Predicting mechanical properties of CFRP composites using data-driven models with comparative analysis
Ammar Alsheghri, A. H. Al-Hammadi, Vassilis Drakonakis, Haris Doumanidis, Imad Barsoum, Maher Maalouf
Abstract
Carbon fiber reinforced polymer (CFRP) composites are increasingly utilized for their lightweight and superior mechanical properties. This study uses machine learning models to predict the mechanical properties of CFRP composites based on the volume fraction of carbon nanotubes (CNTs), interlayer volume fraction, glass transition temperature, and manufacturing pressure. Sixty-two samples covering nine different types of CFRPs were designed, manufactured, and experimentally tested. Three machine learning models, namely ridge regression, random forest, and support vector regression, were trained on the data and compared. The results demonstrated a high prediction accuracy for the flexural strength (R2 = 0.966), flexural modulus (R2 = 0.871), and the mode-II energy release rate (R2 = 0.903). The study highlights the effectiveness of data-driven models in predicting key mechanical properties of CFRP composites, potentially reducing the need for extensive experimental testing and facilitating more efficient material design.