Title: An End-To-End AFP Defect Inspection and Analysis Tool

Authors: Matthew J. Godbold, Christopher M. Sacco, Roudy Wehbe, Ramy Harik

DOI: 10.33599/nasampe/s.22.0729

Abstract: Automated Fiber Placement (AFP) is a methodology for the manufacturing of large composite structures. By marrying robotic layup with composites manufacturing, faster and more consistent results can be attained than through hand layup. Unfortunately, AFP is a process that tends to produce a wide array of manufacturing defects. With AFP becoming a standard in manufacturing of large composite panels, a way to assess the defects formed during layup is vital. This paper will present improvements made to previously developed inspection software, to create a holistic inspection system. Through an updated user interface (UI), the inspection software allows for quick analysis of defects and process parameters in an understandable way through graphical displays. Defects can be mapped back onto the surface for visual representation. The goal of this software is to present the user with any needed inspection data (defect ID, defect type, and area of defect) in an accessible and comprehensible manner. Coupled with the identification and display of defects are unique visualization methods and detailed analysis of part quality. End to end understanding of the effect of parameter changes, machine settings, and other tunable functions can be gained through the application of this comprehensive tool.

References: [1] R. Harik, C. Saidy, S. J. Williams, Z. Gurdal, and B. Grimsley, “Automated fiber placement defect identity cards: Cause, anticipation, existence, significance, and progression,” in International SAMPE Technical Conference, 2018, vol. 2018-May. [2] C. Sacco, A. Baz Radwan, A. Anderson, R. Harik, and E. Gregory, “Machine learning in composites manufacturing: A case study of Automated Fiber Placement inspection,” Composite Structures, vol. 250, 2020, doi: 10.1016/j.compstruct.2020.112514. [3] M. Sharp, R. Ak, and T. Hedberg, “A survey of the advancing use and development of machine learning in smart manufacturing,” Journal of Manufacturing Systems, vol. 48, 2018, doi: 10.1016/j.jmsy.2018.02.004. [4] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, no. 6, 2017, doi: 10.1145/3065386. [5] M. Meng, Y. J. Chua, E. Wouterson, and C. P. K. Ong, “Ultrasonic signal classification and imaging system for composite materials via deep convolutional neural networks,” Neurocomputing, vol. 257, 2017, doi: 10.1016/j.neucom.2016.11.066. [6] M. Kuhl, T. Wiener, and M. Krauß, “Multisensorial self-learning systems for quality monitoring of carbon fiber composites in aircraft production,” in Procedia CIRP, 2013, vol. 12. doi: 10.1016/j.procir.2013.09.019. [7] E. Shelhamer, J. Long, and T. Darrell, “Fully Convolutional Networks for Semantic Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 4, 2017, doi: 10.1109/TPAMI.2016.2572683. [8] J. Y. Wu, S. Sfarra, and Y. Yao, “Sparse principal component thermography for subsurface defect detection in composite products,” IEEE Transactions on Industrial Informatics, vol. 14, no. 12, 2018, doi: 10.1109/TII.2018.2817520. [9] D. Maass, “Progress in automated ply inspection of AFP layups,” Reinforced Plastics, vol. 59, no. 5, 2015, doi: 10.1016/j.repl.2015.05.002. [10] K. Liu, Z. Ma, Y. Liu, J. Yang, and Y. Yao, “Enhanced defect detection in carbon fiber reinforced polymer composites via generative kernel principal component thermography,” Polymers, vol. 13, no. 5, 2021, doi: 10.3390/polym13050825. [11] Y. Tang, Q. Wang, H. Wang, J. Li, and Y. Ke, “A novel 3D laser scanning defect detection and measurement approach for automated fibre placement,” Measurement Science and Technology, vol. 32, no. 7, Jul. 2021, doi: 10.1088/1361-6501/abda95. [12] C. Sacco, A. B. Radwan, R. Harik, and M. van Tooren, “AUTOMATED FIBER PLACEMENT DEFECTS: AUTOMATED INSPECTION AND CHARACTERIZATION.” [13] C. Sacco, A. Baz Radwan, T. Beatty, and R. Harik, “Machine learning based AFP inspection: A tool for characterization and integration,” in International SAMPE Technical Conference, 2019, vol. 2019-May. doi: 10.33599/nasampe/s.19.1594. [14] C. Sacco et al., “On the effect of manual rework in AFP quality control for a doubly-curved part,” Composites Part B: Engineering, vol. 227, Dec. 2021, doi: 10.1016/j.compositesb.2021.109432. [15] D. Duque-Arias et al., “On power Jaccard losses for semantic segmentation,” 2021. [Online]. Available: https://orcid.org/0000-0002-1349-8042 [16] T.-Y. Lin et al., “Microsoft COCO: Common Objects in Context,” May 2014, [Online]. Available: http://arxiv.org/abs/1405.0312

Conference: SAMPE 2022

Publication Date: 2022/05/23

SKU: TP22-0000000729

Pages: 11

Price: $22.00