PSI - Issue 71

Rakesh Kumar Sahu et al. / Procedia Structural Integrity 71 (2025) 203–209

209

5. Conclusion In this study feed forward, neural network is applied to predict the severity of damage such as numbers of damage, width of damage and location of damage present in isotropic Al beam. A tone burst excitation is used to generate Lamb waves in the structure and the severity of the damage is quantified using DI. Some important conclusions are discussed as follows: ● Anti-symmetric wave mode converted into one symmetric mode and one anti-symmetric mode after the interaction with a single damage. Whereas two symmetric modes are generated in case of two damage. ● The neural network algorithm achieved 98% accuracy in the case of single damage whereas 99% for two damage in the AL beam. ● In the case of single damage severity prediction, the width prediction accuracy of 12 mm damage is 100% and for 10 mm damage is 98.55%. whereas location prediction of 12 mm damage is 97% and for 10 mm damage is 90%, which represents the higher accuracy for larger size damage. ● In the case of multiple damage severity prediction, the width prediction accuracy is 99.99% whereas location prediction accuracy for first damage is 97.54% and 98.66% for second damage, which represents high accuracy and promising neural network-based methodology. References Agrahari, J. K., and Kapuria, S. 2016. A refined Lamb wave time-reversal method with enhanced sensitivity for damage detection in isotropic plates. Journal of Intelligent Material Systems and Structures, 27(10), 1283 – 1305. Nandyala AR, Darpe AK, Singh SP. Damage severity assessment in composite structures using multi-frequency lamb waves. Structural Health Monitoring. 2022;21(6):2834-2850. Ewald, V., Groves, R. M., and Benedictus, R. 2019. DeepSHM: a deep learning approach for structural health monitoring based on guided Lamb wave technique. 19. Hua, J., Cao, X., Yi, Y., and Lin, J. 2020. Time-frequency damage index of Broadband Lamb wave for corrosion inspection. Journal of Sound and Vibration, 464. Kapuria, S., and Agrahari, J. K. 2018. Shear-lag solution for excitation, sensing, and time reversal of Lamb waves for structural health monitoring. Journal of Intelligent Material Systems and Structures, 29(4), 585 – 599. Kim, I.,and Chattopadhyay, A. 2015. Guided Lamb wave-based structural health monitoring using a novel wave packet tracing method for damage localization and size quantification. Journal of Intelligent Material Systems and Structures, 26(18), 2515 – 2530. Lopes, V., Park, G., Cudney, H. H., and Inman, D. J. 2000. Impedance-based structural health monitoring with artificial neural networks. Journal of Intelligent Material Systems and Structures, 11(3), 206 – 214. Mori, N., Biwa, S., and Kusaka, T. 2019. Damage localization method for plates based on the time reversal of the mode-converted Lamb waves. Ultrasonics, 91, 19 – 29. Nandyala, A. R., Darpe, A. K., and Singh, S. P. 2020. Damage localization in cross-ply laminated composite plates under varying temperature conditions using Lamb waves. Measurement Science and Technology, 31(6). Pandey, P., Rai, A., and Mitra, M. 2022. Explainable 1-D convolutional neural network for damage detection using Lamb wave. Mechanical Systems and Signal Processing, 164. Pyle, R. J., Bevan, R. L. T., Hughes, R. R., Rachev, R. K., Ali, A. A. S., and Wilcox, P. D. 2021. Deep Learning for Ultrasonic Crack Characterization in NDE. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 68(5), 1854 – 1865. Rautela, M., Senthilnath, J., Moll, J.,and Gopalakrishnan, S. 2021. Combined two-level damage identification strategy using ultrasonic guided waves and physical knowledge assisted machine learning. Ultrasonics, 115. Tabian, I., Fu, H., and Khodaei, Z. S. 2019. A convolutional neural network for impact detection and characterization of complex composite structures. Sensors (Switzerland), 19(22). Yu, L., and Giurgiutiu, V. 2005. Advanced signal processing for enhanced damage detection with piezoelectric wafer active sensors. In Smart Structures and Systems (Vol. 1, Issue 2). Zheng, K., Li, Z., Zhu, J., Xia, R., Chen, J., and Hameed, M. S. 2024. Multistage damage detection method based on the defect mode for periodically stiffened panels. Journal of Sound and Vibration, 569.