US 12,031,230 B2
Quality prediction method, preparation method and system of high resistance gallium oxide based on deep learning and Czochralski method
Hongji Qi, Hangzhou (CN); Duanyang Chen, Hangzhou (CN); and Qinglin Sai, Hangzhou (CN)
Assigned to HANGZHOU FUJIA GALLIUM TECHNOLOGY CO. LTD., Hangzhou (CN)
Appl. No. 17/760,938
Filed by HANGZHOU FUJIA GALLIUM TECHNOLOGY CO. LTD., Zhejiang (CN)
PCT Filed Feb. 7, 2021, PCT No. PCT/CN2021/075853
§ 371(c)(1), (2) Date Mar. 16, 2022,
PCT Pub. No. WO2022/141758, PCT Pub. Date Jul. 7, 2022.
Claims priority of application No. 202011642101.0 (CN), filed on Dec. 31, 2020.
Prior Publication US 2023/0160096 A1, May 25, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. C30B 15/20 (2006.01); C30B 15/14 (2006.01); C30B 29/16 (2006.01); G16C 20/30 (2019.01); G16C 20/70 (2019.01)
CPC C30B 15/20 (2013.01) [C30B 15/14 (2013.01); C30B 29/16 (2013.01); G16C 20/30 (2019.02); G16C 20/70 (2019.02)] 10 Claims
OG exemplary drawing
 
1. A quality prediction and preparation method of high resistance gallium oxide based on deep learning and Czochralski method, comprising:
preparing a seed crystal in a crucible by the Czochralski method;
determining preparation data of a high resistance gallium oxide single crystal prepared by the Czochralski method, the preparation data comprising seed crystal data measured from the seed crystal, an environmental data, and a control data, and the environmental data comprises a doping element concentration and a doping element type;
preprocessing the preparation data to obtain a preprocessed preparation data and training data;
training a neural network model using the training data;
inputting the preprocessed preparation data into the trained neural network model;
determining, by the trained neural network model, a targeted quality data corresponding to the high resistance gallium oxide single crystal through the trained neural network model, and the targeted quality data comprises a predicted resistivity; and
preparing a targeted high resistance gallium oxide crystal according to the targeted quality data.