An Artificial Intelligence-Based Pick-and-Place Process Control for Quality Enhancement in Surface Mount Technology

This research proposes a novel AI-based framework that identifies the optimal placement position based on the solder paste offset's information to minimize post-reflow misalignment of the mini-scale passive components in the pick-and-place (P & P) process. Inevitably, some depositions of solder paste are misaligned with existing technology. With the miniaturization trend in electronics and increased use of lead-free solder, the solder's misalignment has caused component misalignment, especially, in the smaller size cases. Therefore, a novel placement strategy is desired to increase the first pass yield. We propose a mounter optimization model (MOM) to optimize the positional placement parameters by predicting the components' positions after the reflow process. Our framework also adapts the placement positions while updating the model's parameters along with the board-to-board manufacturing process. To the best of our knowledge, it is the first artificial intelligence-based closed-loop system to accommodate various solder paste printing locations based on inspection information. Various solder paste positions with different volumes are considered experimental study. As a result, our MOM shows the effectiveness of reducing the post-reflow misalignment while minimizing its deviation compared to the conventional placement strategy. Indeed, the proposed framework provides the solution to meet the needs of the electronics manufacturing evolution toward Industry 4.0, which is characterized by miniaturization, high-density, and lead-free assembly.