Defects pattern recognition for flip chip solder joint quality inspection with laser ultrasound and interferometer

Author

Sheng Liu ; Ume, I.C.

Author_Institution

Sch. of Mech. Eng., Georgia Inst. of Technol., Atlanta, GA

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

1491

Lastpage

1496

Abstract

A defects pattern recognition system has been developed for the flip chip solder joint quality inspection by using laser ultrasound and interferometric techniques. This system extracts Error Ratio and dominant frequency as features from ultrasound waveforms. It also performs a cluster analysis of those feature vectors by applying probabilistic neural network classification algorithm. The system can automatically classify chips into different clusters, therefore can find differences between good and bad chips, as well as classifying the type of defect.

Keywords

feature extraction; flip-chip devices; inspection; light interferometry; neural nets; pattern classification; pattern clustering; quality control; ultrasonic applications; cluster analysis; defects pattern recognition; error ratio; feature vectors; flip chip; joint quality inspection; laser interferometer; laser ultrasound; probabilistic neural network classification; solder joint quality; ultrasound waveforms; Algorithm design and analysis; Classification algorithms; Clustering algorithms; Flip chip solder joints; Frequency; Inspection; Neural networks; Pattern recognition; Performance analysis; Ultrasonic imaging;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronic Components and Technology Conference, 2002. Proceedings. 52nd

ISSN

0569-5503

Print_ISBN

0-7803-7430-4

Type

conf

DOI

10.1109/ECTC.2002.1008303

Filename

1008303