Pseudograin decomposition of short fiber-reinforced plastics for two-step homogenization using machine learning approach.

• ML-aided two-step homogenization framework of short fiber-reinforced plastics is proposed. • Series–parallel artificial neural networks were developed to 12 pseudograins from a fiber orientation tensor. • ANN model and Mori–Tanaka & Voigt homogenization were implemented into user material subroutine. • The accuracy of the proposed framework was validated with an error of about 3%. Decomposing the representative volume element (RVE) of short fiber-reinforced plastics (SFRPs) into several pseudograins (PGs) is essential for understanding its effective mechanical behavior. However, conventional PG decomposition methodologies are limited by their high computational costs due to iteration-based algorithms. To address this, we propose a machine learning-assisted PG decomposition procedure that utilizes a series–parallel artificial neural network (ANN) system to facilitate the time-consuming decomposition process. To validate the effectiveness of our proposal, we implemented a two-step homogenization framework of SFRP that consists of the series–parallel ANN system, Mori-Tanaka model, and Voigt model into ABAQUS user material subroutine (UMAT). The elastic modulus values predicted by the UMAT are found to be in good agreement with both DIGIMAT-MF and experimental values, while also maintaining low computational time. [ABSTRACT FROM AUTHOR]