News & Posts

My paper "Deep material network with cohesive layers: Multi-stage training and interfacial failure analysis" has just been …

This paper develops a physics-based machine learning model based on the deep material network (DMN) enriched by cohesive layers, which …

Research Topics

.js-id-Methods

Multiscale modeling of carbon fiber reinforced polymer composites.

Network-based machine-learning model with physics-based building blocks and interpretable fitting parameters.

Integration of microstructural reconstruction, mesh generation, finite elemnt analysis and RVE homogenization.

Viscoelasticity, hyperelasticity, large deformation

Analityical and semi-analytical models for fast predictions of material properties

Challenging multiscale and multiphysics problems at the intersection of computational physics, material science and data science.

Model reduction by grouping material points with similar responses.

Learn to learn and explore the possibilities of database interpolation and extrapolation.

Recent Publications

(2019). A data-driven multiscale theory for modeling damage and fracture of composite materials. International Workshop on Meshfree Methods for Partial Differential Equations.

Project URL