Huang Renbin, Zhan Daohua, Yang Xiuding, Zhou Bei, Tang Linjun, Cai Nian, Wang Han, Qiu Baojun
School of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, China.
School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China.
Micromachines (Basel). 2023 Jul 5;14(7):1375. doi: 10.3390/mi14071375.
In order to improve the production quality and qualification rate of chips, X-ray nondestructive imaging technology has been widely used in the detection of chip defects, which represents an important part of the quality inspection of products after packaging. However, the current traditional defect detection algorithm cannot meet the demands of high accuracy, fast speed, and real-time chip defect detection in industrial production. Therefore, this paper proposes a new multi-scale feature fusion module (ATSPPF) based on convolutional neural networks, which can more fully extract semantic information at different scales. In addition, based on this module, we design a deep learning model (ATNet) for detecting lead defects in chips. The experimental results show that at 8.2 giga floating point operations (GFLOPs) and 146 frames per second (FPS), mAP and mAP can achieve an average accuracy of 99.4% and 69.3%, respectively, while the detection speed is faster than the baseline yolov5s by nearly 50%.
为了提高芯片的生产质量和合格率，X射线无损成像技术已广泛应用于芯片缺陷检测，这是产品封装后质量检测的重要组成部分。然而，当前传统的缺陷检测算法无法满足工业生产中高精度、快速且实时的芯片缺陷检测需求。因此，本文提出了一种基于卷积神经网络的新型多尺度特征融合模块（ATSPPF），它能够更充分地提取不同尺度的语义信息。此外，基于该模块，我们设计了一种用于检测芯片引脚缺陷的深度学习模型（ATNet）。实验结果表明，在8.2千兆浮点运算（GFLOPs）和每秒146帧（FPS）的情况下，mAP和mAP分别可实现99.4%和69.3%的平均准确率，同时检测速度比基线yolov5s快近50%。
