Exploring the predictive potential of artificial neural networks in enhancing mechanical properties of derivatives of graphene nanocomposites: a data-driven approach

The given manuscript delves into the realm of materials science and engineering, specifically focusing on the utilization of different derivatives of graphene reinforced in matrix material (DGMM’s) to enhance mechanical properties. Graphene (Gr), with its remarkable characteristics, holds immense promise as reinforcement in composites and nanocomposites (NCs). Using linear regression and artificial neural networks (ANN) framework, this study predicts the weight% of enhanced mechanical properties in DGMMs. By analyzing a dataset comprising various graphene derivatives, matrix materials, processing methods, and resulting enhancements, the ANN model offers valuable insights into the intricate relationships within these NCs. The findings reveal the potential of ANN models in optimizing the design and fabrication processes of DGMMs, thereby accelerating materials development and enabling tailored formulations for specific applications. Also, the given manuscript motivates for future research to enhance the predictive accuracy and broaden the scope of applications for DGMMs.