Title: Automated Fiber Placement Off-Part Time Mitigation Using Portable Augmented Reality System

Authors: Nicklaus Johnson, Christopher Sacco, Alex Brasington, Roudy Wehbe, Ramy Harik

DOI: 10.33599/nasampe/s.22.0706

Abstract: Automated Fiber Placement (AFP) is an additive manufacturing technique for composite materials in which composite strips, denoted as tows, are heated and compressed along a tool surface to create a single ply. Throughout this process many defects tend to arise which, by current industry standards, are identified and manually fixed by trained technicians thus delaying the manufacturing process. This paper presents an approach to mitigate the time allotted to this process using a Portable Augmented Reality (PAR) system that dynamically displays the defect data on the tool surface in real-time. Greyscale images of the ply’s surface generated during inspection are sent into a Machine Learning (ML) program that outlines the defects in polygons of different colors relative to the type of defect associated with the image. The geometries and attributes of each defect are parsed and a CAD representation of the defects on the ply surface is created. This CAD representation can be downloaded through the Augmented Reality (AR) application on an Android device, such as a smart phone. The device is then used to locate the tool surface and display the CAD representation onto the tool surface, thus showing the technician the exact location and type of the different defects.

References: A. Brasington, C. Sacco, J. Halbritter, R. Wehbe and R. Harik, ""Automated fiber placement: A review of history, current technologies, and future paths forward,"" Composites Part C: Open Access, vol. 6, p. 100182, 2021. R. Harik, C. Saidy, S. Williams, Z. Gurdal and B. Grimsley, ""Automated Fiber Placement Defect Identity Cards: Cause, Anticipation, Existence, Significance, and Progression,"" in SAMPE 2018 Conference & Exhibition, Long Beach, CA, 2018. A. Brasington, ""3D Modeling of Automated Fiber Placement Defects,"" in The Composite and Advanced Materials Expo., Orlando, FL, 2020. C. Sacco, A. Brasington, C. Saidy, M. Kirkpatrick, J. Halbritter, R. Wehbe and R. Harik, ""On the effect of manual rework in AFP quality control for a doubly-curved part,"" Composites Part B: Engineering, vol. 227, p. 109432, 2021. T. Rudberg, J. Nielson, M. Henscheid and J. Cemenska, ""Improving AFP Cell Performance,"" SAE International Journal of Aerospace Manufacturing and Automated Fastening, vol. 7, no. 2, 2014. A. Halbritter and R. Harper, ""Big Parts Demand Big Changes to the Fiber Placement Status Quo,"" in SME Composites Manufacturing, Mesa, AZ, 2012. T. R. a. M. H. J. Cemenska, ""Automated In-Process Inspection System for AFP Machines,"" SAE Int. J. Aerosp., 2015. C. Sacco, ""Machine Learning Methods for Rapid Inspection of Automated Fiber Placment Manufactured Composite Structures (Master's Thesis),"" University of South Carolina, 2019. C. Sacco, A. B. Radwan, T. Beatty and R. Harik, ""Machine Learning Based AFP Inspection: A Tool for Characterization and Integration,"" in SAMPE 2019 Conference & Exhibition, Charlotte, NC, 2019. ""Python Language Refernce, version 3.7,"" Foundation, Python Software, [Online]. Available: https://www.python.org/. M. Sanchez-Acevedo, B. Sabino-Moxo and J. Marquez-Dominguez, ""Mobile augmented reality: evolving human-computer interaction,"" in Mobile Platforms, Design, and Apps for Social Commerce, IGI Global, 2017, pp. 153-174.

Conference: SAMPE 2022

Publication Date: 2022/05/23

SKU: TP22-0000000706

Pages: 11

Price: $22.00