[Case Study on Process Informatics] Optimization of GaN Crystal Processing

Processing accuracy that allows for the omission of post-processing, exceeding the target! A case that demonstrates the value of collaboration between AI and humans!

In power semiconductors like GaN, even the smallest roughness at the nanometer level (one-millionth of a millimeter) can affect performance, making crystal processing after creating a cylinder essential in traditional methods. To find appropriate experimental conditions, it is necessary to conduct experiments with at least two different conditions for each factor, meaning that for five factors, a minimum of 32 experiments is required. Based on those trends, we try dozens of experimental conditions to find the combination of factors that leads to the desired results. Therefore, traditional optimization methods centered around experiments required a significant number of trials. In contrast, the approach taken by Aicrystal, which learns from results, explores, and suggests conditions, was able to reduce the number of experiments to just 19. Moreover, this approach achieved a level of processing precision that allowed for the omission of later processes, and the benefits of not needing additional capital investment are significant. The conditions deemed appropriate here were combinations that had never been tried by engineers, showcasing the value of collaboration between AI and humans. *For more details, please refer to the PDF document or feel free to contact us.*

Other analysesAnalysis ServicesOther services