About this Abstract |
| Meeting |
MS&T25: Materials Science & Technology
|
| Symposium
|
Enhancing the Accessibility of Machine Learning-Enabled Experiments
|
| Presentation Title |
High-throughput, Ultra-fast Laser Sintering of Ceramics and Machine-learning Based Prediction on Processing-Microstructure-Property Relationships |
| Author(s) |
Ningxuan Wen, Jianhua Tong, Rajendra K Bordia, Dongsheng Li, Hai Xiao, Fei Peng |
| On-Site Speaker (Planned) |
Fei Peng |
| Abstract Scope |
We report high-throughput, ultra-fast laser sintering of alumina micro-arrays and characterization of microstructure and hardness, as a fast exploration of laser processing parameters, microstructure, and property. These experimental data were used to train generative adversarial networks (GAN)-based machine-learning (ML) models. Accurate ML predictions were demonstrated for the processing-microstructure-property relationship, specifically in (1) prediction of the microstructure of alumina under arbitrary laser power, and (2) prediction of the expected microstructure from the desired hardness. A pre-trained CNN was developed and 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 an ML model that can instantaneously predict the ceramic’s microstructure at the laser spot, based on the laser spot brightness. The ML model can generate more than 10 predictions per second, and the error in average grain size was less than 5% from the experimental observations. |