구조물의 품질 결함 변별력 증대를 위한 수직 에너지 기반의 웨이블릿 Feature 생성
Structural Quality Defect Discrimination Enhancement using Vertical Energy-based Wavelet Feature Generation
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In this paper a novel feature extraction and selection is carried out in order to improve the discriminating capability between healthy and damaged structure using vibration signals. Although many feature extraction and selection algorithms have been proposed for vibration signals, most proposed approaches don’t consider the discriminating ability of features since they are usually in unsupervised manner. We proposed a novel feature extraction and selection algorithm selecting few wavelet coefficients with higher class discriminating capability for damage detection and class visualization. We applied three class separability measures to evaluate the features, i.e. T test statistics, divergence, and Bhattacharyya distance. Experiments with vibration signals from truss structure demonstrate that class separabilities are significantly enhanced using our proposed algorithm compared to other two algorithms with original time-based features and Fourier-based ones.
Abstract
In this paper a novel feature extraction and selection is carried out in order to improve the discriminating capability between healthy and damaged structure using vibration signals. Although many feature extraction and selection algorithms have been proposed for vibration signals, most proposed approaches don’t consider the discriminating ability of features since they are usually in unsupervised manner. We proposed a novel feature extraction and selection algorithm selecting few wavelet coefficients with higher class discriminating capability for damage detection and class visualization. We applied three class separability measures to evaluate the features, i.e. T test statistics, divergence, and Bhattacharyya distance. Experiments with vibration signals from truss structure demonstrate that class separabilities are significantly enhanced using our proposed algorithm compared to other two algorithms with original time-based features and Fourier-based ones.
참고문헌 (13)
- Ambardar, A., "Analog and Digital Signal Processing" (1995), PWS Publishing Company
- Antoniadis, A., "Model selection using wavelet decomposition and applications", Biometrika, 42(4), pp.751~763 (1997)
- Duda, R.O., "Pattern Classification" (2001), Wiley
- Guyon, I., "An introduction to variable and feature selection", Journal of Machine Learning Research, 3, pp.1157~1182 (2003)
- Jung, U., "A vertical-energy-thresholding procedure for data reduction with multiple complex curves", IEEE Transactions on Systems Man and Cybernetics- Part B, 36(5), pp.1128~1138 (2006)
- Lie, J.S., "Bayesian clustering with variable and transformation selection", Bayesian Statistics, 7, pp.249~275 (2003)
- Law, S.S., "Structural damage detection from wavelet packet sensitivity", Engineering Structures, 27, pp.1339~1348 (2005)
- Li, Z., "Damage detection of cracked beams based on wavelet transform", International Journal of Impact Engineering, 32, pp.1190~1200 (2006)
- Li, H., "Structural damage detection using the combination method of EMD and wavelet analysis", Mechanical Systems and Signal Processing, 21, pp.298~306 (2007)
- Mallat, S.G., "A Wavelet Tour of Signal Processing" (1989), Academic Press
- Palacz, M., "Vibration parameters for damage detection in structures", Journal of Sound and Vibration, 249(5), pp.999~1010 (2002)
- A review of structural health monitoring literature: 1996~2001, "Sohn, H.", Los Alamos National Laboratory, ~, pp.Technical Reports LA-13976-MS (2003)
- Swamidas, A.S., "Monitoring crack growth through change of modal parameters", Journal of Sound and Vibration, 186(2), pp.325~343 (1995)