Printed circuit boards (PCBs) are a common structure in electrical circuit systems. During the production process, PCBs may encounter issues such as short circuits, open circuits, spikes, and missing holes, which can severely affect the functionality of the circuit. However, existing PCB defect detection methods suffer from low detection accuracy and slow detection speed. Considering the requirements for accuracy and real-time detection in PCB factories, this paper introduces a rapid PCB defect detection method based on FPGA and YOLOx Plus algorithm. The core detection algorithm of this paper is improved on the basis of YOLOx. In this paper, the network structure of YOLOx defect detection algorithm is first improved, introducing three network modules: weak data enhancement, parameter free attention mechanism SimAM, and FPN+PAN composite feature enhancement, and naming it YOLOx Plus.Then, by quantizing network parameters and designing an FPGA accelerator, the algorithm is accelerated to achieve accurate and rapid detection. In the experiment, the YOLOx-Plus algorithm was deployed on the FPGA and verified, the average detection accuracy of YOLOx-Plus is 93.2%, the network loss is reduced by 1.036, the model size is compressed by 64%, detection speed is improved by 68.1%, and the FPS reaches 72.6. The experimental results show that the proposed PCB defect detection method based on YOLOx-Plus and FPGA can efficiently detect typical defects in PCB boards, overcome the limitations of existing methods, and have a wide range of practical applications.
INDEX TERMS PCB, Defect detection, FPGA, YOLOx-PlusComputer vision technology encompasses knowledge in mathematics, computer science, electronics, and other fields.