.1673-193x.2017.01.031]
　YU Danyang,YU Jianjun,JIN Xindi.Study on two kinds of leakage detection methods for loop gas pipeline network based on pattern recognition[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2017,13(1):187-192.[doi:10.11731/j.issn.1673-193x.2017.01.031]
点击复制

2种基于模式识别的环状燃气管网泄漏检测方法
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
13
期数:
2017年1期
页码:
187-192
栏目:
现代职业安全卫生管理与技术
出版日期:
2017-01-31

文章信息/Info

Title:
Study on two kinds of leakage detection methods for loop gas pipeline network based on pattern recognition
文章编号:
1673-193X(2017)-01-0187-06
作者:
虞丹阳1; 玉建军1; 靳新迪1; 2
1.天津城建大学 能源与安全学院，天津 300384；2. 中国石化销售有限公司 上海石油分公司，上海 200000
Author(s):
YU Danyang1;  YU Jianjun1;  JIN Xindi1; 2
1. School of Energy and Safety Engineering, Tianjin Chengjian University, Tianjin 300384, China; 2. Sinopec Sales Co., Ltd. Shanghai Petroleum Branch, Shanghai 200000, China
关键词:
模式识别; 环状管网; 燃气泄漏; 特征向量; 支持向量机
Keywords:
pattern recognition;  loop pipeline network;  gas leakage;  eigenvector;  support vector machine
分类号:
TE88;X937
DOI:
10.11731/j.issn.1673-193x.2017.01.031
文献标志码:
A
摘要:
为了将模式识别技术应用于环状燃气管网泄漏检测并找到合适的特征提取方法，以天津城建大学实验室环状燃气管网泄漏为例，将实验的28种工况作为测试样本，与之对应的模拟工况作为训练样本，采用提取压力图像特征向量法和节点压力矩阵法分别进行环状燃气管网的泄漏检测，采用支持向量机分类器将2种方法获得的特征向量进行训练与分类检验，进而将其分类准确率进行对比分析。研究结果表明：该2种方法均可用于环状燃气管网泄漏检测，提取压力图像特征向量法因有效地降低了特征向量的维度和数据波动的干扰，其结果更优。结合SCADA和GIS系统，可将该法应用于实际水、气、油管网泄漏检测和定位，有助于降低成本，提高检测效果。
Abstract:
In order to apply the pattern recognition technology to the leakage detection of loop gas pipeline network and find the suitable feature extraction method, the leakage of loop gas pipeline network in the laboratory of Tianjin Chengjian University was taken as an example. 28 kinds of experimental working conditions were taken as the testing samples, and the corresponding simulation working conditions were taken as the training samples. The ei-genvector extracting method from pressure images and the node pressure matrix method were applied respectively to carry out the leakage detection of loop gas pipeline network. The support vector machine (SVM) classifier was used to conduct the training and classification testing on the eigenvectors obtained by the two methods, then the corresponding classification accuracy were compared and analyzed. The results showed that both the methods can be used for leakage detection of loop gas pipeline network. The eigenvector extracting method from pressure im-ages can effectively reduce the dimensionality of eigenvectors and the interference of data fluctuation, with the better results. Combined with SCADA and GIS system, the method can be applied to the leakage detection and lo-cation of the practical water, gas and oil pipeline networks, which can reduce the cost and improve the detection results.

参考文献/References:

［1］王春雪, 吕淑然. 城市燃气管线泄漏致灾灾害链研究［J］. 中国安全生产科学技术, 2016, 12(5):16-21. WANG Chunxue, LYU Shuran. Research on disaster chain of leakage disaster in urban gas pipeline ［J］. Journal of Safety Science and Technology, 2016, 12(5): 16-21.
［2］GAO Xiaoming, FAN Hong, HUANG Teng, et al. Natural gas pipeline leak detector based on NIR diode laser absorption spectroscopy［J］. Spectrochimica Acta Part A-Molecular and Biomolecular Spectroscopy, 2006, 65(1): 133-138.
［3］MENG Lingya, LI Yuxing, WANG Wuchang, et al. Experimental study on leak detection and location for gas pipeline based on acoustic method［J］. Journal of Loss Prevention in the Process Industries, 2012, 25(1): 90-102.
［4］李军, 徐永生, 玉建军.燃气管道泄漏检测新技术［J］.煤气与热力, 2007, 27(7):56-59. LI Jun, XU Yongsheng, YU Jianjun. New technologies for leakage detection of gas pipelin ［J］. GAS ＆ HEAT, 2007, 27(7): 56-59.
［5］Fukushima K, Maeshima R, Kinoshita A. Gas pipeline leak detection system using the online simulation method ［J］. Computers and Chemical Engineering, 2000, 24: 453-456.
［6］张丽娟.基于小波分析的燃气管道泄漏检测与定位研究［D］. 武汉: 华中科技大学, 2006.
［7］黄凤洁，田贯三，贾文磊，等．基于BP神经网络的城市燃气管网泄漏定位［J］．山东建筑大学学报，2011，26（5）：436-439, 475． HUANG Fengjie，TIAN Guansan，JIA Wenlei, et al. Research on the leak location of urban gas pipe network based on BP network ［J］. Journal of Shandong Jianzhu University, 2011, 26(5): 436-439, 475.
［8］季娟,田贵云,王平. 燃气管道检测技术研究进展［J］. 无损检测, 2012, 34(12):20-24. JI Juan, TIAN Guiyun, WANG Ping. Research and development of detection technologies for gas pipeline ［J］. Nondestructive Testing, 2012, 34(12):20-24.
［9］侯庆民.燃气长直管道泄漏检测及定位方法研究 ［D］. 哈尔滨: 哈尔滨工业大学, 2014.
［10］张丽娟, 李帆, 王文龙. 2种基于模式识别的枝状燃气管网泄漏定位方法［J］. 天然气工业, 2007, 27(8):106-108. ZHANG Lijuan, LI Fan, WANG Wenlong. Two leakage positioning methods for dentritic gas pipeline network based on pattern recognition ［J］. Natural Gas Industry, 2007, 27(8): 106-108.
［11］段昱, 武平. 基于模式识别的燃气管网泄漏检测技术［J］. 能源研究与管理, 2014(2):69-72. DUAN Li, WU Ping. Leak detection of gas pipeline network based on pattern recognition ［J］. Energy research and management, 2014(2):69-72.
［12］范会敏, 王浩. 模式识别方法概述 ［J］.电子设计工程, 2012, 20(19):48-51. FAN Huimin, WANG Hao. An overview of the pattern recognition methods ［J］. Electronic Design Engineering, 2012, 20(19): 48-51.
［13］张铮,倪红霞,苑春苗.精通Matlab数字图像处理与识别［M］.北京：人民邮电出版社,2013:42.
［14］王健康.自动指纹识别技术研究 ［D］. 长沙: 中南大学, 2010.
［15］刘炜, 刘宏昭. 检测与定位管道泄漏的图像处理方法研究［J］.控制工程, 2014, 21(2):294-297. LIU Wei, LIU Hongzhao. Application of image processing technology on detection and location of pipeline leak ［J］. Control Engineering of China, 2014, 21(2):294-297.
［16］陈华立，叶昊．基于图像处理的管道泄漏检测与定位［J］．清华大学学报(自然科学版)，2005，45（1）：119-122. CHEN Huali, YE Hao. Oil pipeline leak detection and location based on image processing ［J］. Journal of Tsinghua University(Science and Technology), 2005, 45(1):119-122.
［17］焦娇娜. 变负荷工况下燃气管网泄漏特性实验研究与仿真模拟［D］. 天津: 天津城建大学, 2013.

相似文献/References:

[1]罗景峰,许开立.基于可变模糊组合方法的瓦斯涌出量预测[J].中国安全生产科学技术,2011,7(6):29.
　LUO Jing-feng,XU Kai-li.Gas Emission Rate Forecast Based on variable fuzzy Combination method [J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(1):29.
[2]李德顺,宫博,许开立.石化企业火灾危险性模式识别模型研究[J].中国安全生产科学技术,2012,8(4):122.
　LI De shun,GONG Bo,XU Kai li.Research on risk pattern recognition model of fire inpetrochemical enterprise[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(1):122.
[3]毕慧杰,任延平,张浩浩,等.基于多因素模式识别的煤与瓦斯突出预测研究[J].中国安全生产科学技术,2017,13(6):98.[doi:10.11731/j.issn.1673-193x.2017.06.016]
　BI Huijie,REN Yanping,ZHANG Haohao,et al.Dynamic prediction of coal and gas outburst based on multi-factor pattern recognition[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2017,13(1):98.[doi:10.11731/j.issn.1673-193x.2017.06.016]
[4]胡瑾秋,张来斌,胡静桦.基于视线追踪技术的工艺操作人员人为失误识别研究[J].中国安全生产科学技术,2019,15(5):142.[doi:10.11731/j.issn.1673-193x.2019.05.023]
　HU Jinqiu,ZHANG Laibin,HU Jinghua.Study on human error recognition of process operators based on eye tracking technology[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2019,15(1):142.[doi:10.11731/j.issn.1673-193x.2019.05.023]
[5]吴雪琴,廖斌.基于疲劳模式识别的VDT作业工间休息机制*[J].中国安全生产科学技术,2021,17(3):169.[doi:10.11731/j.issn.1673-193x.2021.03.026]
　WU Xueqin,LIAO Bin.Break mechanism of VDT continuous operation based on fatigue pattern recognition[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(1):169.[doi:10.11731/j.issn.1673-193x.2021.03.026]
[6]谢学斌,王小平,刘涛.基于ICEEMDAN和MC-CNN的矿山声发射信号识别分类方法*[J].中国安全生产科学技术,2022,18(2):113.[doi:10.11731/j.issn.1673-193x.2022.02.017]
　XIE Xuebin,WANG Xiaoping,LIU Tao.Recognition and classification methods of mine acoustic emission signals based on ICEEMDAN and MC-CNN[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(1):113.[doi:10.11731/j.issn.1673-193x.2022.02.017]
[7]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(1):61.[doi:10.11731/j.issn.1673-193x.2022.04.009]
[8]徐浩钧,胡啸峰,吴建松.化学实验室动火实验无人值守行为识别方法研究*[J].中国安全生产科学技术,2023,19(12):135.[doi:10.11731/j.issn.1673-193x.2023.12.018]
　XU Haojun,HU Xiaofeng,WU Jiansong.Research on identification method of unattended behavior in hot experiments of chemical laboratory[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(1):135.[doi:10.11731/j.issn.1673-193x.2023.12.018]

备注/Memo

备注/Memo:
天津市科技支撑计划重点项目 (10ZCGYSF01700)
更新日期/Last Update: 2017-03-02