Time: 2018-5-28 09：00-10：00

Venue: Room 201 Lecture Hall

abstract：Materials design is contingent on the availability of reliable linkages between the microstructure and its associated mechanical properties. This work investigates a surrogate model, which is derived from 3D image-based simulation for revealing the optimum microstructure of particles in materials. This new approach comprises the following steps: (1) generating a dataset using an ensemble of representative microstructures and obtaining their mechanical responses using established finite element simulations, (2) establishing a low-dimensional representation of microstructure microstructures, (3) establishing a relationship between the selected microstructure parameters and mechanical properties using support vector machine, and (4) Obtaining optimum parameters. The proposed methodology has good computational efficiency and accuracy.