Numerical analysis for semiconductor/battery system

Machine learning algorithms help identify hidden patterns in large datasets, enabling us to optimize material properties and reduce trial-and-error experimentation. Deep learning models further enhance our ability to simulate complex material behaviors and predict their performance under various conditions. This cutting-edge approach allows us to explore innovative alloys and tailor material properties, significantly advancing the field of materials science.

Our research lab focuses on the integration of machine learning and deep learning techniques with computational simulations to accelerate the development and characterization of materials. By leveraging these advanced technologies, we are able to efficiently analyze and predict the microstructure-property relationships of metals, which are crucial for designing high-performance materials.

Selected Papers: 

(1) K. Jeong et al., Prediction of uniaxial tensile flow using finite element-based indentation and optimized artificial neural networks, Materials & Design 196, 109104 (2020)

(2) K. Jeong et al., Deep learning-based indentation plastometry in anisotropic materials, International Journal of Plasticity 157, 103403 (2022)

(3) K. Jeong et al., Parameter determination of anisotropic yield function using neural network-based indentation plastometry, International Journal of Mechanical Sciences 263, 108776 (2024)