| 陈晓雷,李正成,沈星阳,马平川,杨富龙.基于CNN-Transformer的多级特征融合晶圆缺陷分类网络[J].电子测量与仪器学报,2026,40(5):50-59 |
| 基于CNN-Transformer的多级特征融合晶圆缺陷分类网络 |
| Multi-level feature fusion wafer defect classification networkbased on CNN-transformer |
| |
| DOI： |
| 中文关键词: 晶圆缺陷分类 单类型缺陷 特征融合 |
| 英文关键词:wafer defect classification single-type defects feature fusion |
| 基金项目:甘肃省科技计划(24JRRA179)、甘肃省科技重大专项(23ZDGE001)、甘肃省联合科研基金(24JRRA829)项目资助 |
|
|
| Author | Institution |
| Chen Xiaolei | School of Microelectronics Industry-education Integration, Lanzhou University of Technology, Lanzhou 730000, China |
| Li Zhengcheng | School of Microelectronics Industry-education Integration, Lanzhou University of Technology, Lanzhou 730000, China |
| Shen Xingyang | School of Microelectronics Industry-education Integration, Lanzhou University of Technology, Lanzhou 730000, China |
| Ma Pingchuan | School of Microelectronics Industry-education Integration, Lanzhou University of Technology, Lanzhou 730000, China |
| Yang Fulong | School of Microelectronics Industry-education Integration, Lanzhou University of Technology, Lanzhou 730000, China |
|
| 摘要点击次数: 275 |
| 全文下载次数: 144 |
| 中文摘要: |
| 晶圆缺陷分类是芯片制造过程中至关重要的一环，准确分类各种类型的缺陷模式对快速定位芯片制造问题并加以修复具有重要意义。针对晶圆缺陷分类中存在的多尺度特征表征不足和跨层次信息融合效率低等问题，提出了基于卷积神经网络（CNN）结合Transformer的多级特征融合晶圆缺陷分类网络（CNN-Transformer multi-level feature fusion network, CTM-Net）。该网络采用双分支并行结构,CNN分支负责提取局部形态和细微缺陷特征，Transformer分支利用自注意力机制建模全局上下文关系以获取全局结构特征，在此基础上，CTM-Net通过构建多级特征交互模块，实现跨尺度、跨层次信息的自适应融合与增强，从而有效弥补单一分支在特征表达上的不足，提升模型的判别能力。CTM-Net在公开WM-811K数据集上的分类准确度达到99.31%，在整体分类性能上优于当前主流的5种代表性先进晶圆缺陷分类方法，尤其在Edge-Loc、Edge-Ring、Loc等关键缺陷类别上表现出了更高的识别精度与稳定性。这一结果证明了CNN和Transformer多级融合方法在处理晶圆缺陷分类任务中的有效性和优势。 |
| 英文摘要: |
| Wafer defect classification is a critical task in the chip manufacturing process, as accurately identifying various types of defect patterns is essential for promptly locating and resolving manufacturing issues. To overcome the limitations of insufficient multi-scale feature representation and low efficiency in cross-level information fusion, this paper proposes a novel multi-level feature fusion network based on convolutional neural networks (CNN) and Transformers, named CTM-Net. The network adopts a dual-branch parallel architecture: the CNN branch focuses on extracting local morphological structures and fine-grained defect details, while the Transformer branch employs self-attention mechanisms to capture global contextual dependencies and structural information. Based on these complementary representations, a multi-level feature interaction module is further designed to adaptively integrate and enhance cross-scale features, effectively compensating for the limitations of single-branch representations and improving the model’s discriminative capability. Experiments conducted on the publicly available WM-811K dataset show that CTM-Net achieves an accuracy of 99.31%, outperforming five representative state-of-the-art wafer defect classification approaches. Notably, the proposed model demonstrates superior recognition accuracy and stability in critical defect categories such as Edge-Loc, Edge-Ring, and Loc, highlighting the effectiveness and advantages of combining CNN and Transformer architectures for multi-level feature fusion in wafer defect classification tasks. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
