2020年第81回応用物理学会秋季学術講演会

講演情報

一般セッション(口頭講演)

15 結晶工学 » 15.6 IV族系化合物(SiC)

[10p-Z23-1~16] 15.6 IV族系化合物(SiC)

2020年9月10日(木) 13:15 〜 18:00 Z23

川西 咲子(東北大)、野口 宗隆(三菱電機)、俵 武志(富士電機)

13:15 〜 13:30

[10p-Z23-1] Solution growth of 150 mm SiC under the guidance of machine learning

Wancheng YU1、Can ZHU1、Yosuke TSUNOOKA2、Wei HUANG2、Yifan DANG2、Shunta HARADA1,2、Miho TAGAWA1,2、Toru UJIHARA1,2,3 (1.IMaSS, Nagoya Univ.、2.Nagoya Univ.、3.GaN-OIL, AIST)

キーワード:Machine learning, Solution growth, SiC

In this paper, 150 mm (6-inch) SiC crystals was fabricated by TSSG technique with the guidance of machine learning. The machine learning technique was adopted to find out the optimal configuration from all possible conditions for crystal growth. By applying the optimal results given by the machine learning, 150 mm 4H-SiC crystal was grown in reality by top-seed solution growth method.Commercial 150 mm 4H-SiC substrates with 4 ° off [0001]-oriented were used as seed crystals.The SiC samples shows uniform step flow surface morphology.Therefore, the machine learning technique represents an innovative and attractive strategy in the development of crystal growth.