In-line defect detection through the introduction of AI-supported inspection systems in the automotive industry

Initial situation

An automotive supplier had quality problems with a product that could not be detected reliably enough
The quality defects were caused by small particles of around 150 µm, which were not detected by the current testing system
Visual inspection by the operating personnel was not possible due to the sheer volume of product and the required efficiency of the inspection process
Market share threatened to be lost due to damage to the company's image
A new inline inspection system was to be developed

0 ppm

Undiscovered errors achieved

0 million €

Cost savings realized through fewer product recalls

Facts

For the root cause analysis and development

Select an inline imaging inspection system and install it together with the supplier
Classify and index images
Train selected AI models and evaluate them in terms of sensitivity and specificity
Apply the UMS AI approach to focus on the best performing algorithms
Improve the inspection system in cooperation with the supplier and demonstrate its suitability

Improvement of assembly processes through optimized development in the automotive industry

Increasing the accuracy of quality inspections through artificial intelligence in the automotive industry

Increased efficiency in quality inspections through AI-supported image recognition in the automotive industry

All cases

Discover more references.