Separation of Weak MultiSource Fault Acoustic Emission Signals Based on Wavelet Packet and Independent Component Analysis

Abstract

Abstract: Abstract： Multisource fault signals (such as crack and friction signals) produced from rotating machinery are difficult to detect and separate; therefore, an extraction method of multisource fault signals based on wavelet packet analysis (WPA) and independent component analysis (ICA) was proposed. The wavelet packet technology was used to reduce the noise outside the frequency band of the linear mixed signals. The signals were decomposed by db2 wavelet into five layers while the signals with the frequency band from 62.5 to 187.5 kHz were reserved. Then, the mixed signals were separated by using the FastICA algorithm. Finally, the shrinkage function was used to reduce the noise in the frequency band. By extracting the noisy weak signals with different input SNRs, the results show that this method can effectively extract the crack and the friction signals with the input SNR higher than -15 dB. Their output SNRs are -1.31 and -1.36 dB and the correlation coefficients are 0.62 and 0.63, respectively, which are higher than those obtained by using the method combined WPA and FastICA and only FastICA algorithm. The SNRs are (-1.74 and -2.06 dB) and (-4.57,-4.31 dB) and correlation coefficients are (0.59,0.59) and (0.17,0.19) for the combined method and FastICA method, respectively. Thus, the method is very suitable for extraction and separation of multisource weak signals.

Key words: Key words： multi-source separation, wavelet packet analysis (WPA), independent component analysis (ICA), de-noising

CLC Number:

WANG Xianghong1a,1b,YIN Dong1a,HU Hongwei1a,MAO Hanling2. Separation of Weak MultiSource Fault Acoustic Emission Signals Based on Wavelet Packet and Independent Component Analysis[J]. Journal of Shanghai Jiaotong University, 2016, 50(05): 757-763.

References

［1］王国彪，何正嘉，陈雪峰，等. 机械故障诊断基础研究“何去何从”［J］. 机械工程学报，2013, 49(1):6372. WANG Guobiao, HE Zhengjia, CHEN Xuefeng, et al. Basic research on machinery fault diagnosis—what is the prescription［J］. Journal of Mechanical Engineering, 2013, 49(1):6372. ［2］艾延廷，费成巍，张凤玲，等. ICA在航空发动机振动信号盲源分离中的应用［J］. 振动、测试与诊断，2010, 30(6):671674. AI Yanting, FEI Chengwei, ZHANG Fengling, et al. Blind source separation for aeroengines vibration signal by independent component analysis［J］. Journal of Vibration, Measurement & Diagnosis, 2010, 30(6):671674. ［3］SANTOSA H, HONG M J, KIM S P, et al. Noise reduction in functional nearinfrared spectroscopy signals by independent component analysis［J］. Review of Scientific Instruments, 2013, 84(7):073106.［4］NAIK G R. An overview of independent component analysis and its applications［J］. Informatica, 2011, 35(1):6381. ［5］HYVARINEN A. Independent component analysis in the presence of Gaussian noise by maximizing joint likelihood［J］. Neurocomputing, 1998, 22(1/2/3):4967. ［6］刘清坤，阙沛文，郭华伟，等. 基于相空间重构和独立分量分析的超声信号噪声消除［J］. 上海交通大学学报,2006,40(10):17391742. LIU Qingkun, QUE Peiwen, GUO Huawei, et al. The noise cancellation for ultrasonic signals using reconstructed phase space and independent component analysis［J］. Journal of Shanghai Jiao Tong University, 2006,40(10):17391742. ［7］沈功田，李金海. 压力容器无损检测——声发射检测技术［J］. 无损检测，2004, 26(9):457463. SHEN Gongtian, LI Jinhai. Nondestructive inspection of pressure vessels: Acoustic emission technique［J］. Nondestructive Testing, 2004, 26(9): 457463. ［8］李欣，梅德庆，陈子辰. 基于ICA的镗削过程颤振征兆信号分离方法研究［J］. 振动与冲击，2013, 32(9):59. LI Xin, MEI Deqing, CHEN Zichen. ICA based separation of chatter symptom signals for precision hole boring processing［J］. Journal of Vibration and Shock, 2013, 32(9):59. ［9］张和发，李立萍，杨小牛，等. 一种适用于微弱信号盲提取的白化方法［J］.电子学报，2011, 39(6):12971301. ZHANG Hefa, LI Liping, YANG Xiaoniu, et al. An efficient whitening method for weak signal extraction ［J］. Acta Electronica Sinica, 2011, 39(6): 12971301. ［10］HYVARINEN A. Fast and robust fixed point algorithms for independent component analysis［J］. IEEE Transactions on Neural Networks, 1999, 10(3): 626634. ［11］唐峰, 孙锬锋, 蒋兴浩,等. 基于改进稀疏编码模型的图像分类算法［J］.上海交通大学学报, 2012, 46(9):14061410. TANG Feng, SUN Tanfeng, JIANG Xinghao, et al. Image categorization algorithm based on improved sparse coding mode［J］. Journal of Shanghai Jiao Tong University, 2012, 46(9):14061410. ［12］ASTM. ASTM E97699: Standard guild for determining the reproducibility of acoustic emission sensor response［S］. Pennsylvania, US: American Society for Testing, 1999:395403.

[1]	CUI Yan* (崔妍), CHEN Shijun (陈世均), QU Meng (瞿勐), HE Shanhong (何善红). Research and Application of New Threshold De-noising Algorithm for Monitoring Data Analysis in Nuclear Power Plant [J]. Journal of shanghai Jiaotong University (Science), 2017, 22(3): 355-360.
[2]	BAI Caijuan1,LIU Jing1,JIANG Xiaoyu2,ZHANG Guoxian1,HUANG Kaiyu1. The Reconstruction of Digital Holography Based on Iterative De-Noising Shrinkage-Thresholding Algorithm [J]. Journal of Shanghai Jiaotong University, 2017, 51(12): 1435-1442.
[3]	WANG Yukui1,2* (王余奎), HUANG Zhijie1 (黄之杰), ZHAO Xucheng1 (赵徐成), ZHU Yi1 (朱毅), WEI Dongtao1 (魏东涛). A Novel De-noising Method Based on Discrete Cosine Transform and Its Application in the Fault Feature Extraction of Hydraulic Pump [J]. Journal of shanghai Jiaotong University (Science), 2016, 21(3): 297-306.
[4]	XIE Wei-Sheng, YANG Gen-Ke. An Adaptive Speech Signal De-noising Algorithm Based on Estimation of Scaled Noise Energy [J]. Journal of Shanghai Jiaotong University, 2012, 46(09): 1445-1449.
[5]	PAN Cheng，TIAN Sheping，YAN Guozheng . Overdetermined ICA and Its Application on the Analysis of Human Colonic Pressure Signals [J]. Journal of Shanghai Jiaotong University, 2010, 44(11): 1595-1599.