A Deep Regression Framework Toward Laboratory Accuracy in the Shop Floor of Microelectronics

Deep learning (DL) has certainly improved industrial inspection, while significant progress has also been achieved in metrology with impressive results reached through their combination. However, it is not easy to deploy metrology sensors in a factory, as they are expensive, and require special acquisition conditions. In this article, we propose a methodology to replace a high-end sensor with a low-cost one introducing a data-driven soft sensor (SS) model. Concretely, a residual architecture (R(2)esNet) is proposed for quality inspection, along with an error-correction scheme to lessen noise impact. Our method is validated in printed circuit board (PCB) manufacturing, through the identification of defects related to glue dispensing before the attachment of silicon dies. Finally, a detection system is developed to localize PCB regions of interest, thus offering flexibility during data acquisition. Our methodology is evaluated under operational conditions achieving promising results, whereas PCB inspection takes a fraction of the time needed by other methods.

Automated summary

Deep learning has made significant progress in industrial inspection and combining it with metrology has yielded impressive results. However, deploying metrology sensors in factories is challenging due to cost and special acquisition conditions. This article proposes a methodology that replaces a high-end sensor with a low-cost data-driven soft sensor model. It introduces a residual architecture (R(2)esNet) for quality inspection and an error-correction scheme to reduce noise impact. The methodology is evaluated in PCB manufacturing and achieves promising results, significantly reducing the inspection time compared to other methods.