Solís M.+, Benítez-Pérez H. +*, Rubio E.+, Medina-Gómez L.+, Moreno E.**, Gonzalez G.++ , Leija L.++
+ DISCA, IIMAS, UNAM, Apdo. Postal 20-726. Admón. No. 20. Del. A. Obregón, México D.F., CP. 01000, México.
++ Sección de Bioelectrónica, Departamento de Ingeniería Eléctrica, CINVESTAV, México.
** Ultrasonic Center, Institute of Cybernetic Mathematics and Physics, La Habana, Cuba.
Fax: ++52 (55) 5616 01 76, Tel: (*) ++52 (55) 5622 36 39
Email: (*) hector@uxdea4.iimas.unam.mx (contact author)
]]> (**)moreno@cidet.icmf.inf.cu
ABSTRACT
The Ultrasonic Pulse-Echo technique has been successfully used in a non-destructive testing of materials. To perform Ultrasonic Non-destructive Evaluation (NDE), an ultrasonic pulsed wave is transmitted into the materials using a transmitting/receiving transducer or arrays of transducers,that produces an image of ultrasonic reflectivity. The information inherent in ultrasonic signals or image are the echoes coming from flaws, grains, and boundaries of the tested material. The main goal of this evaluation is to determine the existence of defect, its size and its position; for that matter, an innovative methodology is proposed based on pattern recognition and wavelet analysis for flaws detection and localization.
The pattern recognition technique used in this work is the neural network named ART2 (Adaptive Resonance Theory) trained by the information given by the time-scale information of the signals via the wavelet transform. A thorough analysis between the neural network training and the type wavelets used for the training has been developed, showing that the Symlet 6 wavelet is the optimum for our problem.
Keywords: Pattern recognition, ART2 Networks, Wavelets coefficients, NDT, Defect Location.
DESCARGAR ARTÍCULO EN FORMATO PDF
6. ACKNOWLEDGEMENTS
]]> The authors would like to thank the financial support of PAPIIT-UNAM (IN106100), CONACYT-31959A, Mexico in connection with this work. Furthermore, authors gratefully acknowledge fruitful discussions with Dr. Arturo Juarez from CIATEQ Mexico.
7. REFERENCES
[1] Abbate, A., Koay, H., Frankel, J., Schroeder, S., and Das, P.; "Signal Detection and Noise Suppression Using a Wavelet Transform Signal Processor: Application to Ultrasonic Flaw Detection"; IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, Vol. 44, No. 1, pp. 14-26, January 1997. [ Links ]
[2] Angrisani, L. Daponte, P., and Dápuzzo M.; "Wavelet Network-Based Detection and Classification of Transients"; IEEE Transactions on Instrumentation and Measurement, vol. 50, No. 5, pp: 1425-1435, 2001. [ Links ]
[3] Carpenter, G. A., and Grossberg, S.; "ART2: Self organization of stable recognition codes for analog input patterns"; Appl. Opt., vol. 26, no. 23, pp. 4919-4930, 1987. [ Links ]
[4] Ciftcioglu, Ö.; "From Neural to Wavelet Network"; IEEE, NAFIPS, 18th International Conference of the North American, pp: 894-898, 1999. [ Links ]
[5] Demirli, R., and Samiie, J.; "Model-Based Estimation of Ultrasonic Echoes Part I: Analysis and Algorithms"; IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, Vol. 48, No. 3, pp. 787-802, 2001a. [ Links ]
[6] Demirli, R., and Samiie, J.; "Model-Based Estimation of Ultrasonic Echoes Part II: Nondestructive Evaluation Applications"; IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, Vol. 48, No. 3, pp. 803-811, 2001b. [ Links ]
[7] Fang Y., and Chow T.; "Orthogonal Wavelet Neural Networks Applying to Identification of Wiener Model"; IEEE Transactions on Circuits and Systems-I: Fundamental Theory and Applications, Vol. 47, No. 4, pp. 591-593, 2000. [ Links ]
[8] Frank, T., Kraiss K. F., and Kuhlen, T.; "Comparative Analysis of Fuzzy ART and ART-2A Network Clustering Performance"; IEEE Transactions on Neural Networks, Vol. 9, No. 3, May, 1998. [ Links ]
[9] Frazier M.; "An Introduction to Wavelets Through Linear Algebra"; Springer-Verlag, 1999. [ Links ]
[10] Kirby, M.; "Geometric Data Analysis"; John Wiley and Sons, Canada, 2001. [ Links ]
[11] Legendre S., Goyette J., and Massicotte D.; "Ultrasonic NDE of Composite material Structures using Wavelet Coefficients"; NDT & E International, No. 34, pp. 31-37, 2001. [ Links ]
[12] Lester W. and Schmerr Jr.; "Fundamentals of Ultrasonic Nondestructive Evaluation"; Plenum Press, USA, 1998. [ Links ]
[13] Moisen M., Benítez H., Medina L., Moreno E., González G., and Leija L.; "ARTMAP Network and Wavelet Analysis for Flaws Characterization"; 16TH World Conference on Nondestructive Testing, 2004. [ Links ]
[14] Solis M., Benítez-Pérez H., Rubio E., Medina-Gómez L.; "Pattern Recognition of Wavelet Decomposition using ART2A Networks for echoes Analysis"; IEEE Ultrasonic Symposium, pp. 679-682, 2001. [ Links ]
[15] Solís M., Benítez H., and Medina L.; "Location of Material Flaws using Wavelet Analysis and Neural Networks";IEEE Ultrasonic Symposium, pp. 841-844, 2002. [ Links ]
[16] Tan, Y., Dang, X., Liang, F., and Su, C. ; "Dynamic Wavelet Network for Nonlinear Dynamic System Identification"; Proceedings of the IEEE International Conference on Control Applications, pp: 214-219, 2000. [ Links ]
[17] Vachtsevanos G., and Wang P. ; "A Wavelet Neural Network Framework For Diagnostics of Complex Engineered Systems"; IEEE, Proceedings of International Symposium of Intelligent Control, pp. 79-84, September, 2001. [ Links ]
[18] Whiteley, J., Davis, J., Mehrotra, A., and Ahalt, S.; "Observations and Problems Applying ART2 for Dynamic Sensor Pattern Interpretation"; IEEE Transactions on Systems, Man, and Cybernetics- Part A: Systems and Humans, Vol. 26, No. 4, July 1996. [ Links ]
[19] Yu, Y., Tan, S., Vandewalle, J., and Deprettere E.; "Near-Optimal Construction of Wavelet Networks for Nonlinear System Modeling"; IEEE International Symposium on Circuits and Systems, ISCAS, Volume: 3, pp: 48 -51, 1996. [ Links ]
]]>