<title>Inspection of ball grid array (BGA) solder joints using x-ray cross-sectional images</title>

Abstract

The ball grid array(BGA) chip is widely used in high density printed circuit board(PCB). However, inspection of defects in the solder joints is difficult by visual or a normal x-ray imaging method, because unlike conventional packages with guilwing type leads, solder joints of the BGA are located underneath its own package and ball type leads. Therefore, x-ray digital tomosynthesis(DT), which form a cross-sectional image of 3-D objects, is needed to image and inspect the solder joints of BGA. In this paper, we propose a series of algorithms for inspecting the solder joints of BGA by using x-ray crosssectional images that are acquired from the developed DT system. BGA solder joints are examined to check the alignment between the chip and pad on a PCB, bridge(electrically short), adequate solder volume. The volnme of the solder joint is represented by a gray level in the x-ray images : thus solderjoints can be examined by use ofthe gray-level profiles of each joint. To inspect and classify various defects, pattern classification method using a learning vector quantization(LVQ) neural network and a look up table(LUT) is proposed. The clusters into which a gray-level profile is classified are generated by the learning process ofthe network by using a number ofsampled gray-level profiles. A series ofthese developed algorithms for inspecting and classifying defects were tested on a number of BGA solder joints. The experimental results show that the proposed method yields satisfactory solutions for inspection based on x-ray cross-sectional images.

Detection of BGA solder defects from X-ray images using deep neural network

“…In this context, we observe that researchers have proposed series of image processing and pattern recognition algorithms for the computer-aided inspection and classification of solder joints in BGA X-ray images. In the literature, studies inspecting the conditions of solder joints generally categorize the BGA X-ray images into two or three broad classes [2][3][4][5][6][7][8][9]. In the majority of these studies, morphological image processing methods are used for the analyses, and results are given for a few images.…”

“…In the study of Roh et al [2] an X-ray digital tomosynthesis system was designed. Using X-ray images of BGA components obtained from this system; solder short-circuits, location errors of solder balls and solder volume level were determined.…”

Edge Extraction by an Exponential Function Considering X-ray Transmission Characteristics

“…There are some works for industrial application that overcome real time issues and difficulty in handling complex geometry (Roh et al 2001;Roh et al 1999;Koh et al 2001). Especially Koh, et al (2001) did work for the inspection of a Ball Grid Array on a PC board by adopting a hybrid neural network for image processing.…”

An Implementation of uniform and simultaneous ART for 3D volume reconstruction in x-ray imaging system

“…In x-ray system, the surface condition of an object, whether it is lambertian or specular, does not affect the inherent characteristics of its x-ray images. Due to these advantages, it is frequently used these days in industries to perform quality inspection of inner structures of electronic goods or mechanical parts [3][4][5] . Especially, in electronic parts inspection three dimensional x-ray imaging techniques are needed for the precise measurement or inspection of ball grid array(BGA) and chip-scale package(CSP) which are widely used in high-density PCB.…”

“…1. To inspect their quality precisely, for example, whether solder joints are well attached with adequate soldering quantity or whether there are void defects within them or not, an inspection method based on three dimensional images is needed [3][4][5][6][7] . There are several techniques to acquire three dimensional information using x-ray images.…”