Optimization of Brake Hose inspection
Surface Inspection

Kundenanforderung
Our customer produces over 70,000 meters of brake hoses every day, which were inspected both by an automated vision system and manually by employees. The existing inspection system often detected defects that were not actually defects, such as slight surface defects or color deviations. This led to a pseudo reject rate of around 5%. In addition, there were several customer complaints, which led to cost-intensive manual re-sorting actions.
To significantly reduce the pseudo reject rate and slippage, the Maddox AI inspection system combines the existing camera hardware with the Maddox AI software. Common defect types that are detected include surface defects such as scratches, cuts and other damage from previous production steps.
The quality of the brake hoses was previously monitored by an automated vision system and manual checks in three shifts, with one to two employees per shift.
Thanks to the integration of the Maddox AI system, quality inspection is fully automated, eliminating the need for manual inspectors. This enables more efficient and precise inspection around the clock.
On average, around 10% of the parts produced were classified as faulty, with half of the parts declared as faulty being pseudo rejects.
Thanks to the increased precision of the Maddox AI inspection system, the pseudo reject rate has been reduced by around 85%, virtually eliminating re-inspections and avoiding unnecessary costs.
Due to the inadequate accuracy of the system, weekly manual re-sorting operations were required, during which the parts had to be checked and re-checked.
Maddox AI has completely eliminated the need for manual re-sorting, as the system accurately and reliably distinguishes between good and faulty parts.
Sounds like what you need?
Do you have questions about this solution or your very specific application?
Our experts will be happy to advise you!
More Case Studies
Browse through some of our selected case studies. If you have any questions about individual examples or your specific use case, please feel free to contact us at any time!
Pharmaceutical and Medical
- All
- Automotive
- Consumer Goods
- Electronical
- Energy Technology
- Infrastructure
- Logistics
- Metal
- Pharmaceutical and Medical
- Plastic
Component Detection
- All
- Code Recognition
- Component Detection
- Positioning Errors
- Surface Inspection
Cardboard
- All
- Cardboard
- Ceramics
- Copper
- Metal
- Paper
- Plastic
- Rubber
- Steel



