Abstract
Based on comparable research studies, the reflow process has been iden- tified as the most critical process to ensure the quality of solder joints on printed circuit boards (PCBs) manufactured using surface mounting technology (SMT). An example of this is the ball grid array (BGA), which is a package that has one face partially covered by pins in a grid pattern that is connected to the pads on the PCB. It is important to note that the solder joints for BGAs are located at the bottom of the package, as opposed to passive components. Because the cover case of the BGA blocks the convection heat from the air, the BGA joints require a greater amount of parasite conduction heat from the boards and pack- age cover. During the manufacturing process, solder paste manufacturers provide specifications, along with temperature curves (i.e., thermal pro- files), to ensure the quality of the solder joints. In the context of the BGA thermal study, one of the significant challenges will be measuring the temperature under the package and predicting the temperature. Thus, a non-contact profile prediction model would help with predicting the BGA joint thermal profile. As part of this study, (1) a physics-informed artificial neural network (PINN) was proposed for temperature predic- tion for the BGA solder joints, and (2) an experiment was conducted 1 2 Thermal Profile Prediction and Recipe Optimization for BGAs to measure the solder joint temperature underneath the BGAs for con- firmation. The study also proposed (3) an optimization model based on mixed integer programming (MILP) to obtain the reflow recipe for the product that contains passive components and BGA packages, which have different heat capacities, by minimizing the difference of the ther- mal profiles. The prediction accuracy is higher than 96% in terms of the R2 fitness to the actual thermal profile. In the optimized recipe, there was a 50% reduction in the gap between the peak temperatures of the hottest (passive components) and the coldest (BGA center) joints.