Abstract
Nondestructive evaluation (NDE) methods provide a way to monitor structures which can decrease maintenance/inspection costs, predict damage locations, and indicate the current state of structural health of a system. Acoustic steady-state excitation spatial spectroscopy (ASSESS) is an ultrasonic NDE technique that utilizes surface velocity response data collected by a laser Doppler vibrometer (LDV) to detect and characterize defects. Processing the resultant wavefield images produces a map of damage which is useful in manufacturing and structural health inspection of aerospace/civil structures.
Convolutional neural networks (CNN) were used to estimate plate defects directly from wavefield maps, producing pixel-wise thickness maps which are able to effectively characterize defects without producing boundary artifacts that occur with Fourier-based processing methods. This work utilized a diverse set of geometries and boundary conditions in its simulation-generated training set to ensure generalizability in the CNN. Using the U-net CNN architecture for image segmentation with a pretrained ResNet model as an encoder, a model was trained, validated, and tested which exhibits superior performance in speed and accuracy than traditional methods of defect characterization, while showing versatility over a wide range of plate shapes and boundary conditions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ostachowicz, W., Kudela, P., Malinowski, P., Wandowski, T.: Damage localization in plate-like structures based on pzt sensors. Mech. Syst. Signal Process. 23(6), 1805 (2009)
Michaels, J.: Ultrasonic wavefield imaging: research tool or emerging NDE method? AIP Conf. Proc. 1806, 020001 (2017)
Eckels, J.D., Fernandez, I.F., Ho, K., Dervilis, N., Jacobson, E.M., Wachtor, A.J.: Application of a U-net convolutional neural network to ultrasonic wavefield measurements for defect characterization. In: Di Maio, D., Baqersad, J. (eds.) Rotating machinery, Optical Methods & Scanning LDV Methods Conference proceedings of the society for experimental mechanics series, vol. 6. Springer, Cham (2021)
Flynn, E.B., Chong, S.Y., Jarmer, G.J., Lee, J.R.: Structural imaging through local wavenumber estimation of guided waves. NDT & E Int. 59, 1 (2013)
Flynn, E., Jarmer, G.: High-speed, non-contact, baseline-free imaging of hidden defects using scanning laser measurements of steady-state ultrasonic vibration. Struct. Health Monit. 2013. (2013)
Eckels, J.D., Fernandez, I.F., Ho, K., Dervilis, N., Jacobson, E.M., Wachtor, A.J.: Predicting local material thickness from steady-state ultrasonic wavefield measurements using a convolutional neural network. Under revision for Ultrasonics (2021)
Wilcox, P.D., Lowe, M.J.S., Cawley, P.: Mode and transducer selection for long range lamb wave inspection. J. Intell. Mater. Syst. Struct. 12(8), 553 (2001)
O’Dowd, N.M., Han, D.-H., Kang, L.-H., Flynn, E.B.: Exploring the performance limits of full-field acoustic wavenumber spectroscopy techniques for damage detection through numerical simulation. In: Proceedings of the 8th European Workshop on Structural Health Monitoring, Bilbao, Spain (2016)
Flynn, E.B., Stull, N.D.: Toward utilizing full-field laser-ultrasound for practical nondestructive inspection with acoustic wavenumber spectroscopy. 2018 IEEE International Ultrasonics Symposium (IUS) (2018)
Koskelo, E.C., Flynn, E.B.: Scanning laser ultrasound and wavenumber spectroscopy for in-process inspection of additively manufactured parts. In: Nondestructive characterization and monitoring of advanced materials, aerospace, and civil infrastructure 2016 (2016)
Jacobson, E.M., Cummings, I.T., Fickenwirth, P.H., Flynn, E.B., Wachtor, A.J. (2020). Defect detection in additively manufactured metal parts using in-situ steady-state ultrasonic response data. In: ASME international mechanical engineering congress and exposition (2020)
Koskelo, E.A.C., Flynn, E.B.: Full-field inspection of three-dimensional structures using steady-state acoustic wavenumber spectroscopy. In: AIP conference proceedings (2017)
Rawat, W., Wang, Z.: Deep convolutional neural networks for image classification: a comprehensive review. Neural Comput. 29(9), 2352–2449 (2017)
Huang, H., Cheng, W., Zhou, M., Chen, J., Zhao, S.: Towards automated 3D inspection of water leakages in shield tunnel linings using mobile laser scanning data. Intell. Sens. Comput. Vis. (2020).
Velas, M., Spanel, M., Hradis, M., Herout, A. CNN for very fast ground segmentation in Velodyne LiDAR data. arXiv (2017)
Çiçek, Ö., Abdulkadir, A., Lienkamp, S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. arXiv (2016)
Lin, T., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42(11), 318–327 (2017)
He, K., Zhang, X., Ren, S., He, K., Sun, J.: Deep residual learning for image recognition. 2016 IEEE conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Acknowledgments
The authors would like to thank Dr. Eric Flynn and Dr. Ian Cummings for their helpful discussions in regard to this research and Joshua Eckels, Isabel Fernandez, and Kelly Ho for providing the database of wavefield simulations. This research was funded by Los Alamos National Laboratory (LANL) through the Engineering Institute’s Los Alamos Dynamics Summer School. The Engineering Institute is a research and education collaboration between LANL and the University of California San Diego’s Jacobs School of Engineering. This collaboration seeks to promote multidisciplinary engineering research that develops and integrates advanced predictive modeling, novel sensing systems, and new developments in information technology to address LANL mission-relevant problems.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Society for Experimental Mechanics, Inc.
About this paper
Cite this paper
Maxwell, C.N., Dalton, J.L., Dzomba, N.E., Jacobson, E.M., Dervilis, N., Wachtor, A.J. (2022). Multilayer Input Deep Learning Applied to Ultrasonic Wavefield Measurements. In: Madarshahian, R., Hemez, F. (eds) Data Science in Engineering, Volume 9. Conference Proceedings of the Society for Experimental Mechanics Series. Springer, Cham. https://doi.org/10.1007/978-3-031-04122-8_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-04122-8_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-04121-1
Online ISBN: 978-3-031-04122-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)