Predicting the Deformation Behavior of Biocomposites using Combined Mathematical and AI-Based Modeling

The use of fossil plastic materials is being significantly replaced by renewable raw materials, such as natural short fiber reinforced (NSFR) polymer composites (biocomposites). Due to the increasing popularity of biocomposites nowadays, ranging from their applications in the food packaging to automotive and aerospace industry, volume of their experimental research is huge. However, experimental research is costly and time consuming. In this research, a micromechanically based constitutive model is proposed to investigate and simulate the elastic-viscoplastic and micro- to macro-scopic deformation behavior of the biocomposites consisting of short biofibers (hemp) and a semi-crystalline polymer matrix (PLA). However, also the constitutive mathematical modeling as such is computationally time-consuming when applied to predict long-term deformation behavior in large design spaces. Therefore, a combination of the proposed mathematical model and an AI-model is proposed. Idea of the concept is that the mathematical model is solely used to predict high-quality data for machine learning (ML) which is computationally very efficient.