Substrate processing apparatus and information processing system
The substrate processing apparatus uses machine learning to predict defects in substrates by integrating detectors and a learned model, addressing the cost and time issues of traditional inspection methods.
TWI933936BActive Publication Date: 2026-08-01EBARA CORP
3 Cites 0 Cited by
Patent Information
- Application Number
- TW111120362
- Authority / Receiving Office
- TW · TW
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2021-06-15
- Filing Date
- 2022-06-01
- Publication Date
- 2026-08-01
- Estimated Expiration
- 2042-05-31
AI Technical Summary
Technical Problem
The challenge of evaluating substrate cleaning performance in a polishing apparatus is costly and time-consuming due to the need for defect inspection, leading to potential defects in uninspected substrates.
Method used
A substrate processing apparatus equipped with detectors that use a learned machine learning model to predict defects without a defect inspection device, incorporating features like dwell time, component positions, and processing recipe information to infer defect numbers, sizes, and locations.
Benefits of technology
Enables defect prediction in substrates without the need for costly defect inspection, allowing identification of defective products through machine learning-based inference.
✦ Generated by Eureka AI based on patent content.
Abstract
The substrate processing apparatus of the present invention comprises: at least one detector for detecting physical quantities of an object during the grinding and / or cleaning and / or drying of the substrate; a transformation unit for transforming the detection values detected by the aforementioned detector during grinding and / or cleaning and / or drying into feature quantities for each processing step of a learned machine learning model; and an inference unit for outputting a predicted value of at least one of the number of defects, defect size, and defect location in the substrate of the object by inputting object data including the aforementioned feature quantities into the learned machine learning model; the aforementioned learned machine learning model is learned using a learning dataset that includes feature quantities containing the detection values detected by the detector during grinding and / or cleaning on the production line of the object or on a production line of the same type as the production line of the object, as input data, and at least one of the number of defects, defect size, and defect location in the substrate as output data.
Need to check novelty before this filing date? Find Prior Art