A Dual-Contrastive-Attention Transformer for Unsupervised Anomaly Detection in Lamb Waves Structural Health Monitoring
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Lamb wave-based Structural Health Monitoring (SHM) is a promising technique for detecting defects in materials and structures. However, traditional methods often rely on computationally intensive signal processing and struggle to detect subtle anomalies wave patterns. In this work, we propose a novel transformer-based framework, called Dual-Contrastive-Attention Transformer (DCAT), for unsupervised anomaly detection in Lamb wave data. DCAT uses two attention branches during training: a Global-Context Attention (GCA) branch that captures long-range patterns, and a Local-Context Attention (LCA) branch that serves as a constraint. A contrastive loss is used to prevent the global branch from over-learning local features, encouraging it to focus on the overall structure. Both branches are trained to reconstruct the input, using a structural similarity (SSIM) loss that better reflects waveform patterns than traditional mean squared error. After training, only the global branch is retained for inference. Anomalies are detected by comparing the input and reconstructed output. Since the global branch cannot easily reproduce local defects, it produces a higher SSIM loss when anomalies are present. We test our model on a Lamb wave dataset with multiple types of defects. DCAT achieves 97.8% accuracy and a precision of 98.6%, outperforming other SOTA baselines. These results show that DCAT is well-suited for accurate Lamb wave-based SHM without the need for labeled data.
How to Cite
##plugins.themes.bootstrap3.article.details##
Deep Learning, Transformer, Lamb Wave Inspection
Azad, M. M., Munyaneza, O., Jung, J., Sohn, J. W., Han, J.-W., & Kim, H. S. (2024). Damage Localization and Severity Assessment in Composite Structures Using Deep Learning Based on Lamb Waves. Sensors, 24(24), 8057.
Cantero-Chinchilla, S., Chiachío-Ruano, J., Chiachío-Ruano, M., Etxaniz, J., Aranguren, G., Jones, A., Essa, Y., & Martin De La Escalera, F. (2018). Lamb wave-based damage indicator for plate-like structures. European Conference of the PHM Society, 4(1).
Darban, Z. Z., Yang, Y., Webb, G. I., Aggarwal, C. C., Wen, Q., Pan, S., & Salehi, M. (2025). DACAD: Domain adaptation contrastive learning for anomaly detection in multivariate time series. IEEE Transactions on Knowledge and Data Engineering.
Ding, Y., Jia, M., Miao, Q., & Cao, Y. (2022). A novel time–frequency Transformer based on self–attention mechanism and its application in fault diagnosis of rolling bearings. Mechanical Systems and Signal Processing, 168, 108616.
Giurgiutiu, V. (2005). Tuned Lamb wave excitation and detection with piezoelectric wafer active sensors for structural health monitoring. Journal of Intelligent Material Systems and Structures, 16(4), 291–305.
Goodge, A., Hooi, B., Ng, S.-K., & Ng, W. S. (2022). Lunar: Unifying local outlier detection methods via graph neural networks. Proceedings of the AAAI Conference on Artificial Intelligence, 36(6), 6737–6745.
Lee, H., Lim, H. J., Skinner, T., Chattopadhyay, A., & Hall, A. (2022). Automated fatigue damage detection and classification technique for composite structures using Lamb waves and deep autoencoder. Mechanical Systems and Signal Processing, 163, 108148.
Li, A., Qiu, C., Kloft, M., Smyth, P., Rudolph, M., & Mandt, S. (2024). Zero-shot anomaly detection via batch normalization. Advances in Neural Information Processing Systems, 36.
Liu, P., Zhang, H., Zhang, K., Lin, L., & Zuo, W. (2018). Multi-level wavelet-CNN for image restoration. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 773–782.
Mishra, S., Vanli, O. A., & Park, C. (2015). A multivariate cumulative sum method for continuous damage monitoring with lamb-wave sensors. International Journal of Prognostics and Health Management, 6(4).
Rizvi, S. H. M., Abbas, M., Zaidi, S. S. H., Tayyab, M., & Malik, A. (2024). LSTM-Based Autoencoder with Maximal Overlap Discrete Wavelet Transforms Using Lamb Wave for Anomaly Detection in Composites. Applied Sciences, 14(7), 2925.
Shentu, Q., Li, B., Zhao, K., Shu, Y., Rao, Z., Pan, L., Yang, B., & Guo, C. (2024). Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders. ArXiv Preprint ArXiv:2405.15273.
Suresh, P., & Ragav, A. (2020). WaDeNet: Wavelet Decomposition based CNN for Speech Processing. ArXiv Preprint ArXiv:2011.05594.
Wang, J., Xu, G., Yan, F., Wang, J., & Wang, Z. (2023). Defect transformer: An efficient hybrid transformer architecture for surface defect detection. Measurement, 211, 112614.
Wong, L., Liu, D., Berti-Equille, L., Alnegheimish, S., & Veeramachaneni, K. (2022). AER: Auto-encoder with regression for time series anomaly detection. 2022 IEEE International Conference on Big Data (Big Data), 1152–1161.
Zhang, Z., Pan, H., Wang, X., & Lin, Z. (2020). Machine learning-enriched lamb wave approaches for automated damage detection. Sensors, 20(6), 1790.
Zhao, X. (2022). Wavelet-attention CNN for image classification. ArXiv Preprint ArXiv:2201.09271.
Zhao, X., Royer, R. L., Owens, S. E., & Rose, J. L. (2011). Ultrasonic Lamb wave tomography in structural health monitoring. Smart Materials and Structures, 20(10), 105002.
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.