| 杜先君,丁家俊,董明月.拓扑数据分析在晶圆图缺陷模式分类中的高效应用[J].电子测量与仪器学报,2025,39(10):185-196 |
| 拓扑数据分析在晶圆图缺陷模式分类中的高效应用 |
| Efficient application of topological data analysis in wafer mapdefect pattern classification |
| |
| DOI： |
| 中文关键词: 晶圆图缺陷模式分类 拓扑数据分析 持久同调 Alpha复形 支持向量机 半导体制造 |
| 英文关键词:wafer map defect pattern classification topological data analysis (TDA) persistent homology Alpha complex support vector machine (SVM) semiconductor manufacturing |
| 基金项目:国家自然科学基金(62241307)、兰州市科技支计划项目(2024-3-47)资助 |
|
|
| Author | Institution |
| Du Xianjun | 1.School of Microelectronics Industry-education Integration, Lanzhou University of Technology, Lanzhou 730050, China;
2.School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou 730050, China |
| Ding Jiajun | School of Microelectronics Industry-education Integration, Lanzhou University of Technology, Lanzhou 730050, China |
| Dong Mingyue | School of Microelectronics Industry-education Integration, Lanzhou University of Technology, Lanzhou 730050, China |
|
| 摘要点击次数: 703 |
| 全文下载次数: 492 |
| 中文摘要: |
| 晶圆图的缺陷模式分类是半导体生产制造过程中的重要环节,对提高产品良品率与生产效率有着重要意义。针对现有深度学习晶圆图缺陷模式分类方法解释性差和资源消耗高等问题,改进了一种基于拓扑数据分析(topological data analysis, TDA)的特征提取方法,其依托持久同调理论,通过构建 Alpha复形(alpha complex)以挖掘晶圆图的拓扑结构,并将其转化为可量化的拓扑特征。实验结果表明,在基于WM-811K数据集构建的模拟晶圆图数据集上,采用Alpha复形代替原VR复形(vietoris-rips complex),平均复形构建时间降低了约82%,平均内存占用降低了约10.09%。此外,将基于TDA的方法与DenseNet121、Swin Transformer以及新兴的ConvNeXt模型进行了对比，在特征提取方面,t-SNE可视化结果显示基于TDA方法提取的特征向量取得了最佳的聚类效果,相比于次优的ConvNeXt,轮廓系数提升了17.24%,提取时间降低了约75%,而内存峰值降低了约95%;在分类性能方面,结合支持向量机（SVM）分类器的实验表明,基于TDA的模型整体分类准确率高达0.992,优于DenseNet(0.989 3)和Swin Transformer(0.982 0)。 |
| 英文摘要: |
| Wafer map defect pattern classification is a critical step in semiconductor manufacturing, significantly impacting product yield and production efficiency. To address the limitations of existing deep learning-based wafer map defect pattern classification methods, such as poor interpretability and high computational resource consumption, this study proposes an improved feature extraction method based on topological data analysis (TDA). By leveraging persistent homology theory, the method constructs Alpha complexes to characterize topological structures in wafer maps and quantifies them into discriminative features. Experimental results on a synthetic wafer map dataset, generated by emulating the geometric distribution characteristics of the WM-811K dataset, demonstrate that replacing the conventional vietoris-rips (VR) complex with the Alpha complex reduces the average complex construction time by approximately 82% and decreases memory usage by 10.09%. Compared to state-of-the-art models including DenseNet121, Swin Transformer, and ConvNeXt, the TDA-based method achieves superior clustering performance, as evidenced by t-SNE visualizations, with a 17.24% improvement in Silhouette Coefficient over the suboptimal ConvNeXt model, along with a 75% reduction in feature extraction time and a 95% reduction in peak memory consumption. When integrated with a support vector machine (SVM) classifier, the TDA-based framework attains an overall classification accuracy of 0.992, outperforming DenseNet (0.989 3) and Swin Transformer (0.982 0). |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
