Eddy Currents Signatures Classification by Using Time Series: a System Modeling Approach

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Sep 29, 2014
Blaise Gue ́pie ́ Mihaly Petreczky Ste ́phane Lecoeuche

Abstract

Non destructive testing methods are often used in order to de- tect and classify structural flaws. The detection of structural flaws is useful for maintenance. In this paper we propose to classify flaws in ferromagnetic materials by measuring Eddy currents. Our approach consists of two steps. First, we use a system identification algorithm to find a dynamical system which describes the data. Then, we use the parameters of this dynamical system as a feature vector and we use support vector machines in order to classify the various cracks. We test our method on a well-known benchmark.

How to Cite

Gue ́pie ́ B. ., Petreczky, M. ., & Lecoeuche S. ́. . (2014). Eddy Currents Signatures Classification by Using Time Series: a System Modeling Approach. Annual Conference of the PHM Society, 6(1). https://doi.org/10.36001/phmconf.2014.v6i1.2343
Abstract 134 | PDF Downloads 127

##plugins.themes.bootstrap3.article.details##

Keywords

predictive maintenance, dynamical model, system identification, Eddy currents

References
Cantrell, J. H., & Yost, W. T. (2001). Nonlinear ultrasonic characterization of fatigue microstructures. International Journal of Fatigue, 23, Supplement 1(0), 487 -
490.

Caruana, R., & Niculescu-Mizil, A. (2006). An empirical comparison of supervised learning algorithms. In Proceedings of the 23rd international conference on ma- chine learning (pp. 161–168). New York, NY, USA: ACM. doi: 10.1145/1143844.1143865

Clark, M., McCann, D., & Forde, M. (2003). Application of infrared thermography to the non-destructive testing of concrete and masonry bridges. Ndt & E International, 36(4), 265–275.

Elaqra, H., Godin, N., Peix, G., R’Mili, M., & Fantozzi, G. (2007). Damage evolution analysis in mortar, during compressive loading using acoustic emission and x-ray tomography: Effects of the sand/cement ratio. Cement and Concrete Research, 37(5), 703 - 713.

Jie, L., Siwei, L., Qingyong, L., Hanqing, Z., & Shengwei, R. (2009, July). Real-time rail head surface defect detection: A geometrical approach. In Industrial electronics, 2009. isie 2009. ieee international symposium on (p. 769-774).

Jo, N. H., & Lee, H.-B. (2009). A novel feature extraction for eddy current testing of steam generator tubes. {NDT} & E International, 42(7), 658 - 663.

Khelil, M., Boudraa, M., Kechida, A., & Drai, R. (2005). Classification of defects by the svm method and the principal component analysis (pca). World Acad. Sci. Eng. Technol, 9, 226–231.

Lingvall, F., & Stepinski, T. (2000). Automatic detecting and classifying defects during eddy current inspection of riveted lap-joints. {NDT} & E International, 33(1), 47 - 55.

Liu, B., Hou, D., Huang, P., Liu, B., Tang, H., Zhang, W., . . . Zhang, G. (2013). An improved pso-svm model for online recognition defects in eddy current testing. Non-
destructive Testing and Evaluation, 28(4), 367-385.

Ljung, L., & So ̈derstro ̈m, T. (1983). Theory and practice of recursive identification. MIT press Cambridge, MA. Madaras, E. I., Prosser, W. H., & Gorman, M. R. (2005). Detection of impact damage on space shuttle structures using acoustic emission. In Review of progress in quantitative nondestructive evaluation: Volume 24
(Vol. 760, pp. 1113–1120).

Mercer, J. (1909). Functions of positive and negative type,and their connection with the theory of integral equations. Philosophical Transactions of the Royal Society, London, 209, 415–446.
Moreira, M., & Mayoraz, E. (1998). Improved pairwise coupling classification with correcting classifiers. In Machine learning: Ecml-98 (pp. 160–171). Springer.

Němec, H., Kužel, P., Garet, F., & Duvillaret, L. (2004). Time-domain terahertz study of defect formation in one-dimensional photonic crystals. Applied optics, 43(9), 1965–1970.

Oukhellou, L., Aknin, P., & Perrin, J.-P. (1999). Dedicated sensor and classifier of rail head defects. Control Engineering Practice, 7(1), 57 - 61.

Smid, R., Docekal, A., & Kreidl, M. (2005). Automated classification of eddy current signatures during manual inspection. NDT & E International, 38(6), 462–470.

Song, S.-J., & Shin, Y.-K. (2000). Eddy current flaw characterization in tubes by neural networks and finite element modeling. {NDT} & E International, 33(4), 233 - 243.

Vapnik, V. (2000). The nature of statistical learning theory. Springer.

Ye, B., Huang, P., Fan, M., Gong, X., Hou, D., Zhang, G., & Zhou, Z. (2009). Automatic classification of eddy current signals based on kernel methods. Nondestructive
Testing and Evaluation, 24(1-2), 19–37.
Section
Poster Presentations