Title: A MACHINE LEARNING-BASED ACCELERATED PYROLYSIS CHARACTERIZATION AND OPTIMIZATION OF HIGH-TEMPERATURE COMPOSITES

Authors: Paulina Portales Picazo, Roger Cheng, Alexander Gray, Navid Zobeiry

DOI: 10.33599/nasampe/s.23.0104

Abstract: Manufacturing polymer-based composites for high-temperature applications is a multi-step and complex process where the material undergoes several transformations. This typically includes a lay-up step, a curing process, a high-temperature pyrolytic process to convert the resin phase into amorphous carbon, followed by several resin backfill steps, and finally graphitization to achieve the desired crystalline structure of carbon atoms. The parameters used during the pyrolysis process significantly affect the degradation reactions, the final yield, laminate permeability, and hence end-part properties. Typically, extensive testing is required to characterize pyrolysis kinetics and identify optimal processing conditions. This paper introduces a novel probabilistic machine-learning (ML)-based framework for accelerated characterization and optimization of the pyrolysis process utilizing theory-based transformations of limited experimental data affected by noise and errors. Gaussian Process Regression (GPR), a Bayesian probabilistic approach to regression, is used to determine optimal test parameters to characterize pyrolysis kinetics accurately and achieve the desired yield while satisfying specific constraints. This approach can be used to improve the processing efficiency of high-temperature composites and increase their performance with minimal experimental effort.

References: 1. Torres-Herrador, F., Coheur, J., Panerai, F., et al. “Competitive kinetic model for the pyrolysis of the Phenolic Impregnated Carbon Ablator.” Aerospace Science and Technology 100 (2020). DOI https://doi.org/10.1016/j.ast.2020.105784 2. Tzeng, S.-S., & Chr, Y.-G. “Evolution of microstructure and properties of phenolic resin-based carbon/carbon composites during pyrolysis.” Materials Chemistry and Physics 73 (2002). 3. Nam, J.-D & Seferis, James. “Volatile Evolution in Thermoset Composites from Processing to Degradation.” Science and Engineering of Composite Materials 2 (1993). DOI 10.1515/SECM.1993.2.3.211. 4. Torres-Herrador, F., Eschenbacher, A., Coheur, J., Blondeau, J., Magin, T. E., & van Geem, K. M. “Decomposition of carbon/phenolic composites for aerospace heatshields: Detailed speciation of phenolic resin pyrolysis products.” Aerospace Science and Technology 119 (2021). DOI https://doi.org/10.1016/j.ast.2021.107079 5. Oliveira de Souza, W., Garcia, K., de Avila Von Dollinger, C., & Pardini, L. “Electrical Behavior of Carbon Fiber/Phenolic Composite during Pyrolysis.” Materials Research 18 (2015): 1209-1216. DOI http://dx.doi.org/10.1590/1516-1439.000515 6. Trick, K. A., Saliba, T. E., & Sandhu, S. S. “A kinetic model of the pyrolysis of the phenolic resin in a carbon/phenolic composite.” Carbon 135(3) (1997): 398-401. DOI https://doi.org/10.1016/S0008-6223(97)89610-8. 7. Wynn, M. & Zobeiry, N. “Investigating the Effect of Temperature History on Crystal Morphology of Thermoplastic Composites Using In Situ Polarized Light Microscopy and Probabilistic Machine Learning.” Polymers 15(1),18. (2023). 8. Freed, Y., Salviato, M. & Zobeiry, N. “Implempentation of a Probabilistic Machine Learning Strategy for Failure Predictions of Adhesively Bonded Joints Using Cohesive Zone Modeling.” International Journal of Adhesion and Adhesives 118, 103226 (2022). 9. Freed, Y., Zobeiry, N., & Salviato, M. “Development of aviation industry-oriented methodology for failure predictions of brittle bonded joints using probabilistic machine learning”. Composite Structures 297, 115979 (2022). 10. Schellhase, K., Brushaber, R., Wu, H., et al. “Development of New Thermal Protection Systems Based on Polysiloxane/Silica Composites: Properties Characterization I.” SAMPE Conference Proceedings. Long Beach, CA, May 23-26 2016. 11. Schellhase, K., Koo, J., Buffy, J., et al. “Development of New Thermal Protection Systems Based on Polysiloxane/Silica Composites: Properties Characterization II.” SAMPE Conference Proceedings. Seattle, WA, May 22-25 2017. DOI https://doi.org/10.1016/j.carbon.2009.09.036 12. Jiang, H., Wang, J., Wu, S., Wang, B., & Wang, Z. “Pyrolysis kinetics of phenol-formaldehyde resin by non-isothermal thermogravimetry.” Carbon, 48(2) (2010): 325-358. DOI https://doi.org/10.1016/j.carbon.2009.09.036 13. Beckers, Thomas. “An Introduction to Gaussian Process Models”. (2021). DOI https://doi.org/10.48550/arXiv.2102.05497 14. Liu, C. L., Dong, W.-S., Song, J. R., & Liu, L. “Evolution of microstructure and properties of phenolic fibers during carbonization.” Materials Science and Engineering A 459(1–2) (2007): 347–354. DOI https://doi.org/10.1016/j.msea.2007.02.067

Conference: SAMPE 2023

Publication Date: 2023/04/17

SKU: TP23-0000000104

Pages: 9

Price: $18.00