AI-Augmented Quality Inspection in Aerospace Composite Material Manufacturing
Keywords:
AI-augmented inspection, generative AI, composite materialsAbstract
Aerospace composite material manufacturing took an evolutionary approach of AI-augmented quality inspection which helps in strict quality control in confirming essential structural integrity and operational safety. This research paper investigates the application of generative AI (GenAI)-powered vision models used in detecting microstructural defects, fiber misalignment, and inconsistencies in carbon fiber-reinforced polymer (CFRP) composites.
Downloads
References
J. Schmidhuber, “Deep learning in neural networks: An overview,” Neural Networks, vol. 61, pp. 85–117, 2015.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Las Vegas, NV, USA, 2016, pp. 770–778.
G. E. Hinton, A. Krizhevsky, and S. Wang, “Transformers for vision applications: A comprehensive review,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 9, pp. 3775–3790, Sep. 2022.
J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018.
A. Dosovitskiy et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2021.
L. Deng and D. Yu, “Deep learning: Methods and applications,” Found. Trends Signal Process., vol. 7, no. 3–4, pp. 197–387, 2014.
S. R. Fahlstrom, P. A. Söderholm, and D. Brotherton, “Applications of AI in non-destructive evaluation for aerospace materials,” J. Nondestruct. Eval., vol. 40, no. 2, pp. 1–17, 2021.
R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Columbus, OH, USA, 2014, pp. 580–587.
J. R. Doppa, S. Sharma, and A. Talapatra, “AI-based quality inspection in aerospace composite manufacturing,” IEEE Access, vol. 9, pp. 108523–108535, 2021.
P. Patel and M. T. Sun, “Vision-based defect detection in manufacturing: A review of recent advancements,” IEEE Trans. Ind. Informat., vol. 18, no. 3, pp. 1807–1820, Mar. 2022.
B. Xu et al., “Thermographic defect detection in composites using deep learning,” J. Therm. Sci. Eng. Appl., vol. 13, no. 3, pp. 1–10, 2021.
C. Zhang, J. Li, and Y. Wang, “A deep convolutional neural network framework for automatic defect detection in carbon fiber reinforced composites,” Compos. Struct., vol. 250, pp. 1–12, 2020.
T. G. Rodgers and H. Chien, “Applications of X-ray computed tomography in aerospace composite inspection,” J. Nondestruct. Eval., vol. 39, no. 2, pp. 1–12, 2020.
A. Graves, A. Rahaman, and S. Hochreiter, “Long short-term memory networks for material property prediction,” IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 6, pp. 2450–2462, Jun. 2021.
D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning internal representations by error propagation,” Nature, vol. 323, no. 1, pp. 533–536, 1986.
J. Bergstra and Y. Bengio, “Random search for hyper-parameter optimization,” J. Mach. Learn. Res., vol. 13, no. 1, pp. 281–305, 2012.
T. P. Breckon, A. Pierrot-Deseilligny, and M. V. Giordano, “AI-driven multi-modal fusion for defect detection in aerospace composites,” in Proc. IEEE Int. Conf. Image Process. (ICIP), Beijing, China, 2017, pp. 2374–2378.
Z. Li et al., “Ultrasonic imaging and AI-based defect segmentation in composite materials,” NDT&E Int., vol. 129, pp. 1–11, 2022.
J. Y. Goulermas and R. Langari, “Fuzzy logic-based defect classification for aerospace composite manufacturing,” IEEE Trans. Ind. Electron., vol. 68, no. 4, pp. 3384–3395, Apr. 2021.
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 1, pp. 436–444, 2015.
