AUTOMATIC VISUAL INSPECTION OF BUMP IN HARD DISK DRIVE COMPONENT USING NEURAL NETWORK AND IMAGE PROCESSING

摘要

This paper presents the progressive development of the automatic visual inspection system for hard disk drive manufacturing. The developed system is applied to inspect the flip-chip solder joints called 'bump' on the flexible PCB. In the designed system, conventional image processing is utilized to find the interesting features from the Flip-Chip image. Such features are adopted as the inputs of the trained artificial neural network (ANN). The designed ANN is used as the expert system for classifying the completeness of bump. To compare performance, the measured value of the bump's length from the proposed inspection system is investigated in comparison with the value from the destructive inspection using micro-electroscope. Experimental results show that our developed system is effectively used to automatically inspect the bump. Inspection time of the proposed system is much faster than that of the human inspection.