IP Library Granted Patent US 12687838
Granted Patent B2
US 12687838 · App. 17/926,746 · Granted Jul 21, 2026

Substrate processing apparatus, substrate processing method, training data generating method, training method, training device, trained model generating method, and trained model

Inventors: Masaki Inaba (Kyoto, JP); Masayuki Otsuji (Kyoto, JP); Ayumi Higuchi (Kyoto, JP)
Assignee: SCREEN Holdings Co., Ltd.
G05B19/4155G06N20/00G05B2219/45031
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12687838
App. No.
17/926,746
Granted
Jul 21, 2026
Kind
B2
Abstract

A substrate processing apparatus includes a substrate holder, a processing liquid supply section, an input information acquiring section, a sublimation drying process condition information acquiring section, and a controller. The input information acquiring section acquires input information including at least one of substrate information and processing liquid information. The sublimation drying process condition information acquiring section acquires, from a trained model based on the input information, sublimation drying process condition information indicating a sublimation drying process condition on a processing target substrate. The controller controls the substrate holder and the processing liquid supply section to perform a sublimation drying process on the process target substrate based on the sublimation drying process condition acquired in the sublimation drying process condition information acquiring section.

Claims (11)

1 . A substrate processing method, comprising:

(a) rotating a process target substrate by a rotatable substrate holder while holding the process target substrate, the process target substrate being provided with a pattern of grooves and structures;

(b) acquiring input information including at least one of substrate information and processing liquid information, the substrate information being information on the process target substrate and indicating an attribute or a forming condition of the grooves and the structures, the processing liquid information indicating an attribute of a processing liquid containing a solvent and a sublimable substance that changes from a solid to a gas at 1 atm without going through a liquid state;

(c) acquiring sublimation drying process condition information from a trained model based on the input information, the sublimation drying process condition information indicating a sublimation drying process condition for the process target substrate;

(d) performing a sublimation drying process on the process target substrate according to the sublimation drying process condition of the sublimation drying process condition information, the sublimation drying process on the process target substrate including a solid formation to form a solid of the sublimable substance from the processing liquid on the process target substrate and a solid sublimation to cause the solid to sublime at 1 atm; and

(e) preparing the trained model before step (c) of acquiring the sublimation drying process condition information by performing machine learning on training data,

the training data including, in a same record, (A) the substrate information and the processing liquid information, (B) the sublimation drying process condition information, and (C) process result information, the substrate information being information on a learning target substrate provided with the pattern of grooves and structures and indicating the attribute or the forming condition of the grooves and structures, the processing liquid information indicating the attribute of the processing liquid used for performance of the sublimation drying process on the learning target substrate, the processing liquid containing the solvent and the sublimable substance that changes from the solid to the gas at 1 atm without going through a liquid state;

the sublimation drying process condition information indicating a condition by which the sublimation drying process has been performed on the learning target substrate; and

the process result information indicating a result of the sublimation drying process that has been performed on the learning target substrate, the sublimation drying process on the learning target substrate including a solid formation to form the solid of the sublimable substance from the processing liquid on the learning target substrate and the solid sublimation to cause the solid to sublime at 1 atm.

2 . The substrate processing method according to claim 1 , wherein step (d) includes supplying the processing liquid to the process target substrate held by the rotatable substrate holder, the processing liquid containing the solvent and the sublimable substance that changes from the solid to the gas at 1 atm without going through a liquid state.

3 . The substrate processing method according to claim 1 , wherein, in the step (d), the solid formed of the sublimable substance from the processing liquid on the process target substrate sublimes with the process target substrate held by the rotatable substrate holder.