DIGITAL LIBRARY: CAMX 2024 | SAN DIEGO, CA | SEPTEMBER 9-12

Get This Paper

Reconstruction of Internal Morphology in Molded Platelet Composite Using Residual Stresses and Deep Convolutional Neural Network

Description

Title: Reconstruction of Internal Morphology in Molded Platelet Composite Using Residual Stresses and Deep Convolutional Neural Network

Authors: Mohammad N. Saquib, Richard Larson, Jiang Li, Sergii G. Kravchenko, Oleksandr G. Kravchenko

DOI: 10.33599/nasampe/c.24.0282

Abstract: Compression molding of discontinuous long fiber composite materials is crucial for meeting industry demands for lightweight, durable products manufactured at a high rate. However, the variability in orientation state of prepreg platelet molded composites, resulting from stochastic molding conditions, poses challenges to reliability. This study introduces a novel computational tool aimed at rapid non-destructive reconstruction of fiber orientation distribution (FOD) in each layer in prepreg platelet molded composite (PPMC) plates. While traditional micro CT would require significant time to generate layer based FOD, a deep convolutional neural network (DCNN) can achieve an order of magnitude increase in part inspection speed. The DCNN utilizes thermal residual strain components on the surface as input to predict FOD throughout the volume. The neural network was trained using thousands of synthetic PPMC morphologies from finite element simulation data. The trained DCNN was used to reconstruct the microstructure of the entire PPMC synthetic coupon. Progressive failure analysis (PFA) was performed on the reconstructed tensile coupons and compared to the PFA simulation of the initial synthetic morphology, which was considered as a ground truth. The failure analysis of the reconstructed PPMC coupon showed 14.53% error in predicting a tensile strength. Furthermore, the observed damage modes and failure locations closely matched between the true and reconstructed morphology, demonstrating that the proposed DCNN model is capable of full morphology reconstruction in PPMC materials.

References: [1] M. G. Bader, “Selection of composite materials and manufacturing routes for cost-effective performance,” Composites Part A: Applied Science and Manufacturing, vol. 33, no. 7, pp. 913–934, Jul. 2002, doi: 10.1016/S1359-835X(02)00044-1. [2] Discontinuous Fiber Composites. MDPI - Multidisciplinary Digital Publishing Institute, 2019. [3] S. Sattar, B. B. Laredo, S. G. Kravchenko, and O. G. Kravchenko, “Effect of platelet length and stochastic morphology on flexural behavior of prepreg platelet molded composites,” Polymer Composites, vol. 44, no. 4, pp. 2122–2137, Apr. 2023, doi: 10.1002/pc.27230. [4] S. G. Kravchenko, “Failure Analysis in Platelet Molded Composite Systems,” Theses and Dissertations Available from ProQuest, pp. 1–340, Jan. 2017. [5] S. Sattar, B. B. Laredo, D. Pedrazzoli, M. Zhang, and O. G. Kravchenko, “Understanding Size Effects on Flexural Properties in Discontinuous Fiber Reinforced Nylon Composites,” The Composites and Advanced Materials Expo (CAMX), 2020, Accessed: Apr. 07, 2024. [Online]. Available: https://www.nasampe.org/store/viewproduct.aspx?id=17720565 [6] M. N. Saquib, “Ballistic Impact on a Sandwich-Structured Composite Armor,” M.S., Texas A&M University - Kingsville, United States -- Texas, 2019. Accessed: Oct. 27, 2023. [Online]. Available: https://www.proquest.com/docview/2507724099/abstract/48CE060DBE39484BPQ/1 [7] S. Alam and M. N. Saquib, “Impact Analysis of a Composite Armor System,” in Volume 9: Mechanics of Solids, Structures, and Fluids, Salt Lake City, Utah, USA: American Society of Mechanical Engineers, Nov. 2019, p. V009T11A009. doi: 10.1115/IMECE2019-11748. [8] D. Leblanc, B. Landry, A. Levy, P. Hubert, S. Roy, and A. Yousefpour, “Compression moulding of complex parts using randomly-oriented strands thermoplastic composites,” presented at the International SAMPE Technical Conference, Jun. 2014. [9] S. G. Kravchenko et al., “Tensile properties of a stochastic prepreg platelet molded composite,” Composites Part A: Applied Science and Manufacturing, vol. 124, p. 105507, Sep. 2019, doi: 10.1016/j.compositesa.2019.105507. [10] S. Yamashita, K. Hashimoto, H. Suganuma, and J. Takahashi, “Experimental characterization of the tensile failure mode of ultra-thin chopped carbon fiber tape-reinforced thermoplastics,” Journal of Reinforced Plastics and Composites, vol. 35, no. 18, pp. 1342–1352, Sep. 2016, doi: 10.1177/0731684416651134. [11] P. Feraboli, E. Peitso, F. Deleo, T. Cleveland, and P. B. Stickler, “Characterization of Prepreg-Based Discontinuous Carbon Fiber/Epoxy Systems,” Journal of Reinforced Plastics and Composites, vol. 28, no. 10, pp. 1191–1214, May 2009, doi: 10.1177/0731684408088883. [12] R. A. Cutting, F. Rios-Tascon, and J. E. Goodsell, “Experimental investigation of the crush performance of prepreg platelet molding compound tubes,” Journal of Composite Materials, vol. 54, no. 27, pp. 4311–4324, Nov. 2020, doi: 10.1177/0021998320929418. [13] J. Teuwsen, S. K. Hohn, and T. A. Osswald, “Direct Fiber Simulation of a Compression Molded Ribbed Structure Made of a Sheet Molding Compound with Randomly Oriented Carbon/Epoxy Prepreg Strands—A Comparison of Predicted Fiber Orientations with Computed Tomography Analyses,” J. Compos. Sci., vol. 4, no. 4, p. 164, Oct. 2020, doi: 10.3390/jcs4040164. [14] S. Sattar, B. Beltran Laredo, D. Pedrazzoli, M. Zhang, S. G. Kravchenko, and O. G. Kravchenko, “Mechanical behavior of long discontinuous glass fiber nylon composite produced by in-situ polymerization,” Composites Part A: Applied Science and Manufacturing, vol. 154, p. 106779, Mar. 2022, doi: 10.1016/j.compositesa.2021.106779. [15] D. E. Sommer, S. G. Kravchenko, W. B. Avery, and R. B. Pipes, “Mechanisms of notch insensitivity in long-fiber discontinuous, prepreg platelet compression molded composites,” Composites Part A: Applied Science and Manufacturing, vol. 162, p. 107133, 2022. [16] P. Feraboli, “Modified SDOF Models for Improved Representation of the Impact Response of Composite Plates,” Journal of Composite Materials, vol. 40, no. 24, pp. 2235–2255, Dec. 2006, doi: 10.1177/0021998306062318. [17] P. Bing, X. Hui-min, H. Tao, and A. Asundi, “Measurement of coefficient of thermal expansion of films using digital image correlation method,” Polymer Testing, vol. 28, no. 1, pp. 75–83, Feb. 2009, doi: 10.1016/j.polymertesting.2008.11.004. [18] O. G. Kravchenko, S. G. Kravchenko, A. Casares, and R. B. Pipes, “Digital image correlation measurement of resin chemical and thermal shrinkage after gelation,” J Mater Sci, vol. 50, no. 15, pp. 5244–5252, Aug. 2015, doi: 10.1007/s10853-015-9072-3. [19] R. A. Larson, R. Hoque, V. Jamora, J. Li, S. Kravchenko, and O. Kravchenko, “Hyperparameters Effect in Deep Convolutional Neural Network Model on Prediction of Fiber Orientation Distribution in Prepreg Platelet Molded Composites,” in AIAA SCITECH 2022 Forum, San Diego, CA & Virtual: American Institute of Aeronautics and Astronautics, Jan. 2022. doi: 10.2514/6.2022-0103. [20] P. Seibert, A. Raßloff, K. Kalina, M. Ambati, and M. Kästner, “Microstructure Characterization and Reconstruction in Python: MCRpy,” Integr Mater Manuf Innov, vol. 11, no. 3, pp. 450–466, Sep. 2022, doi: 10.1007/s40192-022-00273-4. [21] D. M. Dimiduk, E. A. Holm, and S. R. Niezgoda, “Perspectives on the Impact of Machine Learning, Deep Learning, and Artificial Intelligence on Materials, Processes, and Structures Engineering,” Integr Mater Manuf Innov, vol. 7, no. 3, pp. 157–172, Sep. 2018, doi: 10.1007/s40192-018-0117-8. [22] A. Bhaduri, A. Gupta, A. Olivier, and L. Graham-Brady, “An efficient optimization based microstructure reconstruction approach with multiple loss functions,” Computational Materials Science, vol. 199, p. 110709, Nov. 2021, doi: 10.1016/j.commatsci.2021.110709. [23] N. Zobeiry, J. Reiner, and R. Vaziri, “Theory-guided machine learning for damage characterization of composites,” Composite Structures, vol. 246, p. 112407, Aug. 2020, doi: 10.1016/j.compstruct.2020.112407. [24] K. Breuer and M. Stommel, “Prediction of Short Fiber Composite Properties by an Artificial Neural Network Trained on an RVE Database,” Fibers, vol. 9, no. 2, p. 8, Feb. 2021, doi: 10.3390/fib9020008. [25] Y. Tang, Q. Wang, H. Wang, J. Li, and Y. Ke, “A novel 3D laser scanning defect detection and measurement approach for automated fibre placement,” Meas. Sci. Technol., vol. 32, no. 7, p. 075201, Jul. 2021, doi: 10.1088/1361-6501/abda95. [26] K. Sreeshan, R. Dinesh, and K. Renji, “Nondestructive inspection of aerospace composite laminate using thermal image processing,” SN Appl. Sci., vol. 2, no. 11, p. 1830, Nov. 2020, doi: 10.1007/s42452-020-03619-9. [27] S. Zambal, C. Heindl, C. Eitzinger, and J. Scharinger, “End-to-end defect detection in automated fiber placement based on artificially generated data,” in Fourteenth International Conference on Quality Control by Artificial Vision, C. Cudel, S. Bazeille, and N. Verrier, Eds., Mulhouse, France: SPIE, Jul. 2019, p. 68. doi: 10.1117/12.2521739. [28] C. Sacco, A. Baz Radwan, A. Anderson, R. Harik, and E. Gregory, “Machine learning in composites manufacturing: A case study of Automated Fiber Placement inspection,” Composite Structures, vol. 250, p. 112514, Oct. 2020, doi: 10.1016/j.compstruct.2020.112514. [29] M. N. Saquib, R. Larson, S. Sattar, J. Li, S. Kravchenko, and O. Kravchenko, “Experimental Validation of Reconstructed Microstructure via Deep Learning in Discontinuous Fiber Platelet Composite,” Journal of Applied Mechanics, pp. 1–61, Nov. 2023, doi: 10.1115/1.4063983. [30] R. LARSON, J. LI, S. G. KRAVCHENKO, and O. G. KRAVCHENKO, “Fiber Orientation Prediction at Multiple Thicknesses in a PPMC Tensile Coupon,” in PROCEEDINGS OF THE AMERICAN SOCIETY FOR COMPOSITES-THIRTY-EIGHTH TECHNICAL CONFERENCE, 2023. Accessed: Apr. 26, 2024. [Online]. Available: https://scholar.google.com/scholar?cluster=10932736432130836459&hl=en&oi=scholarr [31] R. Larson, R. Hoque, V. Jamora, J. Li, S. G. Kravchenko, and O. G. Kravchenko, “Recognition of local fiber orientation state in prepreg platelet molded composites via deep learning,” Engineering Applications of Artificial Intelligence, vol. 133, p. 108602, Jul. 2024, doi: 10.1016/j.engappai.2024.108602. [32] M. N. Saquib, S. Sattar, R. Larson, J. Li, S. G. Kravchenko, and O. G. Kravchenko, “RECONSTRUCTION OF FULL FIBER ORIENTATION DISTRIBUTION IN MOLDED COMPOSITES USING DEEP LEARNING,” presented at the SPE Automotive Composites Conference and Exhibition, Novi, MI, 2022. [Online]. Available: https://speautomotive.com/wp-content/uploads/2022/10/Reconstruction-of-Full-FIber-Orientation-Distribution-in-Molded-Composites_SAQUIB.pdf [33] S. G. Advani and C. L. Tucker, “The Use of Tensors to Describe and Predict Fiber Orientation in Short Fiber Composites,” Journal of Rheology, vol. 31, no. 8, pp. 751–784, Nov. 1987, doi: 10.1122/1.549945. [34] A. Forghani, M. Shahbazi, N. Zobeiry, A. Poursartip, and R. Vaziri, “An overview of continuum damage models used to simulate intralaminar failure mechanisms in advanced composite materials,” in Numerical Modelling of Failure in Advanced Composite

Conference: CAMX 2024 | San Diego CA

Publication Date: 2024/9/9

SKU: TP24-0000000282

Pages: 15

Price: $30.00

Get This Paper