A deep ensemble convolutional neural network (CNN) model to inspect printed circuit board (PCB) board dual in-line package (DIP) soldering defects with Hybrid-YOLOv2 (YOLOv2 as a foreground detector and ResNet-101 as a classifier) and Faster RCNN with ResNet-101 and Feature Pyramid Network (FPN) (FRRF) achieved a detection rate of 97.45% and a false alarm rate (FAR) of 20%–30% in the previous study [34] . However, applying the method to other production lines, environmental variations, such as lighting, orientations of the sample feeds, and mechanical deviations, led to the degradation in detection performance. This article proposes an effective self-adaption method that collects “exception data” like the samples with which the Artificial Intelligent (AI) model made mistakes from the automated optical inspection inference edge to the training server, retraining with exceptions on the server and deploying back to the edge. The proposed defect detection system has been verified with real tests that achieved a detection rate of 99.99% with an FAR 20%–30% and less than 15 s of inspection time on a resolution $7296 \times 6000$ PCB image. The proposed system has proven capable of shortening inspection and repair time for online operators, where a 33% efficiency boost from the three production lines of the collaborated factory has been reported [6] . The contribution of the proposed retraining mechanism is threefold: 1) because the retraining process directly learns from the exceptions, the model can quickly adapt to the characteristic of each production line, leading to a fast and reliable mass deployment; 2) the proposed retraining mechanism is a necessary self-service for conventional users as it incrementally improves the detection performance without professional guidance or fine-tuning; and 3) the semiautomatic exception data collection method helps to reduce the time-consuming manual labeling during the retraining process.

中文翻译：

---

基于深度集成自适应方法的工业PCB板DIP工艺缺陷自动检测系统

一个深度集成的卷积神经网络（CNN）模型，可使用Hybrid-YOLOv2（YOLOv2作为前景检测器，ResNet-101作为分类器）和Faster RCNN检查印刷电路板（PCB）板双列直插式封装（DIP）焊接缺陷在先前的研究中，使用ResNet-101和功能金字塔网络（FPN）（FRRF）的检测率达到97.45％，错误警报率（FAR）达到20％–30％ [34] 。但是，将该方法应用于其他生产线时，环境变化（例如光照，样品进料的方向和机械偏差）导致检测性能下降。本文提出了一种有效的自适应方法，该方法可以收集“异常数据”，例如人工智能（AI）模型从自动光学检测推理边缘向训练服务器犯错的样本，再对服务器上的异常进行重新训练，然后再部署回去。到边缘。所提议的缺陷检测系统已经过真实测试的验证，在分辨率为20％–30％且检测时间少于15 s的情况下，检测率为99.99％ $ 7296 /次6000 $ PCB图像。事实证明，该提议的系统能够缩短在线操作员的检查和维修时间，据报道，合作工厂的三条生产线可将效率提高33％[6] 。所提出的再培训机制的贡献有三方面：1）因为再培训过程直接从异常中学习，所以模型可以快速适应每条生产线的特性，从而实现快速可靠的大规模部署；2）所提出的再培训机制是常规用户的必要自助服务，因为它无需专业指导或微调即可逐步提高检测性能；3）半自动异常数据收集方法有助于减少重新培训过程中耗时的手动标记。