United KingdomManufacturing2021 – ongoingGKN Aerospace
Robotic AI inspection of complex metallic parts
GKN Aerospace built a robotic inspection cell after tests detected more than 95% of defects
Problem
Complex metal surfaces made small defects difficult to inspect consistently. Curved geometry complicated lighting and camera focus.
Approach
GKN Aerospace worked with university researchers on an ARM Institute-funded inspection system. Robots collected images under controlled lighting, and deep-learning methods assessed surface defects. GKN built the resulting inspection cell in a factory.
Results
Takeaway
The project reported detection and inspection-speed results. Factory-wide financial returns remained projections.
Categories
- Size
- Large enterprise
- Industry
- Manufacturing
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Computer visionRobotics and automation
- Adoption
- Partner co-development
- Evidence
- Company's own claim
Sources
Source summaries
The project funder reported detection above 95% and inspection at approximately one minute per part. It confirmed that GKN built a factory cell; the stated return on investment was expected rather than realized.
Full details are in the original sources.
