Evaluación de Daño en Uniones Adhesivas mediante Descomposición Wavelet de Señales Acústicas y Clasificación con Algoritmos de Inteligencia Artificial
Palabras clave:
Uniones adhesivas, descomposición wavelet, aprendizaje automáticoResumen
Los adhesivos estructurales son una alternativa a las uniones tradicionales, pero su integridad puede verse afectada por defectos en la aplicación o el curado. Para garantizar su fiabilidad, es esencial aplicar técnicas de evaluación no destructiva (END), donde los métodos acústico-ultrasónicos resultan especialmente útiles. Este trabajo propone un enfoque basado en la descomposición wavelet de señales acústicas para extraer características que permitan, mediante algoritmos de inteligencia artificial, la detección automática de daños en uniones adhesivas. La metodología busca mejorar la precisión en la identificación de fallas y aportar una herramienta eficiente para el monitoreo estructural.
Citas
Alzarooni, A., Iqbal, E., Khan, S.U., Javed, S., Moyo, B., Abdulrahman, Y., Anomaly Detection for Industrial Applications, Its Challenges, Solutions, and Future Directions: A Review. IEEE Sens. J. VOL XX NO XX XXXX 2024 XX. 2024
Bhat, G.A., Smagulova, D., Jasiuniene, E., Improved Defect Sizing in Adhesive Joints Through Feature-Based Data Fusion. J. Nondestruct. Eval. 44, 14. https://doi.org/10.1007/s10921-024-01146-w. 2025
Carone, S., Pappalettera, G., Casavola, C., De Carolis, S., Soria, L., A Support Vector Machine-Based Approach for Bolt Loosening Monitoring in Industrial Customized Vehicles. Sensors 23. https://doi.org/10.3390/s23115345. 2023
Casaburo, A., Decision trees-based methods for the identification of damages in strongly damped plates for aerospace applications. Aeronaut. Astronaut. https://doi.org/10.21741/9781644902813-32. 2023
Daubechies, I., Ten Lectures on Wavelets. Society for Industrial and Applied Mathematics. https://doi.org/10.1137/1.9781611970104. 1992
Huynh, H.H., Min, C.-H., 2024. Rotating Machinery Fault Detection Using Support Vector Machine via Feature Ranking. Algorithms 17. https://doi.org/10.3390/a17100441. 2024
L. De Souza, D., H. Granzotto, M., M. De Almeida, G., C. Oliveira-Lopes, L., Fault Detection and Diagnosis Using Support Vector Machines - A SVC and SVR Comparison. J. Saf.Eng. 3, 18–29. https://doi.org/10.5923/j.safety.20140301.03. 2014
Mallat, S.G.,. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans. Pattern Anal. Mach. Intell. 11, 674–693. https://doi.org/10.1109/34.192463. 1989
Moloi, K., Hamam, Y., Jordaan, J.A., A Support Vector Machine Based Technique for Fault Detection in A Power Distribution Integrated System with Renewable Energy Distributed Generation. Adv. Sci. Technol. Eng. Syst. J. 5, 577–588. https://doi.org/10.25046/aj050468. 2020
Nair, A., Cai, C.S., 2010. Acoustic emission monitoring of bridges: Review and case studies. Eng. Struct. 32, 1704–1714. https://doi.org/10.1016/j.engstruct.2010.02.020. 2010
Nordin, M.M., Davies, O., Che Ahmad, M.M., Razali, S.M., Abdullah, M.Z., Towards Reliable Adhesive Bonding: A Comprehensive Review of Mechanisms, Defects, and Design Considerations. Materials 18, 2724. https://doi.org/10.3390/ma18122724. 2025
Pooja, H., Soma, S., Machine Learning System for Fabric Defect Detection and Classification. J. Neonatal Surg. 14, 11–20. https://doi.org/10.52783/jns.v14.2488. 2025
Qu, L., Pei, Y., A Comprehensive Review on Discriminant Analysis for Addressing Challenges of Class-Level Limitations, Small Sample Size, and Robustness. Processes 12. https://doi.org/10.3390/pr12071382. 2024
Rajini, G.K., 2016. A comprehensive review on waveelet transform and its applications. ARPN J. Eng. Appl. Sci. 11. 2016
Ren, Z., Fang, F., Yan, N., Wu, Y., State of the Art in Defect Detection Based on Machine Vision. Int. J. Precis. Eng. Manuf.-Green Technol. 9, 661–691. https://doi.org/10.1007/s40684-021-00343-6. 2022
Rocha, R.C.N., Soares, R.A., Santos, L.I., Camargos, M.O., Ekel, P.Ya., Libório, M.P., dos Santos, A.C.G., Vidoli, F., D’Angelo, M.F.S.V., A New Fault Classification Approach Based on Decision Tree Induced by Genetic Programming. Processes 12. https://doi.org/10.3390/pr12040818. 2024.
Tais, C., Fontana, J.M., Molisani, L., O’Brien, R., Ballesteros, Y., Carretero, R.C., del Real-Romero, J.C., Flaw classification in bonded joints using multivariate statistical analysis and artificial intelligence. Int. J. Adhes. Adhes. 140, 104032. 2025
Tais, C., Fontana, J.M., Molisani, L., OBrien, R., Ballesteros, Y., Del Real Romero, J.C., Fault Detection by Acoustic Signals in Adhesive Joints Using Artificial Neural Networks. Presented at the 14th European Adhesion Conference & 7th World Congress on Adhesion and Related Phenomena, Kongresshaus Garmisch-Partenkirchen. 2023.
Zubayer, H., Zhang, C., Wang, Y., Deep Learning-Based Automatic Defect Detection of Additive Manufactured Stainless Steel. Metals 13. 2023.
Descargas
Publicado
Número
Sección
Licencia
Derechos de autor 2025 Asociación Argentina de Mecánica Computacional
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Esta publicación es de acceso abierto diamante, sin ningún tipo de costo para los autores ni los lectores.
Solo se publicarán aquellos trabajos que han sido aceptados para su publicación y han sido presentados en el congreso de AMCA.
