White text on a light gray background reads UMS+ in large letters, with AN EXPLEO COMPANY in smaller text below.

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

Initial situation

  • A German automotive company carried out the monitoring of weld seams with the help of a worker self-inspection system
  • The company was operating in a highly regulated market environment with strict quality assurance requirements
  • The lack of accuracy of the visual inspection system resulted in high rework rates and complaints from customers
  • The company therefore urgently needed to improve the accuracy of its inspection system to avert impending financial losses

Achievements

0
Reduced inspection time
99,5
Accuracy of the system achieved
Causes
Identified for lack of accuracy

Our approach

  • Introduce an imaging test procedure with AI-supported evaluation
    • Generate images of the (concealed) welds using computer tomography (CT)
    • Create reference training and test data sets according to the defects and specifications
    • Evaluate the performance of different systems according to the state of the art and select the best model
  • Compile and use high-quality training and test data sets with UMS know-how

Further cases

Automotive

Improvement of assembly processes through optimized development in the automotive industry

Automotive

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

Automotive

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

All cases

Discover more references.