Solder joints inspection using neural network and fuzzy rule-based classification

In this paper, we described an approach ,to automation of visual inspection of solder joint defects of SMC(suface mounted components) on PCBs (Printed Circuit Board) by using neural network and fizzy rule-based classification method. Inherent&, suface of the solder joints is curved, tiny and specular reflective; it induces a difiiccul~ of taking good image of the solder joints. And the shape of the solder joints tends to greatly vary with soldetring condition and the shapes are not identical each other, even though solder joints belong to a set of the same soldering quality, This problem makes it dificult to classi5 the solder joints according to their qualities. Neural network and fuzzy rulebased classification method is proposed to cjyiciently make human-like classification criteria of the solder joint shapes. The peformance of the proposed approach is tested on numerous samples of commercial computer PCB board and compared with the human inspector per$ormance.