Designing an Improved Interface in Graphene/Polymer Composites Through Machine Learning
The matrix-reinforcement interface has been studied extensively to enhance the performance of polymer matrix composites (PMCs). One commonly practiced approach is functionalization of the reinforcement, which significantly improves the interfacial interaction. A molecular dynamics (MD) and machine learning (ML) workflow is proposed to identify the optimal functionalization parameters that result in improved mechanical performance of a 3-layer graphene nanoplatelet (GNP)/bismaleimide (BMI) nanocomposite. MD is used to generate the training set for a graph convolutional neural network (GCN). This article reports the MD methodology and an example mechanical response from a pull-out simulation. Upcoming work in the proposed MD-ML workflow for designing a nanocomposite with improved mechanical performance is also discussed.
Proceedings of the American Society for Composites - 37th Technical Conference, ASC 2022
Designing an Improved Interface in Graphene/Polymer Composites Through Machine Learning.
Proceedings of the American Society for Composites - 37th Technical Conference, ASC 2022.
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/16536