Title: MULTI-SOURCE MACHINE LEARNING AND THERMOPLASTICS ENHANCED AEROSTRUCTURE MANUFACTURING

Authors: John Gangloff, Wenping Zhao, Soumalya Sarkar, Sudeepta Mondal, Lei Xing, Abhijit Chakraborty, Amit Surana, Benjamin Bedard, Justin Alms

DOI: 10.33599/nasampe/s.23.0021

Abstract: Raytheon Technologies Research Center, together with Collins Aerospace and Oak Ridge National Laboratory is developing an Artificial Intelligence (AI) / Machine Learning (ML) guided solution to advance the assembly of high performance and lightweight thermoplastic composite (TPC) aerospace products. The solution aims to lower risk & reduce lead time for aircraft aerostructures, based on induction welding (IW) of TPCs to enable high-speed & low-cost production. Cost & lead time of IW process development is reduced by replacing traditional empirical methods with optimization methods that merge AI/ML, physics-based IW process simulations, and IW experiments. A multi-source AI/ML architecture is developed using TPC-IW simulation & experimental data. The ML framework enables fast and robust search of the process parameter design space for the creation of optimum process recipes. Physics-based TPC-IW simulations are assembled and exercised using electromagnetic and heat transfer process models. TPC-IW experimental hardware, software, and system components are assembled to build enough heat at the TPC joint interface to initiate fusion bonding. Single-lap shear mechanical testing of ML-informed IW samples demonstrated targeted joint strengths. Overall, an IW process optimization time reduction of ~2X was demonstrated by implementing the developed ML framework

References: 1. J. Reis, M. de Moura, and S. Samborski. “Thermoplastic Composites and Their Promising Applications in Joining and Repair Composites Structures: A Review.” Materials, 13, 5832, 2020. 2. T. Bayerl, M.Duhovic, P. Mitschang, and D. Bhattacharyya. “The heating of polymer composites by electromagnetic induction – A review.” Composites Part A. 57, 27-40, 2014. 3. W. Zhao, J. Alms, B. Blakeslee, A. Chakraborty, J. Gangloff, M. Klecka, J. Mendoza, Z. Wang, L. Xing, C. Navarro, C. Gong, R. Guha, B. Shah, A Kabir, W. De Backer, A. Cromer, and S. Vaidya. “Automated Induction Welding of Large Thermoplastic Composite Structure.” SAMPE 2022 Conference & Exhibition, Charlotte, NC, USA, May 23, 2022. 4. P. Perdikaris. “Probabilistic Data Fusion and Physics-Informed Machine Learning.” IPAM Workshop: Big Data Meets Large-Scale Computing, Sep. 28, 2018. 5. S. Sarkar, S. Mondal, M. Joly, M.E. Lynch, S.D. Bopardikar, R. Acharya, and P. Perdikaris, “Multifidelity and Multiscale Bayesian Framework for High-Dimensional Engineering Design and Calibration.” ASME. J. Mech. Des. 141(12), 121001, Dec. 2019.

Conference: SAMPE 2023

Publication Date: 2023/04/17

SKU: TP23-0000000021

Pages: 11

Price: $22.00