Use of synthetic photo-realistic images in semiconductor manufacturing devices
By training machine learning models with photorealistic synthetic images in semiconductor manufacturing equipment, the challenge of quickly identifying anomalies has been solved, enabling faster and more accurate anomaly detection and compensation, and improving the stability of the manufacturing process.
CN122162157APending Publication Date: 2026-06-05LAM RES CORP
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- LAM RES CORP
- Filing Date
- 2024-10-10
- Publication Date
- 2026-06-05
Smart Images
Figure CN122162157A_ABST
Abstract
According to some embodiments, methods, systems, and media for using synthetic images are presented. In some embodiments, a method involves obtaining a set of images related to an integrated circuit fabrication chamber, where the set of images includes at least a subset of synthetic images. Each synthetic image of the subset of synthetic images is a photo-realistic synthetic image. In some embodiments, at least a portion of the synthetic images presents an abnormal condition related to the fabrication chamber, and each image in the set of images presents at least one of: 1) a component of the fabrication chamber; 2) a process occurring in the fabrication chamber; or 3) a wafer property of a wafer being processed in the fabrication chamber. The method can also involve using the set of images to train a machine learning model, where the trained machine learning model can be used to predict the abnormal condition.
Need to check novelty before this filing date? Find Prior Art