About this Abstract |
| Meeting |
MS&T25: Materials Science & Technology
|
| Symposium
|
Materials Processing and Fundamental Understanding Based on Machine Learning and Data Informatics
|
| Presentation Title |
The Applications of Generative Adversarial Networks (GANs) on the Prediction of the Material’s Microstructure |
| Author(s) |
Ningxuan Wen, Rajendra K Bordia, Jianhua Tong, Dongsheng Li, Hai Xiao, Fei Peng |
| On-Site Speaker (Planned) |
Fei Peng |
| Abstract Scope |
Prediction processing-microstructure-property (PMP) link is critical for material processing, characterization, and discovery. We demonstrate GAN-based machine learning models that can accurately predict PMP relationships, specifically in the prediction of (1) the microstructure of alumina under arbitrary laser power, (2) the expected microstructure from the desired hardness, (3) real-time, in-situ microstructure during laser manufacturing, and (4) phases and element distributions of multi-phase materials. We demonstrate that experimentally-obtained data of processing parameters, microstructure, and properties were sufficient for training of large models that contain tens of millions of parameters. A pre-trained CNN showed that ML-predicted microstructure had less than 10% error from real ones, in projected hardness. To monitor the microstructure during laser sintering, we demonstrated GAN-based model that can instantaneously predict the ceramic’s microstructure at the laser spot, based on the laser spot brightness. |