Surface Inspection

Inspection of Vacuum Interrupters

Maddox AI enables the reliable and automated identification of surface defects such as soiling, metallic abrasion, impact marks, scratches, chipping on ceramics and many other defects.

Product

Vacuum interrupters

Industry

Energy Technology

Total savings / year​

60 - 80k €

Customer Request

Our customer produces over 1,000 switch tubes every day, which are inspected 100% manually by at least one specialist per shift. Due to the intricate defects (flaking, scratches, contamination) that have to be found on a complex component geometry with copper and ceramic surfaces, magnifying glasses and special lighting were used in the manual inspection. Despite these tools, the inspection accuracy varied considerably between employees per shift.


With the introduction of Maddox AI, inspection has been fully automated so that defective components are detected accurately and reliably. In particular, components are now inspected consistently across all shifts and according to clearly defined defect criteria.

Before

Previous Inspection System

After

With Maddox AI

Quality control was carried out completely manually, which was very time-consuming and costly.

The quality check is now fully automated, which has significantly reduced the manual effort and considerably increased the efficiency of the checks.

As the test results were not recorded digitally, there was no structured root cause analysis for faulty (NOK) parts.

Thanks to the digitalized inspection process, the reject rate in production has been reduced.

On average, only 20% of the rejected parts were really faulty. 80% of the parts could still be sold without any problems / with minor reworking.

Thanks to the increased precision of the Maddox AI inspection system, the pseudo reject rate has been reduced by around 75%, virtually eliminating re-inspections and avoiding unnecessary costs.

Before

Previous Inspection System

Quality control was carried out completely manually, which was very time-consuming and costly.

As the test results were not recorded digitally, there was no structured root cause analysis for faulty (NOK) parts.

On average, only 20% of the rejected parts were really faulty. 80% of the parts could still be sold without any problems / with minor reworking.

After

With Maddox AI

The quality check is now fully automated, which has significantly reduced the manual effort and considerably increased the efficiency of the checks.

Thanks to the digitalized inspection process, the reject rate in production has been reduced.

Thanks to the increased precision of the Maddox AI inspection system, the pseudo reject rate has been reduced by around 75%, virtually eliminating re-inspections and avoiding unnecessary costs.

100%

Digitized Analyses

75%

Less Pseudo Scrap

15 Month

Investment Payback Period

Would you like to learn more about our solution? – Test for free now!

Inspection of Injection Molded Parts

Surface defects such as improper cutting edges, cracks, scratches, and contamination can be reliably and automatically identified on injection-molded parts with the help of Maddox AI.

Inspection of Printed Circuit Boards

Thanks to Maddox AI’s device and software, incorrectly assembled components and other damages can be detected and tracked to a specific PCB.

Medical Hose Inspection

Maddox AI’s fully automated quality inspection reliably detects various defects and impurities such as foreign bodies, bubbles, water droplets, hair and more.
Maddox AI logo