United StatesManufacturing2025 – ongoingCrown Holdings
Machine-learning diagnosis of can defects
Crown reported faster can-defect diagnosis after combining cameras with machine learning
Problem
Can defects created material waste and required production teams to diagnose their causes. Crown sought earlier detection and faster corrective action.
Approach
Crown deployed can-spoilage troubleshooting systems that combined camera inspection with machine learning. The systems classified defects and identified likely causes. They recommended troubleshooting actions, which Crown said reduced diagnosis time and waste while improving line efficiency.
Results
No published figures
Takeaway
The system extended inspection into troubleshooting by suggesting causes and corrective actions. Crown did not quantify the resulting reductions in diagnosis time or waste.
Categories
- Size
- Large enterprise
- Industry
- Manufacturing
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Computer visionPredictive analytics and ML
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
Crown described deployed camera and machine-learning systems for diagnosing can defects. It reported qualitative improvements in troubleshooting speed, material waste and line efficiency without project-specific figures.
Full details are in the original sources.