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

Initial situation

An automotive supplier was experiencing quality issues with a product that could not be reliably inspected
The quality defects were caused by small particles of around 150 µm, which the current inspection system could not detect
Visual inspection by operating personnel was not possible due to the sheer volume of product and the required efficiency of the inspection process
The company’s market share was at risk due to potential damage to its reputation
A new in-line inspection system needed to be developed urgently

< 0 ppm

Undetected quality issues achieved

0 Mio. €

Savings from fewer product recalls realized

Facts

For cause analysis and development identified

Select and install an in-line imaging inspection system in collaboration with the supplier
Classify and index image data
Train selected AI models and evaluate their performance in terms of sensitivity and specificity
Apply the UMS AI approach to identify and focus on the best-performing algorithms
Improve the inspection system in collaboration with the supplier and demonstrate its adequacy and capability

Improving assembly processes through optimized development and Six Sigma in the automotive industry

Increased 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.