Title: Applications of Machine Learning for Process Modeling of Composites

Authors: Navid Zobeiry, Andrew Stewart and Anoush Poursartip

DOI: 10.33599/nasampe/s.20.0053

Abstract: Science-based simulation tools such as Finite Element (FE) models are widely used in engineering applications including process modeling of composites. There are inherent limitations associated with these models including trade-off between fidelity and cost, inability to tackle uncertainties such as unknown manufacturing boundary conditions, and difficulties with inverse modeling and optimization of multi-dimensional problems. With the rise of Machine Learning (ML) and data-driven modeling, many branches of science and engineering are exploring the applications of these methods with varying degrees of success. Here we explore current applications of ML in process simulation of composites. With several case studies, it is demonstrated how some of the limitations of traditional science-based models can be addressed using a combined FE-ML approach in the new paradigm of Theory-Guided Machine Learning (TGML). Specifically, case studies are presented for thermo-chemical analysis of composites processing, where surrogate Neural Networks (NN) are developed for near real-time modeling of the manufacturing process.

References: [1] G. Fernlund, C. Mobuchon, N. Zobeiry, 2.3 Autoclave Processing, in: P.B. Carl Zweben (Ed.), Compr. Compos. Mater. II, 2018: pp. 42–62. https://doi.org/10.1016/b978-0-12-803581-8.09899-4. [2] N. Zobeiry, C. Duffner, Measuring the negative pressure during processing of advanced composites, Compos. Struct. 203 (2018) 11–17. https://doi.org/10.1016/j.compstruct.2018.06.123. [3] C. Li, N. Zobeiry, K. Keil, S. Chatterjee, A. Poursartip, Advances in the characterization of residual stress in composite structures, in: Int. SAMPE Tech. Conf., 2014. [4] N. Zobeiry, A. Poursartip, The origins of residual stress and its evaluation in composite materials, in: Struct. Integr. Durab. Adv. Compos. Innov. Model. Methods Intell. Des., Elsevier Ltd, 2015: pp. 43–72. https://doi.org/10.1016/B978-0-08-100137-0.00003-1. [5] N. Zobeiry, A. Forghani, C. Li, K. Gordnian, R. Thorpe, R. Vaziri, G. Fernlund, A. Poursartip, Multiscale characterization and representation of composite materials during processing, in: Philos. Trans. R. Soc. A Math. Phys. Eng. Sci., 2016: p. 20150278. https://doi.org/10.1098/rsta.2015.0278. [6] A. Johnston, P. Hubert, G. Fernlund, R. Vaziri, A. Poursartip, Process modelling of composite structures employing a virtual autoclave concept, Sci. Eng. Compos. Mater. (1996). [7] N. Zobeiry, K.D. Humfeld, An Iterative Scientific Machine Learning Approach for Discovery of Theories Underlying Physical Phenomena, ArXiv Prepr. arXiv:1909 (2019). [8] G. Fernlund, A. Osooly, A. Poursartip, R. Vaziri, R. Courdji, K. Nelson, P. George, L. Hendrickson, J. Griffith, Finite element based prediction of process-induced deformation of autoclaved composite structures using 2D process analysis and 3D structural analysis, Compos. Struct. (2003). https://doi.org/10.1016/S0263-8223(03)00117-X. [9] G. Fernlund, N. Rahman, R. Courdji, M. Bresslauer, A. Poursartip, K. Willden, K. Nelson, Experimental and numerical study of the effect of cure cycle, tool surface, geometry, and lay-up on the dimensional fidelity of autoclave-processed composite parts, Compos. - Part A Appl. Sci. Manuf. (2002). https://doi.org/10.1016/S1359-835X(01)00123-3. [10] G. Fernlund, A. Poursartip, K. Nelson, M. Wilenski, F. Swanstrom, Process modeling for dimensional control-sensitivity analysis of a composite spar process, in: Int. SAMPE Symp. Exhib., 1999. [11] G. Fernlund, K. Nelson, A. Poursartip, Modeling of process induced deformations of composite shell structures, Int. SAMPE Symp. Exhib. (2000). [12] J. Fabris, C. Mobuchon, N. Zobeiry, D. Lussier, G. Fernlund, A. Poursartip, Introducing thermal history producibility assessment at conceptual design, in: Int. SAMPE Tech. Conf., 2015. [13] N. Zobeiry, A. Poursartip, Theory-Guided Machine Learning for Processing of Advanced Composites, Adv. Mater. under revi (2019). [14] N. Zobeiry, D. VanEe, F. Anthony, A. Poursartip, Theory-guided machine learning for process simulation of composites theory-guided machine learning composites processing modelling for manufacturability assessment in preliminary design, in: NAFEMS 17th World Congr., Quebec City, Canada, 2019. [15] D. Heaven, Why deep-learning AIs are so easy to fool, Nature. 574 (2019) 163–166. https://doi.org/10.1038/d41586-019-03013-5. [16] N. Wagner, J.M. Rondinelli, Theory-guided machine learning in materials science, Front. Mater. 3 (2016). https://doi.org/10.3389/fmats.2016.00028. [17] A. Karpatne, G. Atluri, J.H. Faghmous, M. Steinbach, A. Banerjee, A. Ganguly, S. Shekhar, N. Samatova, V. Kumar, Theory-guided data science: A new paradigm for scientific discovery from data, IEEE Trans. Knowl. Data Eng. 29 (2017) 2318–2331. https://doi.org/10.1109/TKDE.2017.2720168. [18] C. Sacco, A. Baz Radwan, T. Beatty, R. Harik, Machine learning based AFP inspection: A tool for characterization and integration, in: Int. SAMPE Tech. Conf., Soc. for the Advancement of Material and Process Engineering, 2019. https://doi.org/10.33599/nasampe/s.19.1594. [19] D. Heider, M.J. Piovoso, J.W. Gillespie, A neural network model-based open-loop optimization for the automated thermoplastic composite tow-placement system, Compos. Part A Appl. Sci. Manuf. 34 (2003) 791–799. https://doi.org/10.1016/S1359-835X(03)00120-9. [20] D. Nielsen, R. Pitchumani, Intelligent model-based control of preform permeation in liquid composite molding processes, with online optimization, Compos. - Part A Appl. Sci. Manuf. 32 (2001) 1789–1803. https://doi.org/10.1016/S1359-835X(01)00013-6. [21] J. Luo, Z. Liang, C. Zhang, B. Wang, Optimum tooling design for resin transfer molding with virtual manufacturing and artificial intelligence, Compos. - Part A Appl. Sci. Manuf. 32 (2001) 877–888. https://doi.org/10.1016/S1359-835X(00)00147-0. [22] C.W. Lee, B.P. Rice, Modeling of epoxy cure reaction rate by neural network, in: Int. SAMPE Tech. Conf., 1996. [23] C.W. Lee, T. Gibson, K.A. Tienda, T.M. Storage, Reaction rate and viscosity model development for Cytec’s Cycom® 5320 family of resins, in: Int. SAMPE Tech. Conf., 2010. [24] N. Rai, R. Pitchumani, Rapid cure simulation using artificial neural networks, Compos. Part A Appl. Sci. Manuf. (1997). https://doi.org/10.1016/S1359-835X(97)00046-8. [25] J.T. Lin, D. Bhattacharyya, V. Kecman, Multiple regression and neural networks analyses in composites machining, Compos. Sci. Technol. 63 (2003) 539–548. https://doi.org/10.1016/S0266-3538(02)00232-4. [26] N.I.E. Farhana, M.S. Abdul Majid, M.P. Paulraj, E. Ahmadhilmi, M.N. Fakhzan, A.G. Gibson, A novel vibration based non-destructive testing for predicting glass fibre/matrix volume fraction in composites using a neural network model, Compos. Struct. 144 (2016) 96–107. https://doi.org/10.1016/j.compstruct.2016.02.066. [27] K. Manohar, T. Hogan, J. Buttrick, A.G. Banerjee, J.N. Kutz, S.L. Brunton, Predicting shim gaps in aircraft assembly with machine learning and sparse sensing, J. Manuf. Syst. 48 (2018) 87–95. https://doi.org/10.1016/j.jmsy.2018.01.011. [28] Www.convergent.ca/products/raven-simulation-software, RAVEN simulation software, (2013). www.convergent.ca/products/raven-simulation-software. [29] Www.convergent.ca/products/compro-simulation-software, COMPRO simulation software, (2014). www.convergent.ca/products/compro-simulation-software.

Conference: SAMPE 2020 | Virtual Series

Publication Date: 2020/06/01

SKU: TP20-0000000053

Pages: 11

Price: FREE