A Hybrid Deep Learning Framework Based on Diffusion Model and Deep Residual Neural Network for Defect Detection in Composite Plates
Source abstract
Abstract
The establishment of a structural health monitoring (SHM) system for the damage and defects of composite structures is of great theoretical and engineering value to ensure their production and operational safety. Advanced machine learning technologies, such as deep learning, have become one of the main driving forces for state monitoring and predictive analysis of these structures. However, it is difficult to obtain sufficient data to train the deep learning model, which may fail to build an accurate and efficient SHM model. To overcome this problem, a new method based on Lamb waves and the diffusion model (DM) is proposed to realize the identification and classification of different defects for carbon-fiber-reinforced polymer (CFRP) structures. In this study, DM is used as the generation model of data enhancement, and the optimized and improved DDPM model is constructed in this experiment. The deep residual neural network (DenseNet) is used to identify and classify the defect features from the Lamb wave signals. Experimental and test results show that the deep learning framework designed in this study based on DenseNet classification and DDPM data enhancement can accurately detect and classify damage signals of common defects in CFRP composite plates.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Ultrasonics and Acoustic Wave Propagation · Structural Health Monitoring Techniques · Non-Destructive Testing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Shanghai Key Laboratory of Intelligent Sensing and Detection Technology, School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai 200237, China
Funding
National Natural Science Foundation of China · State Key Laboratory of New Textile Materials and Advanced Processing Technologies · the Fundamental Research Funds for the Central Universities
References (29)
Show source-provided references
1. A review of recent research on mechanics of multifunctional composite materials and structures10.1016/j.compstruct.2010.05.003 ↗
2. The use of intelligent computational tools for damage detection and identification with an emphasis on composites—A review10.1016/j.compstruct.2018.05.002 ↗
3. Progressive fatigue damage analysis method of laminated composites
4. Qing, X.L., Li, W.Z., Wang, Y.S., and Sun, H. (2019). Piezoelectric Transducer-Based Structural Health Monitoring for Aircraft Applications. Sensors, 19.10.3390/s19030545 ↗
5. Lamb wave inspection for composite laminates using a combined method of sparse reconstruction and delay-and-sum10.1016/j.compstruct.2019.110973 ↗
6. Traveling distance estimation for dispersive Lamb waves through sparse Bayesian learning strategy10.1088/1361-665X/ab28f0 ↗
7. Nonlinear Ultrasonic Techniques for Nondestructive Assessment of Micro Damage in Material: A Review10.1007/s12541-009-0019-y ↗
8. Application of signal processing techniques to ultrasonic testing of plates by S0 Lamb wave mode10.1016/j.ndteint.2010.10.004 ↗
9. Xu, J.C., Zhu, W.J., Xiang, Y.X., Gao, Y., and Qiu, X. (2021). Localization and Imaging of Micro-Cracks Using Nonlinear Lamb Waves with Imperfect Group-Velocity Matching. Appl. Sci., 11.10.3390/app11178069 ↗
10. Beyond the hype: Big data concepts, methods, and analytics10.1016/j.ijinfomgt.2014.10.007 ↗
11. Deep Learning in Neural Networks: An Overview10.1016/j.neunet.2014.09.003 ↗
12. Lu, C., Wang, Y., Ragulskis, M., and Cheng, Y. (2016). Fault Diagnosis for Rotating Machinery: A Method based on Image Processing. PLoS ONE, 11.10.1371/journal.pone.0164111 ↗
13. Real-time motor fault detection by 1D convolutional neural networks10.1109/TIE.2016.2582729 ↗
14. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks10.1016/j.jsv.2016.10.043 ↗
15. Signal Model-Based Fault Detection and Diagnosis for Induction Motors Using Features of Vibration Signal in Two-Dimension Domain10.5545/sv-jme.2010.162 ↗
16. Deep learning based crack damage detection technique for thin plate structures using guided lamb wave signals10.1088/1361-665X/ab58d6 ↗
17. Lamb wave-based damage detection of composite structures using deep convolutional neural network and continuous wavelet transform10.1016/j.compstruct.2021.114590 ↗
18. A New Convolutional Neural Network Based Data-Driven Fault Diagnosis Method10.1109/TIE.2017.2774777 ↗
19. Synthesizing time-series wound prognosis factors from electronic medical records using generative adversarial networks10.1016/j.jbi.2021.103972 ↗
20. Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., and Ganguli, S. (2015, January 6–11). Deep Unsupervised Learning using Nonequilibrium Thermodynamics. Proceedings of the 32nd International Conference on Machine Learning (ICML), Lille, France.
21. Ruttor, A., Batz, P., and Opper, M. (2013, January 5–10). Approximate Gaussian process inference for the drift function in stochastic differential equations. Proceedings of the 26th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA.
22. Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., and Poole, B. (2020). Score-based generative modeling through stochastic differential equations. arXiv.
23. Denoising diffusion probabilistic models
24. Song, Y., and Ermon, S. (2019). Advances in Neural Information Processing Systems 32, Curran Associates Inc.
25. Song, Y., and Kingma, P.D. (2021). How to train your energy-based models. arXiv.
26. Narayan, S.S., and Marlin, B.M. (2021, January 3–7). Multi-Time Attention Networks for Irregularly Sampled Time Series. Proceedings of the ICLR 2021, Virtual. Available online: https://iclr.cc/Conferences/2021.
27. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
28. Huang, G., Sun, Y., Liu, Z., Sedra, D., and Weinberger, K. (2016, January 11–14). Deep Networks with Stochastic Depth. Proceedings of the 14th European Conference, Amsterdam, The Netherlands.10.1007/978-3-319-46493-0_39 ↗
29. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2017.243 ↗