Dongfeng Motor
M-Hero AI paint-defect inspection and robotic sanding
Dongfeng deployed AI paint inspection and sanding with reported defect-recognition accuracy above 95%
Problem
Reflective vehicle paint made small defects difficult to identify. Sanding curved surfaces also depended on workers' experience.
Approach
M-Hero and Huazhong University of Science and Technology began a manufacturing partnership in March 2026. Their production paint-shop system combined deep-learning vision with constant-force sanding and automatic abrasive replacement. It connected defect detection and positioning to sanding and traceability.
Results
Takeaway
The system linked visual inspection directly to corrective work, although the disclosed accuracy came from the project team.
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
Dongfeng published a Wuhan broadcaster's account of robots deployed at M-Hero. It confirmed production use of deep-learning paint inspection and robotic sanding, with performance figures attributed to university project personnel.
Full details are in the original sources.