An ABAQUS® plug-in for generating virtual data required for inverse analysis of unidirectional composites using artificial neural networks

Abstract This paper presents a robust ABAQUS ® plug-in called Virtual Data Generator ( VDGen ) for generating virtual data identifying the uncertain material properties in unidirectional lamina through artificial neural networks (ANNs). The supports 3D finite element models of unit cells with square and hexagonal fibre arrays, uses Latin-Hypercube sampling methods robustly imposes periodic boundary conditions. Using generated from plug-in, ANN is demonstrated to explicitly accurately parameterise relationship between mechanical fibre/matrix interphase parameters at microscale UD macroscale. tool applicable general enables easy establishment high-fidelity micromechanical identified properties.