公开(公告)号：US11527404B2

公开(公告)日：2022-12-13

申请号：US16818491

申请日：2020-03-13

Applicant: TOKYO ELECTRON LIMITED

Inventor： Tetsuya Saitou ,  Takashi Kamio ,  Kazuyoshi Yamazaki ,  Naoshige Fushimi

IPC: H01L21/02 ,  H01L21/67

Abstract: An apparatus includes: a processing container; a stage provided inside the processing container to place a substrate thereon; a gas supply mechanism for supplying a processing gas into the processing container; and at least three ultraviolet light sources provided to irradiate the processing gas inside the processing container with ultraviolet rays. The ultraviolet light sources are provided to be offset from a rotation axis of the stage in a plan view, and are arranged in a light source arrangement direction with distances from the ultraviolet light sources to the rotation axis being different from one another. The ultraviolet light sources include first to third ultraviolet light source. The third ultraviolet light source is arranged such that distances L1, L2, and L3 from the first to third ultraviolet light sources, respectively, to the rotation axis in a plan view satisfies a relationship of L1

公开(公告)号：US11625518B2

公开(公告)日：2023-04-11

申请号：US17274739

申请日：2019-08-29

Applicant: Tokyo Electron Limited

Inventor： Kosuke Yamamoto ,  Motoshi Fukudome ,  Ken Itabashi ,  Naoshige Fushimi ,  Kazuyoshi Matsuzaki

IPC: G06F30/27 ,  G06F119/18 ,  G06N3/02

Abstract: A learning device for performing a machine learning based on a learning model using data input to an input layer, includes: a calculation part configured to calculate a predetermined number of features, in which simulation data as a result of simulating semiconductor manufacturing processes by setting environmental information inside a process vessel in which the semiconductor manufacturing processes are performed and using a predetermined component provided in the process vessel as a variable, and XY coordinates parallel to a plane of a wafer are associated with each other; and an input part configured to input the calculated predetermined number of features to the input layer.