Classification of Solder Joints via Automatic Mistake Reduction System for Improvement of AOI Inspection

Abstract

The precisions of Surface Mount Technology (SMT) process and equipment have become an important and challengeable issue due to the design requirements of miniaturization of components and high density placement on boards. The inspection equipment for the automated optical inspection (AOI) and solder paste inspection (SPI) machines in SMT line also have become essential tools. Nowadays, the AOI machine is widely utilized and installed as last station in SMT line to check the defects such as open, short, tombstone... etc. The high false detection rate of AOI will affect the production yield rate and overall equipment effectiveness. In order to solve this problem, the new system based on machine learning approach called automatic mistake reduction (AMR) system is proposed in this paper. The experimental results showed that the proposed method is not only more efficient, but also provides an accurate recognition rate in the SMT process.