| About this Abstract |
| Meeting |
MS&T24: Materials Science & Technology
|
| Symposium
|
Grain Boundaries, Interfaces, and Surfaces: Fundamental Structure-Property-Performance Relationships
|
| Presentation Title |
Machine Learning-Aided Optimization of the Flash Sintering Process |
| Author(s) |
Alfredo Sanjuan Sanjuan, Edwin R García, Shiyu Zhou, Chao Shen, Bo Yang, Xinghang Zhang, Haiyan Wang |
| On-Site Speaker (Planned) |
Alfredo Sanjuan Sanjuan |
| Abstract Scope |
Modern sintering of ceramics is a result of a multiplicity of physical driving forces, including mechanical stresses, surface tension, and electrical energy, which contribute to the microstructural mechanisms for pore reduction, dislocation and grain boundary motion. Here, by starting from experimental densification curves, a physics-based, machine learning-aided formulation is presented to infer the equilibrium and kinetic parameters controlling the sintering process. Different modes and regimes of sintering behavior including classic, electric field assisted, flash, and ultra fast, are: 1) mapped out and analyzed by summarizing the parameters into practical driving force-controlled maps, and 2) demonstrated for materials such as Alumina, Titania and YSZ. |