Printed Circuit Board Defect Detection Based on Improved YOLOv5

Aiming at the problems of low efficiency and poor real-time performance in the printed circuit board (PCB) defect detection, a PCB defect detection method based on the improved YOLOv5 is proposed, which integrates the module of multiscale detection, attention mechanism and multi-branch. A shallow detection layer is added to detect smaller defect targets and fused with features of the deep network. An optimized anchor clustering method was used to obtain a more suitable size for the dataset. The Convolutional Block Attention Module (CBAM) is introduced to reweight and assign important feature channels to learn more valuable features. The re-parameterization convolution (RepConv) module is integrated to decouple the multi-branch training model into a single-way inference model by structural re-parameterization, which improves the model’s training performance and reduces inference time. The experimental results show that the detection accuracy of the proposed algorithm reaches 98.3% on the extended dataset, which is 3.4% higher than that of the original algorithm. At the same time, a real-time detection performance of 63 FPS is achieved, which satisfies the detection requirements of the PCB.

I. Introduction

With the rapid development of the electronic manufacturing industry, the PCB is widely used as the core component of electronic products. The increasing demand inevitably brings new challenges to manufacturing enterprises. In the actual production process, affected by equipment, environment, manual operation and other factors, many defects are produced on the surface of PCB, which will not only affect the performance of the PCB but also cause economic losses and personnel injuries [1]. Therefore, defect detection has become a crucial part of quality control in PCB manufacturing process.