| 林冬梅,樊煜杰,陈晓雷,杨富龙,李策.基于SOP芯片三维点云图像的引脚缺陷检测方法[J].电子测量与仪器学报,2025,39(8):42-53 |
| 基于SOP芯片三维点云图像的引脚缺陷检测方法 |
| Pin defect detection method based on 3D point cloud image of SOP chip |
| |
| DOI： |
| 中文关键词: 小外形封装芯片引脚 三维缺陷检测 点云处理 DCPP-PointNet |
| 英文关键词:small out-line package chip pins three-dimensional defect detection point cloud processing DCPP-PointNet |
| 基金项目:国家自然科学基金（62361038，62363025）、甘肃省集成电路制造材料创新联合体项目（23ZDGE001）、甘肃省科技计划（24JRRA181）、甘肃省教育厅高校教师创新基金（2023A 019）项目资助 |
|
|
| Author | Institution |
| Lin Dongmei | School of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China |
| Fan Yujie | School of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China |
| Chen Xiaolei | School of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China |
| Yang Fulong | School of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China |
| Li Ce | School of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China |
|
| 摘要点击次数: 773 |
| 全文下载次数: 685 |
| 中文摘要: |
| 针对目前小外形封装(SOP)芯片引脚的三维缺陷检测任务，现有的点云深度学习方法难以有效检测常见的引脚缺陷。为解决这一问题，
定义了一种有缺陷的芯片引脚点云(DCPP)图像，并创建了相应的DCPP数据集。同时提出了一种面向DCPP图像的DCPP-PointNet缺陷检测算法。该算法新增加的
局部-空间特征提取（LSFE）网络，可有效提高模型的旋转鲁棒性，使得模型在面对旋转的芯片点云数据时仍能保持良好的检测性能；其次设计全新的
倒残差多尺度卷积网络（iRMSC-Net）替换PointNet++中的特征编码器，通过加强对点云边缘局部信息的学习能力，从而实现对SOP芯片引脚常见缺陷的精确分类和定位；最后采用Focal损失函数解决了正负样本不平衡的问题，使得模型能够更加关注难以区分的缺陷样本，提高检测精度。在自建的DCPP数据集上进行的实验结果表明，DCPP-PointNet网络在总体准确率（OA）和平均交并比（mIoU)等评估指标上均优于现有的PointNet、PointNet++、DGCNN等经典点云分割模型，展现了高达98.9%的OA和93.7%的mIoU。消融实验进一步验证了DCPP-PointNet中各个改进模块的有效性，LSFE网络、iRMSC-Net特征编码器和Focal损失函数三者共同作用，对提高模型的检测精度和鲁棒性具有重要意义。 |
| 英文摘要: |
| For the three-dimensional defect detection task of SOP chip pins, existing point cloud deep learning methods struggle to effectively detect common pin defects. To address this issue, a DCPP image is defined and a corresponding DCPP dataset is created. A DCPP-PointNet defect detection algorithm is also proposed, specifically designed for DCPP images. This algorithm incorporates a LSEF network, which enhances the model’s rotational robustness and ensures good detection performance even with rotated point cloud data. Additionally, a new iRMSC-Net network is designed to replace the feature encoder in PointNet++, improving the model’s ability to learn local edge features of point clouds and enabling precise classification and location of common SOP chip pin defects. Focal loss function is employed to tackle the imbalance between positive and negative samples, allowing the model to focus more on hard-to-distinguish defect samples and thus improving detection accuracy. Experimental results on the self-built DCPP dataset show that the DCPP-PointNet network surpasses existing point cloud segmentation models such as PointNet, PointNet++, and DGCNN in terms of OA and mIoU. It achieved an OA of 98.9% and an mIoU of 93.7%. Ablation studies further confirm the effectiveness of the improvements in DCPP-PointNet, where the combined action of the LSFE network, iRMSC-Net feature encoder, and Focal loss function significantly enhances the model’s detection accuracy and robustness. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
