Companies are under enormous pressure not only to reliably deliver products of impeccable quality, but also to reduce their operating costs at the same time. Digital solutions are needed in production to overcome product anomalies and reduce reject rates. The answer: Artificial intelligence in combination with computer vision and linking quality data with production data.
However, the requirements are high: In order to meet the strict quality assurance standards of the automotive industry, even complex component geometries must be inspected at high process speeds - and with maximum precision and process reliability. Variations in detection, insufficient traceability to individual serial numbers or batches and challenges caused by changing environmental conditions can lead to costly errors, production downtime and complaints.
VIVALDI Digital Solutions GmbH has developed an exemplary, innovative solution for AI quality inspection in real time. In addition to an edge server with an Intel processor, intelligent image processing plays a key role in the so-called SensorBox. Designed for an automotive supplier and its production site in the Czech Republic, up to 70 USB3 uEye+ XC autofocus cameras from IDS Imaging Development Systems perform automatic visual inspection for surface inspection in several inspection cells.
"The IDS cameras integrated into the test cells capture high-resolution images of the surface of aluminium components from German OEMs, in this case an electric motor," says Uwe Siegwart, Managing Director at Vivaldi, explaining the camera's task. The captured images are pre-processed to optimise factors such as exposure, white balance and colour correction. The AI recognises various surface defects such as scratches, pores or dirt. "There are strict requirements at the plant in the Czech Republic. According to the defect catalogue, defects from 0.2 millimetres must be reliably detected. The test time per component must not exceed 36 seconds," says Uwe Siegwart, explaining the stringent guidelines. Up to 2,400 electric motor housings per day are tested 100 per cent automatically with the successfully implemented system.
Read the full article at IDS-imaging.com.
