Title: Machine Learning Based AFP Inspection: A Tool for Characterization and Integration

Authors: Christopher Sacco, Anis Baz Radwan, Tyler Beatty, and Ramy Harik

DOI: 10.33599/nasampe/s.19.1594

Abstract: Automated Fiber Placement (AFP) has become a standard manufacturing technique in the creation of large scale composite structures due to its high production rates. However, the associated rapid layup that accompanies AFP manufacturing has a tendency to induce defects. We forward an inspection system that utilizes machine learning (ML) algorithms to locate and characterize defects from profilometry scans coupled with a data storage system and a user interface (UI) that allows for informed manufacturing. A Keyence LJ-7080 blue light profilometer is used for fast 2D height profiling. After scans are collected, they are process by ML algorithms, displayed to an operator through the UI, and stored in a database. The overall goal of the inspection system is to add an additional tool for AFP manufacturing. Traditional AFP inspection is done manually adding to manufacturing time and being subject to inspector errors or fatigue. For large parts, the inspection process can be cumbersome. The proposed inspection system has the capability of accelerating this process while still keeping a human inspector integrated and in control. This allows for the rapid capability of the automated inspection software and the robustness of a human checking for defects that the system either missed or misclassified.

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 SAMPE Conference Proceedings, 2018. [2] L. G. Bahamonde Jácome, M. A. Albazzan, P. L. Chevalier, Z. Gürdal, B. F. Tatting, and R. Harik, “Rapid tools for an AFP manufacturing defects assessment framework,” Int. SAMPE Tech. Conf., vol. 2018–May, 2018. [3] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Adv. Neural Inf. Process. Syst., pp. 1–9, 2012. [4] S. Wu, S. Zhong, and Y. Liu, “Deep residual learning for image steganalysis,” Multimed. Tools Appl., pp. 1–17, 2017. [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, pp. 128–135, 2017. [6] M. Kuhl, T. Wiener, and M. Krauß, “Multisensorial self-learning systems for quality monitoring of carbon fiber composites in aircraft production,” Procedia CIRP, vol. 12, pp. 103–108, 2013. [7] H. D. Benítez, H. Loaiza, E. Caicedo, C. Ibarra-Castanedo, A. H. Bendada, and X. Maldague, “Defect characterization in infrared non-destructive testing with learning machines,” NDT E Int., vol. 42, no. 7, pp. 630–643, 2009. [8] C. Cortes and V. Vapnik, “Support-Vector Networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995. [9] J. Brüning, B. Denkena, M. A. Dittrich, and T. Hocke, “Machine Learning Approach for Optimization of Automated Fiber Placement Processes,” Procedia CIRP, vol. 66, pp. 74–78, 2017. [10] M. Cacciola, S. Calcagno, F. C. Morabito, and M. Versaci, “Computational intelligence aspects for defect classification in aeronautic composites by using ultrasonic pulses,” IEEE Trans. Ultrason. Ferroelectr. Freq. Control, vol. 55, no. 4, pp. 870–878, 2008. [11] G. D’Angelo and S. Rampone, “Feature extraction and soft computing methods for aerospace structure defect classification,” Meas. J. Int. Meas. Confed., vol. 85, pp. 192–209, 2016. [12] C. Sacco, A. B. Radwan, R. Harik, and M. Van Tooren, “Automated Fiber Placement Defects: Automated Inspection and Characterization,” SAMPE 2018 Conf. Proceeding, 2018. [13] J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 07–12–June, pp. 3431–3440, 2015. [14] X. Glorot and Y. Bengio, “Understanding the difficulty of training deep feedforward neural networks,” Pmlr, vol. 9, pp. 249–256, 2010. [15] B. Krawczyk, “GPU-accelerated extreme learning machines for imbalanced data streams with Concept Drift,” Procedia Comput. Sci., vol. 80, pp. 1692–1701, 2016. [16] M. A. Franco and J. Bacardit, “Large-scale experimental evaluation of GPU strategies for evolutionary machine learning,” Inf. Sci. (Ny)., vol. 330, pp. 385–402, 2016. [17] R. Wehbe, R. Harik, and Z. Gürdal, “In-Plane Tow Deformations Due to Steering in Automated Fiber Placement,” in AIAA Scitech 2019 Forum, 2019, pp. 1–13. [18] G. Rousseau, R. Wehbe, J. Halbritter, and R. Harik, “Automated fiber placement path planning: A state-of-the-art review,” Computer-Aided Design and Applications. 2019.

Conference: SAMPE 2019 - Charlotte, NC

Publication Date: 2019/05/20

SKU: TP19--1594

Pages: 10

Price: FREE