- E-mail.dongilshin@postech.ac.kr
- Website.https://datasolid.postech.ac.kr
- Degree.Ph. D. Seoul National University (2019)
- Lab.Data-driven Solid mechanics Laboratory
Our research group focuses on the computational simulation and optimization of solid mechanics problems, mainly translating data into actionable decisions within complex systems. Our primary research interests include solving problems related to structural optimization, real-time simulation, reduced-order modeling, and uncertainty quantification by combining data-driven methodologies, such as artificial intelligence, with physics-based models. Our research in developing solid mechanics theories, analyses, modeling, and design across various fields is essential for ensuring mechanical performance, efficiency, safety, and sustainability. Applications of our work span the automotive and aerospace industries, extreme sensors, sustainable design, personalized design, and design automation.
MAJOR RESEARCH ACHIEVEMENTS
- Data-driven analysis and modeling for thin-walled structures: Developing reduced elements to enhance performance.
- Record-breaking performance for optomechanical sensors: Using Bayesian machine learning approaches to guide the design process.
- Material modeling with physics-informed machine learning: Utilizing Deep Material Network (DMN) for multi-scale and multi-physics mechanical design.
RESEARCH INTERESTS
- Building a co-design simulation model integrating multiple scales from materials to structures.
- Multi-modal/multi-fidelity design for materials and structures with extreme characteristics.
- Personalized design and design automation.