Using asymptotic homogenization and machine learning to derive a 3D trace theory for GFRP

Abstract

Tsai’s modulus was proposed as a trace theory for CFRP, where only one property is measured experimentally and the other four properties are computed using the normalized trace relation. An extension of this theory is proposed for GFRP. Laminae elastic properties are generated using the asymptotic homogenization and a machine learning training is performed applying decision trees algorithm to define normalized trace relations for GFRP. The results are validated with experimental data of 12 GFRP laminae, indicating average errors around 5% for longitudinal and transversal elastic moduli and in-plane Poisson’s ratio, and around 10% for in-plane and out-of-plane shear moduli.