Case study · Semiconductors & electronics

Inline computer vision catches wafer-thinning defects in Intel assembly/test

Wafer thinning and film application were inspected offline on a sample after several steps, so tool problems such as a bent grinding arm could damage many wafers before detection.

Manufacturer
Intel
Use cases
1
Evidence
Manufacturer-reported
Year
2023

Manufacturer-reported  This result comes from the manufacturer's own publications, such as newsroom posts, earnings materials or engineering blogs. It has not been independently verified.

The challenge

Wafer thinning and film application were inspected offline on a sample after several steps, so tool problems such as a bent grinding arm could damage many wafers before detection.

The approach

Intelligent Wafer Vision Inspection (IWVI) uses high-resolution cameras and an edge ML model during grinding and film application, sounding an alarm or stopping the tool when defects appear. After a nine-month PoC in two facilities it is being deployed to all Intel assembly and test factories.

Reported improvements

Percent change as reported by the source; hover for the exact wording

Wafer-thinning issues detected earlier↑ 50%

1 use case in this implementation

  1. Visual quality inspection

    Edge machine-learning model analyzes multiple images per second during wafer thinning to detect micrometer-scale defects inline.

    • up to 50% of wafer-thinning issues can be detected earlier with inline inspection compared to offline inspection
    • Scrap avoidance, saving Intel up to USD 2 million each year

Outcomes as reported by the source. We do not adjust, combine or extrapolate reported figures.

Related case studies

Put AI to work

Find the AI opportunities hiding in your plant.

Genvo, our implementation partner, works with manufacturers to pick the right first project, connect the systems you already run and put AI agents and tools into daily use, with people approving what goes out.

Assessments and consultations are provided by Genvo. How our partnership works.