| About this Abstract |
| Meeting |
MS&T21: Materials Science & Technology
|
| Symposium
|
Manufacturing and Processing of Advanced Ceramic Materials
|
| Presentation Title |
Ultra-fast Laser Sintering of Alumina and the Microstructure Prediction Based on Machine Learning |
| Author(s) |
Xiao Geng, Jianan Tang, Dongsheng Li, Yunfeng Shi, Rajendra Kumar Bordia, Jianhua Tong, Hai Xiao, Fei Peng |
| On-Site Speaker (Planned) |
Fei Peng |
| Abstract Scope |
We report an ultra–fast sintering phenomenon of alumina under scanning laser irradiation, and a machine learning approach to predict the microstructure of such alumina. Using CO2 laser irradiation, we found that micrometer–sized alumina powder can be sintered close to full density within a few tens of seconds. The microstructure and sintering master curve of laser–sintered alumina were different from those of the furnace–sintered alumina. Since the microstructure of laser-sintered alumina is significantly different from the furnace-sintered ones, to predict alumina’s microstructure under laser sintering, we developed an elegant machine learning algorithm to predict the microstructure under arbitrary laser power. We name this algorithm, regression-based conditional generative adversarial networks (GANs) with Wasserstein loss function and gradient penalty (RCWGAN-GP). The RCWGAN-GP realistically regenerates the SEM micrographs under the trained laser powers. Further, it also accurately predicts the alumina’s microstructure under unexplored laser power. |