Title: Machine Learning-Based Process Simulation Approach for Real-Time Optimization and Active Control of Composites Autoclave Processing

Authors: Keith D. Humfeld, Navid Zobeiry

DOI: 10.33599/nasampe/s.21.0476

Abstract: For manufacturing of composites, several parts may be processed simultaneously in an autoclave or oven. Depending on the equipment design, tool/part geometries, and tool nesting, convective heat transfer Boundary Conditions (BCs) may vary around parts in each load. As a result, temperature histories in some of the parts may not conform to specifications such as limits on maximum part temperature, or part temperature rate. To mitigate risk, in addition to conducting finite element simulations prior to fabrication based on assumed BCs, leading and lagging thermocouples, embedded in parts or placed in proxy locations, are used to monitor temperature history during processing. In this study, a recently developed machine learning framework, CompML (Composites Machine Learning) is used for active control of the autoclave. CompML uses TC data at the start of the autoclave processing for real-time inverse modeling of the thermo-chemical problem, and to identify BCs for all parts in each load. The results are then used for real-time optimization of autoclave cure recipe to the shortest cycle that satisfies specifications in all parts. A successful virtual demonstration of the approach for HEXCEL AS4/8552 parts processed on Invar tools is discussed in the paper.

References: 1. J. Fabris, D. Lussier, N. Zobeiry, C. Mobuchon, A. Poursartip. Development of Standardized Approaches to Thermal Management in Composites Manufacturing. In SAMPE Technical Conference Proceedings. Society for the Advancement of Material and Process Engineering. Seattle, WA, June, pp. 2-5. 2014. 2. J. Fabris, C. Mobuchon, N. Zobeiry, D. Lussier, G. Fernlund, A. Poursartip. Introducing thermal history producibility assessment at conceptual design. In SAMPE conference, society for the advancement of material and process engineering. 2015. 3. M. Mohseni, N. Zobeiry, G. Fernlund, Process-induced matrix defects: post-gelation, Composite Part A, DOI: 10.1016/j.compositesa.2020.106007, 2020. 4. L. Farhang, M. Mohseni, N. Zobeiry, G. Fernlund, Experimental study of void evolution in partially impregnated prepregs, Journal of Composite Materials, 54(11):1511-1523, 2019. 5. N. Zobeiry, A. Poursartip, The origins of residual stress and its evaluation in composite materials, In: Beaumont, P.W.R., Soutis S. and Hodzic A. (eds.), 2015. 6. K. Farnand, N. Zobeiry, A. Poursartip, G. Fernlund, Micro-level mechanisms of fiber waviness and wrinkling during hot drape forming of unidirectional prepreg composites, Composites Part A: Applied Science and Manufacturing, 103:168-177, 2017. 7. N. Zobeiry, A. Lee, C. Mobuchon, Fabrication of Transparent Composites, Composites Science and Technology, 197:108281, 2020. 8. N. Zobeiry, A. Forghani, C. Li, K. Gordnian, R. Thorpe, R. Vaziri, G. Fernlund, G., A. Poursartip, Multiscale characterization and representation of composite materials during processing, in: Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. p. 20150278. https://doi.org/10.1098/rsta.2015.0278, 2016. 9. N. Zobeiry, J. Park, A. Poursartip, An infrared thermography-based method for the evaluation of the thermal response of tooling for composites manufacturing. J. Compos. Mater. 53, 1277–1290. https://doi.org/10.1177/0021998318798444, 2019. 10. J. Fabris, C. Mobuchon, N. Zobeiry, A. Poursartip, Understanding the consequences of tooling design choices on thermal history in composites processing, in: International SAMPE Technical Conference, 2016. 11. J. Park, N. Zobeiry, A. Poursartip, A, Tooling materials and their effect on surface thermal gradients, in: International SAMPE Technical Conference, 2017. 12. G. Fernlund, C. Mobuchon, N. Zobeiry, 2.3 Autoclave Processing, In: Beaumont P.W.R. and Zweben C.H. (eds.), Comprehensive Composite Materials II, 2:42-62, Oxford: Academic Press, 2018. 13. N. Zobeiry, K.D. Humfeld. A Physics-Informed Machine Learning Approach for Solving Heat Transfer Equation in Advanced Manufacturing and Engineering Applications. arXiv preprint arXiv:2010.02011, 2020. 14. N. Zobeiry, A. Stewart, A. Poursartip. Applications of Machine Learning for Process Modeling of Composites. In SAMPE Virtual Conference. 2020. 15. N. Zobeiry, J. Reiner, R. Vaziri. Theory-guided machine learning for damage characterization of composites. Composite Structures, 112407, 2020. 16. N. Zobeiry, K.D. Humfeld, An iterative machine learning approach for discovery of theories underlying physical phenomena, arXiv preprint arXiv:1909.13718 17. D. Van Ee, A. Poursartip. HexPly 8552 Material Properties Database for use with COMPRO CCA and RAVEN. Version 0.9. NCAMP. Wichita, KS (2009).

Conference: SAMPE NEXUS 2021

Publication Date: 2021/06/29

SKU: TP21-0000000476

Pages: 9

Price: FREE