[9p-N405-1~18] 11.2 Thin and thick superconducting films, coated conductors and film crystal growth

4:15 PM - 4:30 PM JST(7:15 AM - 7:30 AM UTC)Presentation by Applicant for JSAP Young Scientists Presentation Award

[9p-N405-11] RGB Analysis of plume images in the PLD method

〇(M2)Tatsuma Hachiya¹, Nakao Shoya¹, Horio Keiichi^1,5, Ichino Yusuke^3,5, Ichinose Ataru^4,5, Horide Tomoya^2,5, Matsumoto Kaname^2,5, Yoshida Yutaka^2,5 (1.Kyushu Inst. of Technol., 2.Nagoya Univ., 3.Aichi Inst. of Technol., 4.CRIEPI, 5.JST-CREST)

Keywords:

Machine Learning,Plume,Principal Component Analysis

We aim to improve the reproducibility of thin film deposition in the PLD method and to stabilize the process. In this research , we consider the relationship between the color of the plume generated on the target and the materials and process parameters. Nine types of target materials were prepared, including those with different mixing ratios. The oxygen partial pressure and laser power were varied in three different ways for each parameter. Principal component analysis was performed on the plume for a total of 81 conditions, using the RGB intensity of 45 pixels from the center to the right and upward as the feature values.