Vibration source separation algorithm for gear box based on time-frequency masking and vibration signal features

被引：0

作者：

Zhang B. ^{[1
]}

Wang L. ^{[2
]}

Zou Z. ^{[2
]}

Teng W. ^{[1
]}

Deng Y. ^{[2
]}

机构：

[1] Key Laboratory of Power Station Energy Transfer Conversion and System, Ministry of Education, North China Electric Power University, Beijing

[2] China Three Gorges Corporation, Beijing

来源：

Zhendong yu Chongji/Journal of Vibration and Shock | 2023年 / 42卷 / 15期

关键词：

gear fault features; time-frequency masking; vibration source separation;

D O I：

10.13465/j.cnki.jvs.2023.15.010

中图分类号：

学科分类号：

摘要：

Here, aiming at the problem of multi-source mixing in gearbox vibration signals, a gearbox vibration source separation algorithm based on time-frequency masking and vibration signal features was proposed. Main steps of the algorithm were as follows: firstly, a time domain vibration signal was converted into a time-frequency spectrum using short-time Fourier transform for analysis, gear meshing frequency features were obtained with optimal ratio masking; then, the peak-seeking algorithm was used to obtain all frequency components in mixed signal, fault components were further separated combined with fault frequency domain features, gear modulation features were achieved through ideal ratio masking; finally, the inverse short-time Fourier transform was used to recover source signals. The algorithm was verified with wind-power transmission test rig signals and actual wind-power field vibration signals. The results showed that the proposed algorithm can effectively separate vibration source signals and extract fault components when gear rotating speed is known. © 2023 Chinese Vibration Engineering Society. All rights reserved.

引用

页码：73 / 82

页数：9

共 16 条

[1] HERAULT J, JUTTEN C., Space or time adaptive signal processing by neural network models, Aip Conference 151 on Neural Networks for Computing, (1986)
[2] LI Y P, WANG D L., On the optimally of ideal binary time-frequency masks, Speech Communication, 51, 3, pp. 230-239, (2009)
[3] HUMMERSONE C, MASON R, BROOKES T., Ideal binary mask ratio
[4] a novel assessing binary-mask-based sound source separation algorithms [J], IEEE Transactions on Audio, Speech, and Language Processing, 19, 7, pp. 2039-2045, (2011)
[5] NARAYANAN A, WANG D L., Ideal ratio mask estimation using deep neural networks for robust speech recognition [C], 2013 IEEE International Coference on Acoustics, Speech and Aignal Processing, (2013)
[6] LIANG S, LIU W J, JIANG W, Et al., The optimal ratio time-frequency mask for speech separation in terms of the signal-to-noise ratio, The Joural of the Acoustical Society of America, 134, 5, pp. 452-458, (2013)
[7] ZHU Huijie, WANG Xinqing, RUI Ting, Et al., Shift invariant sparse coding for blind source separation of single channel mechanical signal [J], Journal of Vibration Engineering, 28, 4, pp. 625-632, (2015)
[8] HAO Y S, SONG L Y, WANG M Y, Et al., Underdetermined source separation of bearing faults based on optimized intrinsic characteristic-scale decomposition and local non-negative matrix factorization, IEEE Access, 7, pp. 11427-11435, (2019)
[9] YANG Guangzhen, JING Jianping, MING Yang, Et al., Blind vibration sources separation method based on signal feature of aircraft engine [J], Journal of Xi'an Jiaotong University, 51, 6, pp. 20-27, (2017)
[10] LIU Kunpeng, XIA Junzhong, BAI Yunchuan, Et al., Application of EDRS in blind source separation of rolling element bearing vibration signal [J], Jourmal of Vibration and Shock, 38, 20, pp. 106-111, (2019)

← 1 2 →