Xu Youzhi, Wu Hao, Liu Yulong, Liu Xiaoming
School of Mechanical Engineering, Anhui University of Technology, Ma'anshan 243002, China.
Micromachines (Basel). 2025 Feb 26;16(3):261. doi: 10.3390/mi16030261.
Soldering of printed circuit board (PCB)-based surface-mounted assemblies is a critical process, and to enhance the accuracy of detecting their multi-targeted soldering defects, we propose an automated sample generation method that combines ControlNet and a Stable Diffusion Model. This method can expand the dataset by quickly obtaining sample images with high quality containing both defects and normal detection targets. Meanwhile, we propose the Cascade Mask R-CNN model with ConvNeXt as the backbone, which performs well in dealing with multi-target defect detection tasks. Unlike previous detection methods that can only detect a single component, it can detect all components in the region. The results of the experiment demonstrate that the detection accuracy of our proposed approach is significantly enhanced over the previous convolutional neural network model, with an increase of more than 10.5% in the mean accuracy precision (mAP) and 9.5% in the average recall (AR).
基于印刷电路板（PCB）的表面贴装组件的焊接是一个关键过程，为提高检测其多目标焊接缺陷的准确性，我们提出了一种结合ControlNet和稳定扩散模型的自动样本生成方法。该方法可以通过快速获取包含缺陷和正常检测目标的高质量样本图像来扩展数据集。同时，我们提出了以ConvNeXt为骨干的级联掩码R-CNN模型，该模型在处理多目标缺陷检测任务方面表现出色。与以往只能检测单个组件的检测方法不同，它可以检测区域内的所有组件。实验结果表明，我们提出的方法的检测精度比以前的卷积神经网络模型有显著提高，平均精度均值（mAP）提高了10.5%以上，平均召回率（AR）提高了9.5%。
