South KoreaManufacturing2022 – ongoingSK hynix
Gauss Labs machine learning for wafer-quality prediction
SK hynix reduced process variability by 29% with wafer-quality prediction, according to Gauss Labs
Problem
Physical metrology took tens of minutes per wafer, so SK hynix inspected only a small share of production. That limited the information available to detect process problems.
Approach
SK hynix put Gauss Labs AI into semiconductor processes at the end of 2022. Machine learning analyzed equipment history and sensor readings to predict wafer quality in real time. The predictions supported process monitoring and metrology decisions.
Results
Takeaway
Predictions extended monitoring beyond physically inspected wafers. The reported variability reduction came from the supplier's CEO.
Categories
- Size
- Large enterprise
- Industry
- Manufacturing
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Vendor solution
- Evidence
- Vendor case study
Sources
Source summaries
An interview with Gauss Labs CEO Younghan Kim described production use at SK hynix since late 2022. It reported a 29% reduction in process variability after adoption.
Full details are in the original sources.