A team led by researchers at Nagoya University in Japan has succeeded in predicting crystal orientation by teaching artificial intelligence (AI) using optical photographs of polycrystalline materials. The results were published in APL Machine Learning.
Crystals are important components of many machines. Well-known materials used in industry contain polycrystalline components such as metal alloys, ceramics and semiconductors. Because polycrystals are made up of many crystals, they have a complex microstructure, and their properties vary greatly depending on the orientation of the crystal grains. This is especially important for silicon crystals used in solar cells, smartphones and computers.
Professor Noritaka Usami said, “To obtain polycrystalline materials that can be used effectively in industry, it is necessary to control and measure the crystal orientation distribution.” “However, this is hampered by the expensive equipment and outdated techniques required to measure large area samples.”
A team led by Professor Usami (he, he) of the Nagoya University Graduate School of Engineering and Professor Hiroaki Kudo (he, he) of the Graduate School of Informatics, in collaboration with RIKEN, applied a machine learning model to evaluate the photographs taken. bottom. The surface of the polycrystalline silicon material is irradiated from various directions. As a result, we found that AI succeeded in predicting the crystal orientation distribution.
“This measurement took about 1.5 hours to take the optical photos, train the machine learning model, and predict the direction, which is a significant speedup compared to about 14 hours with conventional technology.” said Usami. “It also makes it possible to measure large areas of matter that were not possible with conventional methods.”
Usami has high hopes that the team’s technology will be used in industry. “This is a technology that will revolutionize materials development,” Usami said. “This research is intended for all researchers and engineers who develop polycrystalline materials. It is possible to create a polycrystalline material orientation analysis system that packages a crystal orientation prediction model based on image data collection and machine learning. We expect many companies to participate.” Such equipment will be installed when working with polycrystalline materials. “
/ Open to the public. This material from the original organization/author may be of the nature of its time and has been edited for clarity, style and length. Mirage.News does not take any organizational positions or positions and all views, positions and conclusions expressed herein are those of the authors only. Read the full article here.
