Designing formulations of bio-based, multicomponent epoxy resin systems via machine learning

Titelangaben

Albuquerque, Rodrigo Q. ; Rothenhäusler, Florian ; Ruckdäschel, Holger:
Designing formulations of bio-based, multicomponent epoxy resin systems via machine learning.
In: MRS Bulletin. (30 Juni 2023) .
ISSN 1938-1425
DOI der Verlagsversion: https://doi.org/10.1557/s43577-023-00504-9

Volltext

	Format: PDF Name: s43577-023-00504-9.pdf Version: Veröffentlichte Version Verfügbar mit der Lizenz Creative Commons BY 4.0: Namensnennung
	Download (2MB)

Abstract

Petroleum-based epoxy resins are commonly used as a matrix in fiberreinforced polymer composites. Bio-based epoxy resin systems could be a more environmentally friendly alternative to conventional epoxy resins. In this work, novel formulations of multicomponent, amino acid-based resin systems exhibiting high or low glass-transition temperatures (Tg) were designed via Bayesian optimization and active learning techniques. After only five high-Tg experiments, thermosets with Tg already higher than those of the individual components were obtained, pointing out the existence of synergistic effects among the amino acids used and confirming the efficiency of the theoretical design. Linear and nonlinear machine learning (ML) models successfully predicted Tg with a mean absolute error of 3.98◦C and R² score of 0.91. A price reduction of up to 13.7% was achieved while maintaining the Tg of 130◦C using an optimized formulation. The LASSO model provided information about the dependence of Tg on the number of active hydrogen atoms and aromaticity. This study highlights the importance of Bayesian optimization and ML to achieve a more sustainable development of epoxy resin materials.