[1] Yu Jintao, Ding Mingli, Meng Fangang, et al. Acoustic emission source identificationbased on harmonic wavelet packet and support vector machine [J]. Journal of Southeast University (English Edition), 2011, 27 (3): 300-304. [doi:10.3969/j.issn.1003-7985.2011.03.015]

Copy

Acoustic emission source identificationbased on harmonic wavelet packet and support vector machine()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

27

Issue:

2011 3

Page:

300-304

Research Field:

Materials Sciences and Engineering

Publishing date:

2011-09-30

Info

Title:

Acoustic emission source identificationbased on harmonic wavelet packet and support vector machine

Author(s):

Yu Jintao¹;  2;  Ding Mingli¹;  Meng Fangang³;  Qiao Yuliang³;  Wang Qi¹

¹ Department of Automatic Measurement and Control, Harbin Institute of Technology, Harbin 150001, China
² School of Computer and Information Engineering, Harbin University of Commerce, Harbin 150028, China
³ Harbin

Keywords:

harmonic wavelet packet;  hierarchy support vector machine;  acoustic emission source identification

PACS:

TG115.28

DOI:

10.3969/j.issn.1003-7985.2011.03.015

Abstract:

In order to solve the fatigue damage identification problem of helicopter moving components, a new approach for acoustic emission(AE)source type identification based on the harmonic wavelet packet(HWPT)feature extraction and the hierarchy support vector machine(H-SVM)classifier is proposed. After a four-level decomposition of the HWPT, the energy feature of AE signals in different frequency bands is extracted, which overcomes the shortcomings of the traditional wavelet packet including energy leakage, and inflexible frequency band selection and different frequency resolutions on different levels. The H-SVM classifier is trained with a subset of the experimental data for known AE source types and tested using the remaining set of data. The results of pressure-off experiments on the specimens of carbon fiber materials indicate that the proposed approach can effectively implement the AE source type identification, and has a better performance in terms of computational efficiency and identification accuracy than the wavelet packet(WPT)feature extraction.

References:

[1] Tittmann B R, Yen C E. Acoustic emission technique for monitoring the pyrolysis of composites for process control [J]. Ultrasonics, 2008, 48(6/7): 621-630.
[2] Liu Q, Chen X. Fuzzy pattern recognition of AE signals for grinding burn [J]. Machine Tools & Manufacture, 2005, 45(7/8): 811-818.
[3] Zhou Rui, Bao Wen, Li Ning, et al. Mechanical equipment fault diagnosis based on redundant second generation wavelet packet transform [J]. Digital Signal Processing, 2010, 20(1): 276-288.
[4] Feng Zhigang, Wang Qi, Shida K. Design and implementation of a self-validating pressure sensor[J]. IEEE Sensors Journal, 2009, 9(3): 207-218.
[5] Zhang Wenbin, Zhou Xiaojun, Lin Yong, et al. Harmonic wavelet package method used to extract fault signal of a rotation machinery[J]. Journal of Vibration and Shock, 2009, 28(3): 87-89.(in Chinese)
[6] Zhao Yuanxi, Xu Yonggang, Gao Lixin, et al. Fault pattern recognition technique for roller bearing acoustic emission based on harmonic wavelet packet and BP neural network[J]. Journal of Vibration and Shock, 2010, 29(10): 162-165;257.(in Chinese)
[7] Emamian V, Kaveh M, Tewfik A H, et al. Robust clustering of acoustic emission signals using neural networks and signal subspace projections [J]. EURASIP Journal on Applied Signal Processing, 2003, 2003(3): 276-286.
[8] Newland D E. Harmonic wavelet analysis [J]. Proceedings of the Royal Society A, 1993, 443(1917): 203-225.
[9] Newland D E. Wavelet analysis of vibration, part 1: theory [J]. Journal of Vibration and Acoustic, 1994, 116(4): 409-416.
[10] Newland D E. Wavelet analysis of vibration, part 2: wavelet map [J]. Journal of Vibration and Acoustic, 1994, 116(4): 417-425.
[11] Qian Huimin, Mao Yaobin, Xiang Wenbo, et al. Recognition of human activities using SVM multi-class classifier [J]. Pattern Recognition Letters, 2010, 31(2): 100-111.
[12] Avci D, Varol A. An expert diagnosis system for classification of human parasite eggs based on multi-class SVM [J]. Expert Systems with Applications, 2009, 36(1): 43-48.
[13] Anand J R, Mehrotra K, Mohan C K, et al. Efficient classification for multiclass problems using modular neural networks [J]. IEEE Transactions on Neural Networks, 1995, 6(1): 117-124.
[14] Kumar S, Ghosh J, Crawford M M. Hierarchical fusion of multiple classifiers for hyper spectral data analysis [J]. Pattern Analysis and Applications, 2002, 5(2): 210-220.

Memo

Memo:

Biographies: Yu Jintao(1974—), male, graduate; Wang Qi(corresponding author), male, master, professor, wangqi@hit.edu.cn.
Foundation items: The Natural Science Foundation of Heilongjiang Province(No.F201018), the National Natural Science Foundation of China(No.60901042).
Citation: Yu Jintao, Ding Mingli, Meng Fangang, et al. Acoustic emission source identification based on harmonic wavelet packet and support vector machine[J].Journal of Southeast University(English Edition), 2011, 27(3):300-304.[doi:10.3969/j.issn.1003-7985.2011.03.015]

Common functions