一种半导体设备参数整体变差自动识别方法及系统
By using an automatic identification method for overall variation in semiconductor equipment parameters, and leveraging the FDC system and big data processing engine, the shortcomings of identifying incremental variation in equipment parameters have been addressed. This has enabled automated and accurate risk warnings, thereby improving production yield.
Patent Information
- Application Number
- CN202610419236.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-01
- Publication Date
- 2026-07-17
- Estimated Expiration
- 2046-04-01
AI Technical Summary
In existing semiconductor manufacturing technologies, the gradual deterioration of equipment parameters cannot be effectively identified, and the specification limits lack dynamic optimization, resulting in delayed risk warnings. Furthermore, the low efficiency of processing massive amounts of data makes it difficult to achieve timely risk warnings.
An automatic identification method for overall variation of semiconductor equipment parameters is adopted. The FDC chart of equipment parameters is obtained through the FDC system. The baseline standard deviation is calculated based on historical datasets and outliers are filtered out. The current standard deviation is determined by the quartile method and drift coefficient. Combined with a big data processing engine, automated and accurate overall variation identification and specification limit optimization are achieved.
It enables automatic, efficient, and accurate identification of semiconductor equipment parameters, improves the timeliness and coverage of risk warnings, reduces missed detections, and enhances production yield assurance.
Smart Images
Figure CN121959384B_ABST
Abstract
Citation Information
Patent Citations
Power plant equipment operation state evaluation platform
CN116664018A
Gas generator set fault detection method and device, equipment and storage medium
CN120847609A