Rub-impact acoustic emission signal recognition of rotating machinery based on gaussian mixture model

被引：0
|
作者：
Deng A. [1 ]
Bao Y. [2 ]
Zhao L. [3 ]
机构：
[1] School of Energy and Environment, Southeast University
[2] School of Information Engineering, Nanjing Institute of Technology
[3] School of Information Science and Engineering, Southeast University
来源：
Jixie Gongcheng Xuebao/Journal of Mechanical Engineering | 2010年 / 46卷 / 15期
关键词：
Acoustic emission recognition; Cepstral coefficients; Fractal dimension; Gaussian mixture model;
D O I：
10.3901/JME.2010.15.052
中图分类号：
学科分类号：
摘要：
On the basis of modal acoustic emission and narrow-band signal theory, the mathematical expression of multi-modal AE signal is given. A mixed parameter composed of logarithm cepstral coefficients and fractal dimension is presented as the characteristic coefficients of rub-impact AE signal, and the AE recognition system based on Gaussian mixture model is also established. Because the eigenvector of each modal wave in rub-impact AE signal is different, so a model of probability density function of eigenvector is built and it is regarded as a clustering. Training model is established with mean, covariance matrix and probability of each clustering. Sum likelihood probability weighted by maximal ratio combining to likelihood probability of Gaussian model will be obtained when the tested signal is recognized, if the probability is larger than a set threshold, it can be confirmed that rub-impact AE is available. Rub impact AE signals are sampled from rotor test stand, the types of input model of Gaussian are sorted by AE waveform shapes and its fractal dimensions, then white noise and non-stationary noise are added to simulate the real AE signal. In the end, this Gaussian mixture model is used for AE recognition. The results indicate that the model has high recognition rate and good anti-noise ability. © 2010 Journal of Mechanical Engineering.
引用
收藏
页码：52 / 58
页数：6
相关论文
共 20 条
  • [1] Geng R., Evaluation of calendar damage of aircraft main structures using modal acoustic emission, Chinese Journal of Mechanical Engineering, 39, 9, pp. 128-132, (2003)
  • [2] Jin W., Chen C., Jin Z., Et al., Study on three parameter ratio method in AE source recognition, Chinese Journal of Scientific Instrument, 29, 3, pp. 530-534, (2008)
  • [3] Van D.G., Wevers M., van Hulle M.M., Wavelet packet decomposition for the identification of corrosion type from acoustic emission signals, International Journal of Wavelets, Multiresolution and Information Processing, 7, 4, pp. 513-534, (2009)
  • [4] Kalogiannakis G., Quintelier J., de Baets P., Et al., Identification of wear mechanisms of glass/polyester composites by means of acoustic emission, Wear, 264, 3, pp. 235-244, (2008)
  • [5] Dunegan H.L., Modal analysis of acoustic emission signals, Journal of Acoustic Emission, 15, 1, pp. 1-4, (1998)
  • [6] Kotnik B., Vlaj D., Kacic Z., Et al., Robust MFCC feature extraction algorithm using efficient additive and convolutional noise reduction procedures, ICSLP'02 Proceedings, pp. 455-448, (2002)
  • [7] Li C., Cepstrum-based analysis method for the auto correlation of rough surface profile, Chinese Journal of Mechanical Engineering, 40, 5, pp. 87-91, (2004)
  • [8] Song X., Ma H., Mao G., Et al., Fault diagnosis technique of rotating machine based on CHMM, Chinese Journal of Mechanical Engineering, 42, 5, pp. 126-130, (2006)
  • [9] Gong X., Wang H., MFCC feature extraction in noisy environments, Microcomputer Information, 23, 8, pp. 247-249, (2007)
  • [10] Chu D., Zhang Z., Wang G., Et al., Theory and experiment on the viscous heating of fluid damper under shock environment, Chinese Journal of Mechanical Engineering, 21, 3, pp. 66-71, (2008)
12