波纹度预测装置、波纹度预测方法、被研磨物的加工方法及程序
By using a waviness prediction device and a prediction model to predict the waviness during the semiconductor wafer grinding process, the problem of not being able to detect waviness anomalies in a timely manner in the existing technology is solved, thereby improving the yield and production efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- RESONAC CORP
- Filing Date
- 2022-12-20
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies cannot detect and predict waviness anomalies during semiconductor wafer grinding in a timely manner, resulting in reduced yield. Furthermore, the long waviness measurement time makes it difficult to detect and recover defective products in large-scale production.
A waviness prediction device is used to receive waviness data and feature quantities, and use a prediction model to predict waviness, including the acquisition and learning of feature quantities such as the number of grinding pads and the torque of the sun gear, to achieve waviness prediction and threshold judgment, and output adjustments to cope with processing conditions.
It enables early prediction of waviness anomalies, improves yield, avoids large-scale substrate rejection due to waviness anomalies, and improves production efficiency and product quality.
Smart Images
Figure CN118450966B_ABST