Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Improving X-ray inspection of printed circuit boards by integration of neural network classifiers

: Neubauer, C.; Hanke, R.F.


Institute of Electrical and Electronics Engineers -IEEE-:
Electronics manufacturing for the year 2000. Fifteenth IEEE/CHMT International Electronics Manufacturing Technology Symposium
New York, NY: IEEE, 1993
ISBN: 0-7803-1424-7
ISBN: 0-7803-1425-5
ISBN: 0-7803-1426-3
International Electronics Manufacturing Technology Symposium (IEMT) <15, 1993, Sata Clara/Calif.>
Conference Paper
Fraunhofer IIS A ( IIS) ()
Bildverarbeitung; defect recognition; Fehlererkennung; image processing; neural network; neuronales Netzwerk; Röntgenprüfung; x-ray inspection

In order to achieve six sigma quality for PCB-production x-ray inspection of solder joints is a powerful method to assure a high standard in fabrication. Current x-ray inspection systems require CAD files and intensive manual fine tuning. Neural network classifiers are able to adapt inspection tasks by presentation of typical training patterns. In this work neural networks are integrated into a x-ray inspection system both to increase defect recognition accuracy as well as to minimize manual adjustments of the system. The experiments carried out on different SMT device types (QFP, TAB, PLCC) prove the capability of neural network based approaches to correctly segment objects (solder joints etc.) and to detect defects (solder voids etc.).