Enhancing Material Characterization: Multifidelity Deep Neural Network for Stress-Strain Curve Prediction From Small Punch Test Data

The accurate determination of a material's true stress-strain relationship is crucial for predicting its performance in engineering applications. However, traditional methods for determining material behavior often depend on extensive experiments. Although these methods are essential, they are inherently complex, time-consuming, and often suffer from limited accuracy and reliability when small sample sizes are involved. To address these challenges, this article introduces a multifidelity deep neural network architecture that utilizes both low-fidelity and high-fidelity datasets to predict true stress-strain curves from small punch test (SPT) data. The low-fidelity data are calculated using an empirical function based on the Swift model, providing an initial understanding of material behavior. In contrast, the finite element method (FEM) provides high-fidelity data, enhancing the model's ability to capture complex material characteristics. This framework merges low-fidelity and high-fidelity networks to estimate mechanical properties with low-fidelity and high-fidelity data. The effectiveness of the proposed approach has been demonstrated through experimental validation, highlighting its exceptional ability to generalize across material thicknesses and properties beyond the training set. The proposed approach outperformed traditional empirical methods and maintained strong performance even when applied to real-world materials.