Yu Shiwei, Pan Feng, Zhang Xiaoqiang, Zhou Linhua, Zhang Liang, Wang Jikui
CGN Digital Technology Co., Ltd., Shanghai, China.
PLoS One. 2025 Apr 18;20(4):e0320344. doi: 10.1371/journal.pone.0320344. eCollection 2025.
Aiming at the problems of low accuracy and large computation in the task of PCB defect detection. This paper proposes a lightweight PCB defect detection algorithm based on YOLO. To address the problem of large numbers of parameters and calculations, GhostNet are used in Backbone to keep the model lightweight. Second, the ordinary convolution of the neck network is improved by depthwise separable convolution, resulting in a reduction of redundant parameters within the neck network. Afterwards, the Swin-Transformer is integrated with the C3 module in the Neck to build the C3STR module, which aims to address the issue of cluttered background in defective images and the confusion caused by simple defect types. Finally, the PANet network structure is replaced with the bidirectional feature pyramid network (BIFPN) structure to enhance the fusion of multi-scale features in the network. The results indicated that when comparing our model with the original model, there was a 47.2% reduction in the model's parameter count, a 48.5% reduction in GFLOPs, a 42.4% reduction in Weight, a 2.0% reduction in FPS, and a 2.4% rise in mAP. The model is better suited for use on low-arithmetic platforms as a result.
针对印刷电路板（PCB）缺陷检测任务中准确率低和计算量大的问题，本文提出了一种基于YOLO的轻量级PCB缺陷检测算法。为了解决参数数量多和计算量大的问题，在主干网络中使用GhostNet以保持模型轻量级。其次，通过深度可分离卷积改进颈部网络的普通卷积，从而减少颈部网络内的冗余参数。之后，将Swin-Transformer与颈部的C3模块集成以构建C3STR模块，旨在解决缺陷图像中背景杂乱以及简单缺陷类型造成的混淆问题。最后，将PANet网络结构替换为双向特征金字塔网络（BIFPN）结构，以增强网络中多尺度特征的融合。结果表明，将我们的模型与原始模型进行比较时，模型的参数数量减少了47.2%，浮点运算次数（GFLOPs）减少了48.5%，权重减少了42.4%，每秒帧数（FPS）减少了2.0%，平均精度均值（mAP）提高了2.4%。因此，该模型更适合在低算力平台上使用。
