SciELO - Scientific Electronic Library Online

 
vol.6 issue1An Automatic Test Environment for Microelectronics Education and ReserchPattern Classification of Decomposed Wavelet Information using ART2 Networks for echoes Analysis author indexsubject indexsearch form
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

  • Have no similar articlesSimilars in SciELO

Share


Journal of applied research and technology

On-line version ISSN 2448-6736Print version ISSN 1665-6423

J. appl. res. technol vol.6 n.1 Ciudad de México Apr. 2008

 

Diverse Time-Frequency Distributions Integrated to an ART2 Network for Non-Destructive Testing

 

Benítez–Pérez H.,1 y Medina–Gómez L.2

 

1 Departamento de Ingeniería de Sistemas Computacionales y Automatización, IIMAS, UNAM, Apdo. Postal 20-726, Del. A. Obregón, México D. F., CP. 01000, México. Email: (*) hector@uxdea4.iimas.unam.mx

2 Departamento de Física, Facultad de Ciencias, UNAM, Apdo. Postal 20-726 Fax: ++52 55 5616 01 76, Tel: (*) ++52 55 5622 36 23

 

ABSTRACT

The use of several techniques for non-destructive testing is a common strategy for detecting and classifying flaws in aluminium material. Techniques like multiresolution data analysis and data classifiers are valuable for obtaining as much information as possible from the flaws. The combination of both techniques allows the clear definition of several characteristics like localization, size and form. In this study, localization using Time-Frequency Distribution feature extraction and an ART2 neural network as a classifier is the main goal.

Keywords: Non-destructive Testing, Neural Networks, Time Frequency Distribution Approach.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

8. ACKNOWLEDGMENTS

The authors thank the financial support of PAPIIT-UNAM (IN106100 and IN105303), Mexico in connection with this work. Furthermore, the authors gratefully acknowledge fruitful discussions with Dr. Arturo Juarez from CIATEQ, Mexico.

 

9. REFERENCES

[1] Angrisani, L., Daponte, P., and Dápuzzo, M., Wavelet Network-Based Detection and Classification of Transients, IEEE Transactions on Instrumentation and Measurement, 2001, 50, 1425-1435.         [ Links ]

[2] Baraldi, A.,. and Blonda, P., A Survey of Fuzzy Clustering Algorithms for Pattern Recognition-Part I, IEEE Transactions on Systems, Man and Cybernetics- Part B: Cybernetics, 1999, 29, 778-785.         [ Links ]

[3] Benítez-Pérez H., Rubio-Acosta, E., Medina L. and García-Nocetti F., A Bessell Time Frequency Distribution and ART2 Network approach in Non Destructive Evaluation World Congress of Ultrasound; WCU, 2003 France, October.         [ Links ]

[4] Carpenter, G. A., and Grossberg, S., ART2: Self organization of stable recognition codes for analog input patterns, Appl. Opt., 1987, 26, 23, 4919-4930.         [ Links ]

[5] Ciftcioglu, Ö., From Neural to Wavelet Network, IEEE, NAFIPS, 18th International Conference of the North American, 1999, 894-898.         [ Links ]

[6] Cohen L., Time-Frequency Distributions- A Review, Proceedings of the IEEE, 1989, 77, 941-981.         [ Links ]

[7] Demirli, R., and Samiie, J., Model-Based Estimation of Ultrasonic Echoes Part II: Nondestructive Evaluation Applications, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2001a, 48, 3, 803-811.         [ Links ]

[8] Demirli, R., and Samiie, J., Model-Based Estimation of Ultrasonic Echoes Part I: Analysis and Algorithms, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2001 b, 48, 3, 787-802.         [ Links ]

[9] 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, 2000, 47, 4, 591-593.         [ Links ]

[10] Frank, T., Kraiss, K. F., and Kuhlen, T., Comparative Analysis of Fuzzy ART and ART-2A Network Clustering Performance, IEEE Transactions on Neural Networks, 1998, 9, 3, May.         [ Links ]

[11] Frosberg F., Oung H., and Needleman L., Doppler Spectral Estimation Using Time-Frequency Distributions, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control, 1999, 46, 3.         [ Links ]

[12] Garcia-Nocetti F., Solano-Gonzalez J., Rubio-Acosta E., and Moreno-Hernandez E., Fast Computation of Time Frequency Distributions using Parallel DSP-Based System for Signal Analysis, IFAC Conference on New Technologies for Computer Control, 2001, Hong Kong, 187-192.         [ Links ]

[13] Kirby, M., Geometric Data Analysis, John Wiley and Sons, 2001, Canada.         [ Links ]

[14] Legendre S., Goyette J., and , Massicotte D., Ultrasonic NDE of Composite material Structures using Wavelet Coefficients, NDT & E International, 2001, 34, 31-37.         [ Links ]

[15] Lester W. and Schmerr Jr., Fundamentals of Ultrasonic Nondestructive Evaluation, Plenum Press, 1998, USA.         [ Links ]

[16] Martin W. and Flandrin P., Wigner-Ville Spectral Analysis of Nonstationary Processes, IEEE Transactions on Acoustics, Speech, and Signal Processing, 1985, ASSP-33., 6, 1461-1470.         [ Links ]

[17] Mitra S., Digital Signal Processing, McGraw-Hill, 2001 USA.         [ Links ]

[18] Moisen, M., H. Benítez, L. Medina, E. Moreno, G. González, and L. Leija, ARTMAP NETWORK AND WAVELET ANALYSIS FOR FLAWS CHARACTERIZATION, 16th World Conference on Nondestructive Testing, 2004, Toronto, Canada.         [ Links ]

[19] Moya E., Sainz, G. I., Grande, B., Fuente M. J., and Perán J., Neural PCA Based Fault Diagnosis, Proceedings of the European Control Conference, 2001, 809-813, Oporto, Portugal.         [ Links ]

[20] Oppenheim A., and Schafer R., Discrete-Time Signal Processing, Prentice Hall, 1999.         [ Links ]

[21] Solís M., Benítez-Pérez H., Moreno E., Medina L., Gonzalez.G., Pattern Recognition of Wavelets Decomposition using ART2 Networks for echoes Analysis, IEEE International Ultrasonics Symposium, 2002, Munich, Germany, October.         [ Links ]

[22] Solis, M.; Benitez-Perez, H.; Rubio, E.; Medina-Gomez, L.; Moreno-Hernandez, E., Pattern recognition of wavelets decomposition using ART2 networks for echoes analysis, Ultrasonics Symposium, 2001 IEEE, 2001, 1, 679-682.         [ Links ]

[23] Tang 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, 2000, 214-219.         [ Links ]

[24] Vachtsevanos, G., and Wang P., A Wavelet Neural Network Framework For Diagnostics of Complex Engineered Systems, IEEE, Proceedings of International Symposium of Intelligent Control, 2001, 79-84, September.         [ Links ]

[25] Whiteley, J., Davis, 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, 1996, 26, 4, July.         [ Links ]

[26] Yu, Y., and 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, 1996, 3, 48 -51.         [ Links ]

Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License