针对管道同时发生多点泄漏时，各个泄漏点的声波信号相互叠加，影响泄漏声波传播规律，不能有效检测多点泄漏的问题，提出一种基于改进变分模态分解(variational mode decomposing，VMD)和双支持向量机(twin support vector machine, TWSVM)的多点泄漏检测方法。由于VMD的分解模态个数影响多点泄漏特征提取的效果，采用误差能量函数自适应选取VMD分解本征模态函数个数;将多点泄漏声波信号经改进VMD消噪并进行多点泄漏声波信号特征值提取，组成特征向量;将特征向量作为TWSVM的输入，进行多点泄漏识别。结果表明，所提出的多点泄漏检测方法能有效检测多点泄漏，多点泄漏检测准确率达到984%。
Abstract
Here, aiming at the problem of acoustic wave signals of various leakage points overlapping with each other during multi-point leakage in pipeline simultaneously occurring to affect the propagation law of leakage acoustic wave and be unable to effectively detect multi-point leakage, a multi-point leakage detection method based on improved variational mode decomposition (VMD) and twin support vector machine (TWSVM) was proposed.Due to the number of decomposition modes of VMD affecting the effect of multi-point leakage feature extraction, the number of intrinsic mode functions of VMD was adaptively selected by using the error energy function, and thus VMD was improved.Then, the multi-point leakage’s acoustic wave signals were denoised with the improved VMD, and their feature values were extracted to form feature vectors.Finally, feature vectors were taken as the input of TWSVM, and TWSVM was used to do multi-point leakage recognition.The field test results showed that the proposed multi-point leakage detection method can be used to effectively detect multi-point leakage, and its detection accuracy reaches 98.4%.
关键词
多点泄漏 /
变分模态分解 /
双支持向量机 /
误差能量函数
{{custom_keyword}} /
Key words
multi-point leaks /
variational mode decomposition (VMD) /
twin support vector machine (TWSVM) /
error energy function
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］VERDE C, TORRES L.Modeling and monitoring of pipelines and networks［M］.Berlin: Springer, 2017.
［2］WANG X, GHIDAOUI M S.Identification of multiple leaks in pipeline II: Iterative beamforming and leak number estimation［J］.Mechanical Systems and Signal Processing, 2019,119: 346-362.
［3］DATTA S, SARKAR S. A review on different pipeline fault detection methods［J］.Journal of Loss Prevention in the Process Industries, 2016, 41: 97-106.
［4］WANG X, GHIDAOUI M S.Identification of multiple leaks in pipeline: Linearized model, maximum likelihood, and super-resolution localization［J］.Mechanical Systems and Signal Processing, 2018, 107: 529-548.
［5］LIU C, CUI Z, FANG L, et al.Leak localization approaches for gas pipelines using time and velocity differences of acoustic waves［J］.Engineering Failure Analysis, 2019, 103:1-8.
［6］LIU J, ZANG D, LIU C, et al.A leak detection method for oil pipeline based on markov feature and two-stage decision scheme［J］.Measurement, 2019, 138: 433-445.
［7］GUO C, WEN Y, LI P, et al, Adaptive noise cancellation based on EMD in water-supply pipeline leak detection［J］.Measurement, 2016, 79:188-197.
［8］REN H, LIU W, SHANE M, et al, A new wind turbine health condition monitoring method based on VMD-MPE and feature-based transfer learning［J］.Measurement,2019, 148:1-8.
［9］LI J, CHEN Y, QIAN Z, et al.Research on VMD based adaptive denoising method applied to water supply pipeline leakage location［J］.Measurement, 2020, 151:1-13.
［10］LIU C, LI Y, FANG L, et al.New leak-localization approaches for gas pipelines using acoustic waves［J］.Measurement, 2019, 134:54-65.
［11］CHEN Q, SHEN G, JIANG J, et al.Effect of rubber washers on leak location for assembled pressurized liquid pipeline based on negative pressure wave method［J］.Process Safety and Environmental Protection, 2018, 119:181-190.
［12］HE G, LIANG Y, LI Y, et al.A method for simulating the entire leaking process and calculating the liquid leakage volume of a damaged pressurized pipeline［J］.Journal of Hazardous Materials, 2017, 332:19-32.
［13］WANG F, LIN W, LIU Z, et al. Pipeline leak detection by using time-domain statistical features［J］.IEEE Sensors Journal, 2017, 17: 6431-6442.
［14］LANG X, LI P, GUO Y, et al.A multiple leaks localization method in a pipeline based on change in the sound velocity［J］.IEEE Transactions on Instrumentation and Measurement, 2019(11):2955774.
［15］DELGADO-AGUIAGA J A, BESANON G, BEGOVICH O, et al.Multi-leak diagnosis in pipelines based on extended Kalman filter［J］.Control Engineering Practice, 2016, 49: 139-148.
［16］RUI Z, HAN G, ZHANG H, et al.A new model to evaluate two leak points in a gas pipeline［J］.Journal of Natural Gas Science and Engineering, 2017(46): 491-497.
［17］黄海松，魏建安，任竹鹏，等.基于失衡样本特效过采样算法与SVM的滚动轴承故障诊断［J］.振动与冲击，2020，39(10)：65-73.
HUANG Haisong, WEI Jian’an, REN Zhupeng, et al.Rolling bearing fault diagnosis based on imbalanced sample characteristics oversampling algorithm and SVM ［J］.Journal of Vibration and Shock, 2020，39(10)：65-73.
［18］ZHOU B, LIU A, WANG X, et al.Compressive sensing-based multiple-leak identification for smart water supply systems［J］.IEEE Internet of Things Journal, 2020, 5(2): 1228-1240.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1885 KB)
