Material Parameter Identification of Elastoplastic Constitutive Models Using Machine Learning Approaches

Today, the vast majority of design tasks are based on simulation tools. However, success depends accurate identification constitutive parameters materials, i.e., its calibration. The classical parameter strategy, which relies homogeneous tests, does not provide and robust results required by automotive aerospace industry. Recently, numerical inverse methods, such as Finite Element Model Updating (FEMU) Virtual Fields Method (VFM), have been developed for identifying heterogeneous tests. Although these methods proven effective linear non-linear models, process is complex, making it computationally expensive. In this work, a machine learning algorithm (XGBoost) used to pursue goal models using A statistical analysis conducted identify correlation between training dataset size, mechanical tests material parameters. understand importance different inputs reduce computational time.