earticle

영어

This study proposes a surrogate model framework that integrates finite element analysis and deep learning to rapidly estimate equivalent material properties of patterned sheets. Conventional homogenization methods can only be applied after the pattern geometry has been finalized, requiring additional modeling and simulation. In contrast, the proposed approach establishes a surrogate model in advance, enabling the immediate estimation of equivalent material properties once the pattern geometry is defined. A dataset of 5,000 cases was generated using simulations, and Bayesian hyperparameter optimization was applied to improve model performance. The surrogate model achieved R² values above 0.99 for all target properties, confirming high internal consistency. Experimental validation with patterned STS304 specimens yielded meaningful results, with all errors remaining within 15%, which demonstrates the reliability of the proposed surrogate model despite minor deviations caused by fabrication imperfections and limited training data. Despite these limitations, the proposed system enables instant estimation of equivalent properties from pattern geometries, offering significant reduction in computational cost and design time. This approach enhances design reliability and provides a practical tool for the application of patterned materials in industrial engineering.