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

被引：0
|
作者：
Zhou Y.-N. [1 ,2 ]
Dong H.-L. [1 ,2 ,3 ]
Zhang Y. [4 ]
Lu J.-Y. [1 ,2 ,3 ]
机构：
[1] Artificial Intelligence Energy Research Institute, Northeastern Petroleum University, Daqing
[2] Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control, Northeastern Petroleum University, Daqing
[3] Sanya Offshore Oil & Gas Research Institute, Northeast Petroleum University, Sanya
[4] Institute of Electronic Science, Northeastern Petroleum University, Daqing
来源：
Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition) | 2022年 / 52卷 / 04期
关键词：
Dispersion entropy; Feature extraction; Pipeline leakage; Variational mode decomposition; Wasserstein distance;
D O I：
10.13229/j.cnki.jdxbgxb20200889
中图分类号：
学科分类号：
摘要：
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%. © 2022, Jilin University Press. All right reserved.
引用
收藏
页码：959 / 969
页数：10
相关论文
共 35 条
  • [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, Sensors, 18, 11, (2018)
  • [2] Zhu J X, Ren L, Ho S C, Et al., Gas pipeline leakage detection based on PZT sensors, Smart Materials and Structures, 26, 2, (2017)
  • [3] Liu Cui-wei, Jing Hua-fei, Fang Li-ping, Et al., A theoretical study of acoustic attenuation model of gas pipeline leakage, Vibration and Shock, 37, 20, pp. 109-114, (2018)
  • [4] Cao Xue-wei, Sun Shou-qun, Xuan Li-ming, Et al., Optimization of wavelet analysis in denoising of pipeline leakage signals, Petrochemical Automation, 55, 1, pp. 29-34, (2019)
  • [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, Mechanical Systems and Signal Processing, 72, pp. 266-285, (2016)
  • [6] Zhao Li-qiang, Wang Jian-lin, Yu Tao, Study on feature extraction method of oil pipeline leakage signal based on improved EMD, Chinese Journal of Scientific Instrument, 34, 12, pp. 2696-2702, (2013)
  • [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, IEEE Access, 5, pp. 8659-8668, (2017)
  • [8] Zhou Ying-tao, Zhou Shao-qi, Yao Yuan-hang, Et al., Leakage location detection of acoustic emission pipeline based on EEMD, Sichuan Journal of military Industry, 36, 3, pp. 110-113, (2015)
  • [9] Zhou Yi-na, Lu Jing-yi, Dong Hong-li, Et al., The denoising method of variational mode decomposition based on cloud similarity measurement, Journal of Jilin University (Information Science Edition), 38, 1, pp. 9-17, (2020)
  • [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, Proceedings Mathematical Physical and Engineering ences, 454, 1971, pp. 903-995, (1998)
1234