An Artificial Neural Network (ANN) Model for Predicting Water Absorption of Nanoclay-Epoxy Composites

CAPIEL, GUILLERMINA; FLORENCIA, ARROSIO; ALVAREZ, VERA A.; MONTEMARTINI, PABLO E.; MORÁN, JUAN

Journal of Materials Science and Chemical Engineering

scientific research publishing

Lugar: New York; Año: 2019 vol. 07 p. 87 - 97

2327-6045

Glass fiber reinforced epoxy (GFRE) composite materials are prone to sufferfrom water absorption due to their heterogeneous structure. The main processgoverning water absorption is diffusion of water molecules through theepoxy matrix. However, hydrolytic degradation may also take place duringcomponents service life especially due high temperatures. In order to mitigatethe effects of the water diffusive processes in the deterioration of in-servicebehavior of epoxy matrix composites, the use of chemically modified nanoclaysas an additive has been proposed and studied in previous works [1]. Inthis work, an Artificial Neural Network (ANN) model was developed for betterunderstanding and predicting the influence of modified and unmodifiedbentonite addition on the water absorption behavior of epoxy-anhydride systems.An excellent correlation between model and experimental data wasfound. The ANN model allowed the identification of critical points like theprecise temperature at which a particular system?s water uptake goes beyonda predefined threshold,