A Novel Defect Classification Scheme Based on Convolutional Autoencoder with Skip Connection in Semiconductor Manufacturing
A Novel Defect Classification Scheme Based on Convolutional Autoencoder with Skip Connection in Semiconductor Manufacturing
复制标题
DOI：
10.23919/icact53585.2022.9728861
复制
发表时间：
2022-02
期刊：
影响因子：
--
通讯作者：
Jae-Min Cha;Juyong Park;J. Jeong
中科院分区：
文献类型：
--
作者：
Jae-Min Cha;Juyong Park;J. Jeong
半导体工艺由于其复杂多样的工艺，不可避免地会产生缺陷。特别是，晶圆可以说是半导体制造的核心，因为它们直接关系到半导体的生产率。因此，检测和分类晶圆上的缺陷可以帮助工程师解决缺陷的根本原因，提高成品率。本文提出了一种基于跳跃连接的卷积自动编码器，用于晶圆图缺陷分类。首先，通过构造卷积块来设计编解码器。对称块采用跳接方式连接。最后，使用学习的编码器的权重对分类器的训练数据进行编码。通过跳跃连接成功地降低了模型的损失，并通过对编码器的重用提高了性能。
The semiconductor process cannot avoid defects due to its complex and diverse processes. In particular, wafer can be said to be the core of semiconductor manufacturing because they are directly related to the productivity of semiconductors. Therefore, detecting and classifying defects on wafers can help engineers address the root cause of defects and improve yield. In this paper, we propose a convolutional autoencoder using skip connection for wafer map defect classification. First, the encoder and decoder are designed by constructing a convolutional block. And connect the symmetrical blocks with skip connection. Finally, the training data of the classifier is encoded using the weights of the learned encoder. The loss of the model was successfully reduced with skip connection, and improved performance was obtained by reusing the encoder.