IC solder joint inspection based on the Gaussian mixture model. Issue 4 (5th September 2016)

• Record Type: Journal Article
• Authors: Cai, Nian; Ye, Qian; Liu, Gen; Wang, Han; Yang, Zhijing
• Is Part Of: Soldering & surface mount technology. Volume 28:Issue 4(2016)
• Page Start: 207
• Page End: 214
• Publication Date: 2016-09-05
• Subjects: Statistical modelling -- Defect inspection -- Gaussian mixture model -- IC solder joint -- AOI; Brazing -- Periodicals; Solder and soldering -- Periodicals; 671.5605
• DOI: 10.1108/SSMT-03-2016-0005
• Languages: English
• ISSNs: 0954-0911

Abstract

Abstract : Purpose: This paper aims to inspect solder joint defects of integrated circuit (IC) components on printed circuit boards. Here, an IC solder joint inspection algorithm is developed based on a Gaussian mixture model (GMM). Design/methodology/approach: First, the authors train a GMM using numerous qualified IC solder joints. Then, the authors compare the IC solder joint images with the trained model to inspect the potential defects. Finally, the authors introduce a frequency map and define a metric termed as normalized defect degree to evaluate qualities of the tested IC solder joints. Findings: Experimental results indicate that the proposed method is superior to the state-of-the-art methods on IC solder joint inspection. Originality/value: The approach is a promising method for IC solder joint inspection, which is quite different from the traditional classifier-based methods.