The Optimal Values of Hashin Damage Parameters Predict Using Inverse Problem in a CFRP Composite Material

Abstract

The ever-increasing demand for advanced composite materials in industries like aerospace and automotive has spurred the drive to address their inherent weaknesses. This pursuit is facilitated by the availability of numerical simulations and artificial intelligence, offering a cost-effective means to comprehensively study various phenomena without excessive reliance on experimentation. While existing models in the scientific realm provide a foundation for composite material modeling, achieving results closely aligned with experimental data is often challenging due to the variation of the parameters and conditions. This present study introduces an innovative approach aimed at optimizing composite material performance and minimizing discrepancies between experimental and numerical outcomes. This approach leverages sophisticated optimization algorithms to fine-tune the Hashin damage parameters, resulting in a highly accurate model. Furthermore, the incorporation of an Artificial Neural Network (ANN) via an inverse problem based on Jaya’s algorithm solving strategy facilitates the prediction of optimal parameters, ensuring a significant reduction in error. This novel methodology presents a promising avenue for elevating the efficiency and reliability of CFRP composite materials in practical applications.