TaiwanManufacturing2019 – ongoingUnimicron
Deep-learning inspection of printed circuit boards
Unimicron said AI inspection reduced the share of products needing manual reinspection to 30%
Problem
Unimicron's optical inspection equipment produced results affected by differences in product color and height. Workers had to recheck its findings, and fatigue could cause costly mistakes.
Approach
Unimicron combined deep learning with its existing optical inspection equipment on production lines. General manager Lan Ting said all products previously required manual reinspection, compared with 30% after deployment.
Results
Takeaway
The reported improvement concerned the amount of manual reinspection. Unimicron did not disclose a corresponding defect-escape rate.
Categories
- Size
- Large enterprise
- Industry
- Manufacturing
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Computer vision
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
iThome reported Unimicron's general manager describing deployed deep-learning inspection. He said manual reinspection fell from all products to 30%, which he characterized as a 70% efficiency improvement.
Full details are in the original sources.