Data augmentation of scarce experimental data for constitutive models

Abstract

This study explores two different data augmentation approaches to generate artificial data for the training process of machine learned constitutive models. The cyclic Ramberg-Osgood model was employed by predicting the stress amplitude at 1% strain amplitude in the materials. A baseline model using 96 materials in the training process was first defined. Ten materials out of the 96 were sampled to be augmented. The first augmentation approach was to perform a linear numerical scaling of sampled materials to generate artificial copies. However, this approach lack the real physical behaviour of the material. Thus, to account for the physical behaviour, an augmentation based on empirical statistical distributions of the material behaviour of the sampled materials was made. This generates improved artificial data with a reliable outcome. Hence, a robust, accurate and efficient training procedure was obtained compared to used experimental data.