Advancing PCB Quality Control : Harnessing YOLOv8 Deep Learning for Real-Time Fault Detection

Printed Circuit Boards (PCBs) are materials used to connect components to one another to form a working circuit.
\nPCBs play a crucial role in modern electronics by connecting various components. The trend of integrating more
\ncomponents onto PCBs is becoming increasingly common, which presents significant challenges for quality control
\nprocesses. Given the potential impact that even minute defects can have on signal traces, the surface inspection of
\nPCB remains pivotal in ensuring the overall system integrity. To address the limitations associated with manual
\ninspection, this research endeavors to automate the inspection process using the YOLOv8 deep learning algorithm
\nfor real-time fault detection in PCBs. Specifically, we explore the effectiveness of two variants of the YOLOv8
\narchitecture: YOLOv8 Small and YOLOv8 Nano. Through rigorous experimentation and evaluation of our dataset
\nwhich was acquired from Peking University’s Human-Robot Interaction Lab, we aim to assess the suitability of
\nthese models for improving fault detection accuracy within the PCB manufacturing process. Our results reveal
\nthe remarkable capabilities of YOLOv8 Small models in accurately identifying and classifying PCB faults. The
\nmodel achieved a precision of 98.7%, a recall of 99%, an accuracy of 98.6%, and an F1 score of 0.98. These findings
\nhighlight the potential of the YOLOv8 Small model to significantly improve the quality control processes in PCB
\nmanufacturing by providing a reliable and efficient solution for fault detection.