吉林大学学报(工学版) ›› 2022, Vol. 52 ›› Issue (4): 959-969.doi: 10.13229/j.cnki.jdxbgxb20200889

• 通信与控制工程 • 上一篇    

基于VMD去噪和散布熵的管道信号特征提取方法

周怡娜1,2(),董宏丽1,2,3,张勇4,路敬祎1,2,3()   

  1. 1.东北石油大学 人工智能能源研究院，黑龙江 大庆 163318
    2.东北石油大学 黑龙江省网络化与智能控制重点实验室，黑龙江 大庆 163318
    3.东北石油大学 三亚海洋油气研究院，海南 三亚，572024
    4.东北石油大学 电子科学学院，黑龙江 大庆 163318
  • 收稿日期:2020-11-19 出版日期:2022-04-01 发布日期:2022-04-20
  • 通讯作者: 路敬祎 E-mail:1182090720@qq.com;ljywdm@126.com
  • 作者简介:周怡娜（1989-），女，博士研究生.研究方向：信号处理和管道泄漏检测技术. E-mail：1182090720@qq.com
  • 基金资助:
    国家自然科学基金项目(61873058);黑龙江省自然科学基金项目(LH2020F005);东北石油大学青年科学基金项目(2018QNL33);冶金装备及其控制教育部重点实验室基金项目(MECOF2019B01);海南省科技专项项目(ZDYF2022SHFZ105)

Feature extraction method of pipeline signals based on VMD de-noising and dispersion entropy

Yi-na ZHOU1,2(),Hong-li DONG1,2,3,Yong ZHANG4,Jing-yi LU1,2,3()   

  1. 1.Artificial Intelligence Energy Research Institute，Northeastern Petroleum University，Daqing 163318，China
    2.Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control，Northeastern Petroleum University，Daqing 163318，China
    3.Sanya Offshore Oil & Gas Research Institute，Northeast Petroleum University，Sanya 572024，China
    4.Institute of Electronic Science，Northeastern Petroleum University，Daqing 163318，China
  • Received:2020-11-19 Online:2022-04-01 Published:2022-04-20
  • Contact: Jing-yi LU E-mail:1182090720@qq.com;ljywdm@126.com

RICH HTML

 7   

PDF (PC)

579

摘要：

针对管道声波信号非线性、非平稳性特点和管道泄漏信号特征提取困难的问题，提出一种管道声波信号特征提取方法。首先，采用变分模态分解（VMD）算法对采集到的声波信号进行去噪，在此过程中采用最小巴氏距离法确定VMD分解的模态个数，并通过评估VMD分解后各本征模态函数（IMF）分量与原始信号的概率密度之间的Wasserstein距离（WD）来筛选有效模态，对筛选的有效模态进行重构。然后，对重构的信号计算其散布熵值作为信号特征参数，最后将特征参数输入极限学习机（ELM）进行工况识别。实验结果表明，本文方法能够较准确地分类识别管道信号，总的识别率达到了100%。

关键词: 管道泄漏, 变分模态分解, Wasserstein距离, 散布熵, 特征提取

Abstract:

In view of the non-linear and non-stationary characteristics of pipeline acoustic signals and the difficulty of extracting the characteristics of pipeline leakage signal， a feature extraction method for acoustic signal was proposed. Firstly， the variational mode decomposition （VMD） was used to de-noise the collected acoustic signal， during which process the mode number of VMD was determined by the method of Minimum Bhattacharyya distance. Then the Wasserstein Distance （WD） between the probability density of the （Intrinsic Mode Function） IMF components was obtained by VMD and the original signal， which was evaluated to select the effective modes so as to reconstruct the selected effective modes. Finally， the dispersion entropy value of the reconstructed signal was used as the signal characteristic parameter， and the characteristic parameter was input into the extreme learning machine （ELM） to recognize the working condition. Experimental results show that the proposed method could classify and recognize pipeline signals accurately， and the total recognition rate is up to 100%.

Key words: pipeline leakage, variational mode decomposition, Wasserstein distance, dispersion entropy, feature extraction

中图分类号: 

  • TN911.72

图1

基于最小巴氏距离法确定最优参数K值流程图"

图2

有效模态选取流程图"

图3

本文方法流程图"

图4

3种工况信号的时域波形图及频谱图"

表1

不同K值下的最小巴氏距离值（Bdmin）"

KBdminKBdmin
20.006260.0064
30.009470.0062
40.012880.0000
50.009490.0000

图5

VMD分解结果"

图6

各分量与原始信号的概率密度之间的WD"

图7

去噪后的泄漏信号时域波形及频谱图"

图8

去噪后的三种管道工况信号"

图9

不同工况下去噪信号的散布熵值拟合曲线"

表2

数据集分配表"

管道工况训练集/个测试集/个类别标签
敲击80201
泄漏80202
正常80203

图10

测试集分类结果"

表3

各方法测试集ELM识别结果"

方 法准确率/%
训练准确率测试准确率
VMD?DE?ELM100100
DE?ELM92.0890
NLM?DE?ELM99.1795
VMD?SSE?ELM77.576.67
VMD?IE?ELM97.0893.33
VMD?BE?ELM82.580
VMD?SE?ELM99.1798.33
VMD?ELM8575
ELM80.1773.33
1 Pan S S, Xu Z D, Li D S, et al. Research on detection and location of fluid-filled pipeline leakage based on acoustic emission technology[J]. Sensors, 2018, 18(11): No. 3628.
2 Zhu J X, Ren L, Ho S C, et al. Gas pipeline leakage detection based on PZT sensors[J]. Smart Materials and Structures, 2017, 26(2): No. 025022.
3 刘翠伟,敬华飞,方丽萍,等. 输气管道泄漏声波衰减模型的理论研究[J]. 振动与冲击, 2018, 37(20): 109-114.
Liu Cui-wei, Jing Hua-fei, Fang Li-ping, et al. A theoretical study of acoustic attenuation model of gas pipeline leakage [J]. Vibration and Shock, 2018, 37(20): 109-114.
4 曹雪伟,孙首群,宣立明,等. 小波分析在管道泄漏信号去噪中的优化研究[J]. 石油化工自动化, 2019, 55(1): 29-34.
Cao Xue-wei, Sun Shou-qun, Xuan Li-ming, et al. Optimization of wavelet analysis in denoising of pipeline leakage signals[J]. Petrochemical Automation, 2019, 55(1): 29-34.
5 Yu X C, Liang W, Zhang L B, et al. Dual-tree complex wavelet transform and SVD based acoustic noise reduction and its application in lead detection for natural gas pipeline[J]. Mechanical Systems and Signal Processing, 2016, 72: 266-285.
6 赵利强,王建林,于涛. 基于改进EMD的输油管道泄漏信号特征提取方法研究[J]. 仪器仪表学报, 2013, 34(12): 2696-2702.
Zhao Li-qiang, Wang Jian-lin, Yu Tao. Study on feature extraction method of oil pipeline leakage signal based on improved EMD[J]. Chinese Journal of Scientific Instrument, 2013, 34(12): 2696-2702.
7 Liang X M, Li P, Hu Z Y, et al. Leak detection and location of pipelines based on LMD and least squares twin support vector machine[J]. IEEE Access, 2017,5: 8659-8668.
8 周颖涛,周绍骑,姚远航,等. 基于EEMD的声发射管道泄漏定位检测[J]. 四川兵工学报, 2015, 36(3): 110-113, 116.
Zhou Ying-tao, Zhou Shao-qi, Yao Yuan-hang, et al. Leakage location detection of acoustic emission pipeline based on EEMD[J]. Sichuan Journal of military Industry, 2015, 36(3): 110-113, 116.
9 周怡娜,路敬祎,董宏丽,等. 云相似度测量的变分模态分解去噪方法[J]. 吉林大学学报: 信息科学版, 2020, 38(1): 9-17.
Zhou Yi-na, Lu Jing-yi, Dong Hong-li, et al. The denoising method of variational mode decomposition based on cloud similarity measurement[J]. Journal of Jilin University (Information Science Edition), 2020, 38(1): 9-17.
10 Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings Mathematical Physical and Engineering ences, 1998, 454(1971): 903-995.
11 李余兴,李亚安,陈晓,等. 基于VMD和中心频率的舰船辐射噪声特征提取方法研究[J]. 振动与冲击, 2018, 37(23): 213-218, 285.
Li Yu-xing, Li Ya-an, Chen Xiao, et al. Research on the extraction method of ship radiation noise based on VMD and central frequency[J]. Vibration and Impact, 2018, 37(23): 213-218, 285.
12 吴文轩,王志坚,张纪平,等. 基于峭度的VMD分解中K值的确定方法研究[J]. 机械传动, 2018, 42(8): 153-157.
Wu Wen-xuan, Wang Zhi-jian, Zhang Ji-ping, et al. Research on the method of determining K value in VMD decomposition based on kurtosis[J]. Mechanical Transmission, 2018, 42(8): 153-157.
13 Yang H B, Liu S L, Zhang H L. Adaptive estimation of VMD modes number based on cross correlation coefficient[J]. Journal of Vibroengineering, 2017, 19(2): 1185-1196.
14 昝涛,庞兆亮,王民,等. 基于VMD的滚动轴承早期故障诊断方法[J]. 北京工业大学学报, 2019, 45(2): 103-110.
Zan Tao, Pang Zhao-liang, Wang Min, et al. Early fault diagnosis method of rolling bearings based on VMD[J]. Journal of Beijing University of Technology, 2019, 45(2): 103-110.
15 Li Y, Li Y, Chen X,et al. Research on ship- radiated noise denoising using secondary variational mode decomposition and correlation coefficient[J]. Sensors, 2017, 18(1): No. 18010048.
16 周怡娜,路敬祎,张勇,等. VMD-SG-WT去噪法及其在混沌去噪中的应用[J]. 东北石油大学学报, 2020, 44(4): 113-120, 132.
Zhou Yi-na, Lu Jing-yi, Zhang Yong, et al. VMD-SG-WT denoising method and its application in chaotic denoising[J]. Journal of Northeast Petroleum University, 2020, 44(4): 113-120, 132.
17 Zhang X, Miao Q, Zhang H, et al. A parameter-adaptive VMD method based on grasshopper optimization algorithm to analyze vibration signals from rotating machinery[J]. Mechanical Systems and Signal Processing, 2018, 108: 58-72.
18 周洋,向阳,黄陈哲,等. 基于VMD⁃SVD能量标准谱⁃Teager能量算子的轴承故障诊断方法[J]. 噪声与振动控制, 2019, 39(4): 212-217, 253.
Zhou Yang, Xiang Yang, Huang Chen-zhe, et al. The fault diagnosis method for bearing Based on VMD-SVD energy standard spectrum-Teager energy operator[J]. Noise and Vibration Control, 2019, 39(4): 212-217, 253.
19 任学平,李攀,王朝阁,等. 基于改进VMD与包络导数能量算子的滚动轴承早期故障诊断[J]. 振动与冲击, 2018, 37(15): 6-13.
Ren Xue-ping, Li Pan, Wang Chao-ge, et al. Early fault diagnosis of rolling bearing based on improved VMD and envelope derivative energy operator[J]. Vibration and Shock, 2018, 37(15): 6-13.
20 王秀芳,檀丽丽,姜春雷,等. 基于互信息的VMD算法在管道泄漏检测中的应用[J]. 压力容器, 2017, 34(8): 75-80.
Wang Xiu-fang, Tan Li-li, Jiang Chun-lei, et al. The application of VMD algorithm based on mutual information in pipeline leakage detection[J]. Pressure vessel, 2017, 34(8): 75-80.
21 Chang L, Cao H, Shen C. Dual-Mass MEMS Gyroscope parallel denoising and temperature compensation processing based on WLMP and CS-SVR[J]. Micromachines, 2020, 11(6): 586.
22 李帅永,夏传强,程振华,等. 基于VMD和互谱分析的供水管道泄漏定位方法[J]. 仪器仪表学报, 2019, 40(7): 195-205.
Li Shui-yong, Xia Chuan-qiang, Cheng Zhen-hua, et al. Water supply pipeline leakage location method Based on VMD and mutual spectrum analysis[J]. Journal of Instrumentation, 2019, 40(7): 195-205.
23 Ma W P, Yin S X, Jiang C L, et al. Variational mode decomposition denoising combined with the Hausdorff distance[J]. Review of Entific Instruments, 2017, 88(3): No. 035109.
24 Yang J, Wang X, Feng Z, et al. Research on pattern recognition method of blockage signal in pipeline based on LMD information entropy and ELM[J]. Mathematical Problems in Engineering Theory Methods & Applications, 2017(3): 1-16.
25 王秀芳,王昕. EEMD近似熵和支持向量机的管道泄漏特征向量提取研究[J]. 化工自动化及仪表, 2015, 42(11): 1226-1229.
Wang Xiu-fang, Wang Xin. Study on EEMD approximate entropy and SVM pipeline leak feature extraction[J]. Control and Instruments in Chemical Industry, 2015, 42(11): 1226-1229.
26 冯雪松,文玉梅,甄锦鹏,等. 管道泄漏声振动信号的特征分析[J]. 声学技术, 2015, 34(5): 413-418.
Feng Xue-song, Wen Yu-mei, Zhen Jin-peng, et al. Characteristic analysis of acoustic vibration signals of pipeline leakage[J]. Acoustic Technology, 2015, 34(5): 413-418.
27 刘炜,刘宏昭. 应用模糊熵和相似度的管道泄漏检测与定位[J]. 机械科学与技术, 2016, 35(3): 437-443.
Liu Wei, Liu Hong-zhao. Application of fuzzy entropy and similarity in pipeline leakage detection and location [J]. Mechanical Science and Technology, 2016, 35(3): 437-443.
28 袁培龙,周绍骑,周颖涛,等. 基于内禀模态奇异值熵的声发射管道泄漏诊断[J]. 重庆理工大学学报, 2016, 30(11): 60-64.
Yuan Pei-long, Zhou Shao-qi, Zhou Ying-tao, et al. Diagnosis of acoustic emission pipeline leakage based on intrinsic mode singular value entropy[J]. Journal of Chongqing University of Technology, 2016, 30(11): 60-64.
29 孙洁娣,肖启阳,温江涛,等. 基于LMD包络谱熵及SVM的天然气管道微小泄漏孔径识别[J]. 机械工程学报, 2014, 50(20): 18-25.
Sun Jie-di, Xiao Qi-yang, Wen Jiang-tao, et al. Small leakage aperture identification of natural gas pipeline based on LMD envelope spectrum entropy and SVM[J]. Journal of Mechanical Engineering, 2014, 50(20): 18-25.
30 Rostaghi M, Azami H. Dispersion entropy: a measure for time-series analysis[J]. IEEE Signal Processing Letters, 2016: 23(5): 610-614.
31 Dragomiretskiy K, Zosso D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
32 Kailath T. The divergence and bhattacharyya distance measures in signal selection[J]. IEEE Transactions on Communication Technology, 1967, 15(1): 52-60.
33 Lipman Y, Puente J, Daubechies I. Conformal wasserstein distance: II. computational aspects and extensions[J]. Mathematics of Computation, 2011, 82(281): 331-381.
34 Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1-3): 489-501.
35 梁洪卫. 油气管道泄漏声波信号检测与识别技术研究[D]. 大庆:东北石油大学电气信息工程学院,2019.
Liang Hong-wei. A study on detection and identification technology of oil and gas pipeline leakage acoustic signal [D]. Daqing: School of Electrical and Information Engineering, Northeast Petroleum University, 2019.
[1] 王进花,胡佳伟,曹洁,黄涛. 基于自适应变分模态分解和集成极限学习机的滚动轴承多故障诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 318-328.
[2] 李国发,王彦博,何佳龙,王继利. 机电装备健康状态评估研究进展及发展趋势[J]. 吉林大学学报(工学版), 2022, 52(2): 267-279.
[3] 陈晓雷,孙永峰,李策,林冬梅. 基于卷积神经网络和双向长短期记忆的稳定抗噪声滚动轴承故障诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 296-309.
[4] 许鸿奎,姜彤彤,李鑫,姜斌祥,王永雷. 结合降噪自编码与极限学习机的LTE上行干扰分析[J]. 吉林大学学报(工学版), 2022, 52(1): 195-203.
[5] 刘桂霞,裴志尧,宋佳智. 基于深度学习的蛋白质⁃ATP结合位点预测[J]. 吉林大学学报(工学版), 2022, 52(1): 187-194.
[6] 刘远红,郭攀攀,张彦生,李鑫. 基于黎曼流形的稀疏图保持投影的特征提取[J]. 吉林大学学报(工学版), 2021, 51(6): 2268-2279.
[7] 钟辉,康恒,吕颖达,李振建,李红,欧阳若川. 基于注意力卷积神经网络的图像篡改定位算法[J]. 吉林大学学报(工学版), 2021, 51(5): 1838-1844.
[8] 朱小龙,谢忠. 基于海量文本数据的知识图谱自动构建算法[J]. 吉林大学学报(工学版), 2021, 51(4): 1358-1363.
[9] 徐涛,马克,刘才华. 基于深度学习的行人多目标跟踪方法[J]. 吉林大学学报(工学版), 2021, 51(1): 27-38.
[10] 耿庆田, 于繁华, 王宇婷, 高琦坤. 基于特征融合的车型检测新算法[J]. 吉林大学学报(工学版), 2018, 48(3): 929-935.
[11] 董强, 刘晶红, 周前飞. 用于遥感图像拼接的改进SURF算法[J]. 吉林大学学报(工学版), 2017, 47(5): 1644-1652.
[12] 尹明, 战荫伟, 裴海龙. 基于稀疏补算子学习的图像融合方法[J]. 吉林大学学报(工学版), 2016, 46(6): 2052-2058.
[13] 肖钟捷. 基于小波空间特征谱熵的数字图像识别[J]. 吉林大学学报(工学版), 2015, 45(6): 1994-1998.
[14] 刘红，孙爽滋，王庆元，李延忠. 基于PSO的模拟电路故障信息特征提取[J]. 吉林大学学报(工学版), 2015, 45(2): 675-680.
[15] 潘海阳, 刘顺安, 姚永明. 基于深度信息的自主空中加油技术[J]. 吉林大学学报(工学版), 2014, 44(6): 1750-1756.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 《吉林大学学报(工学版)》编辑部
地址：长春市人民大街5988号　电话：+86-431-85095297　传真：+86-431-85094074　E-mail: xbgxb@jlu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发