As the globalization of semiconductor design and manufacturing processes
continues, the demand for defect detection during integrated circuit
fabrication stages is becoming increasingly critical, playing a significant
role in enhancing the yield of semiconductor products. Traditional wafer map
defect pattern detection methods involve manual inspection using electron
microscopes to collect sample images, which are then assessed by experts for
defects. This approach is labor-intensive and inefficient. Consequently, there
is a pressing need to develop a model capable of automatically detecting
defects as an alternative to manual operations. In this paper, we propose a
method that initially employs a pre-trained VAE model to obtain the fault
distribution information of the wafer map. This information serves as guidance,
combined with the original image set for semi-supervised model training. During
the semi-supervised training, we utilize a teacher-student network for
iterative learning. The model presented in this paper is validated on the
benchmark dataset WM-811K wafer dataset. The experimental results demonstrate
superior classification accuracy and detection performance compared to
state-of-the-art models, fulfilling the requirements for industrial
applications. Compared to the original architecture, we have achieved
significant performance improvement.

这篇论文提出了一种利用预训练的 VAE 模型获取晶圆图故障分布信息，并结合原始图像集进行半监督模型训练的方法。通过师生网络的迭代学习，该模型在 WM-811K 晶圆数据集上验证得到了卓越的分类准确性和检测性能，实现了对工业应用的要求，并在性能上有显著的提升。

晶片地圖缺陷模式半監督分類使用潛在向量表示

Wafer Map Defect Patterns Semi-Supervised Classification Using Latent  Vector Representation

Semiconductor supply chains are described by significant demand fluctuation
that increases as one moves up the supply chain, the so-called bullwhip effect.
To counteract, semiconductor manufacturers aim to optimize capacity
utilization, to deliver with shorter lead times and exploit this to generate
revenue. Additionally, in a competitive market, firms seek to maintain customer
relationships while applying revenue management strategies such as dynamic
pricing. Price change potentially generates conflicts with customers. In this
paper, we present KnowGraph-PM, a knowledge graph-based dynamic pricing model.
The semantic model uses the potential of faster delivery and shorter lead times
to define premium prices, thus entail increased profits based on the customer
profile. The knowledge graph enables the integration of customer-related
information, e.g., customer class and location to customer order data. The
pricing algorithm is realized as a SPARQL query that relies on customer profile
and order behavior to determine the corresponding price premium. We evaluate
the approach by calculating the revenue generated after applying the pricing
algorithm. Based on competency questions that translate to SPARQL queries, we
validate the created knowledge graph. We demonstrate that semantic data
integration enables customer-tailored revenue management.

该论文提出了一种基于知识图谱的动态定价模型 KnowGraph-PM，利用客户档案和订单行为来确定相应的价格溢价，实现了客户量身定制的收益管理。