Application of computational intelligence techniques for optimization of solder volume in PCB assembly

摘要

Application of insufficient or excessive amounts of the solder paste during the solder paste printing process can result in circuit issues, such as an incomplete circuit when the paste applied is insufficient and a short circuit when the paste applied is excessive. The former is resulting from a solder open; the latter is resulting from the forming of a solder bridge. This study attempts to optimize solder volume in a printed circuit board assembly. Computational intelligence techniques, including neural network, genetic algorithm, particle swarm optimization, and simulated annealing, were used to address this problem. A real case study was presented to confirm the effectiveness of the computational intelligence techniques.