G2LGAN: 對不平衡資料集進行資料擴增應用於晶圓圖缺陷分類;G2LGAN: Data augmentation of imbalanced data sets for wafer map defect classification

NCU Institutional Repository > 資訊電機學院 > 電機工程研究所 > 博碩士論文 > Item 987654321/88351

請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/88351

題名:	G2LGAN: 對不平衡資料集進行資料擴增應用於晶圓圖缺陷分類;G2LGAN: Data augmentation of imbalanced data sets for wafer map defect classification
作者:	王承暘;Wang, Chieng-Yang
貢獻者:	電機工程學系
關鍵詞:	生成對抗網路;晶圓缺線分類;不平衡資料集;GAN;Wafer map defect classification;imbalanced data
日期:	2022-01-12
上傳時間:	2022-07-14 00:16:17 (UTC+8)
出版者:	國立中央大學
摘要:	半導體的製造需要經過多個複雜的化學程序，任一環節的錯誤皆會使生產的晶圓產生缺陷，因此晶圓缺陷分類是半導體產業維持並提升良率的關鍵任務。然而，目前的晶圓缺陷分類仍然由工程師透過人力進行分類，因此本論文透過神經網路在圖像分類上的優異表現來自動化分類晶圓圖缺陷。由於半導體製程的進步使得具有缺陷的晶圓圖難以收集。為了解決資料集不平衡與資料不足的問題，本論文提出了一個數據擴增方法與隨機欠採樣能夠有效的平衡資料集。在晶圓圖分類網路的部份本文使用輕量型的網路架構，除了能夠減少計算資源提高模型效率之外還能夠消除資料集所造成的過擬合 (Overfitting)的問題。本論文提出的資料擴增是基於生成對抗網路 (Generative Adversarial Network, GAN)，所提出的方法 G2LGAN(Global to Local GAN)能夠優先學習資料集的全局特徵再學習個別類別的局部特徵，即使在資料集不平衡的情況下也能夠有效生成各個類別的資料以解決資料不足的問題。分類網路則是基於 MobileNetV2，根據實驗結果發現在晶圓缺陷分類任務上，與高維度的特徵相比，低維度的特徵較為重要，根據此結果來設計分類網路達到縮小模型並維持高準確度。本文使用 WM-811K資料集進行驗證。由於該資料集具有嚴重的數據不平衡問題。本文集成了資料增強與隨機欠採樣的方法來優化資料集，並使用所提出的分類網路進行分類任務。實驗結果顯示，所提出的 G2LGAN能夠提升模型準確度約 9.15%。所提出的晶圓分類網路與現有的研究相比，在模型的參數量上節省了 58%，並且在準確度上有 1.39%與 F1-Score上有 12.35%的領先。;Semiconductor manufacturing requires multiple complex chemical processes. Errors in any link will cause defects in the produced wafers. Therefore, wafer map defect classification is a key task for the semiconductor industry to maintain and improve yield. However, the current wafer defect classification is still performed by engineers through human labor. Therefore, this paper uses the excellent performance of neural networks in image classification to automatically classify wafer defects. Due to advances in semiconductor manufacturing processes, it is difficult to collect defective wafer maps. In order to solve the problem of data set imbalance and insufficient data, this paper proposes a data augmentation method and random undersampling that can effectively balance the data set. In the part of the wafer map classification network, this article uses a lightweight network architecture, which not only reduces computing resources and improves model efficiency, but also eliminates the problem of overfitting caused by data sets. The data augmentation proposed in this paper is based on the Generative Adversarial Network (GAN). The proposed method G2LGAN (Global to Local GAN) can first learn the global features of the data set and then learn the local features of individual classes, even in In the case of imbalanced data sets, various classes of data can be effectively generated to solve the problem of insufficient data. The classification network is based on MobileNetV2. According to the experimental results, it is found that in wafer defect classification tasks, low-dimensional features are more important than high-dimensional features. Based on this result, the classification network is designed to reduce the model and maintain high accuracy. This article uses the WM-811K data set for verification. Because this data set has serious data imbalance problem. This paper integrates data enhancement and random undersampling methods to optimize the data set, and uses the proposed classification network for classification tasks. Experimental results show that the proposed G2LGAN can improve the accuracy of the model by approximately 9.15%. Compared with the existing research, the proposed wafer classification network saves 58% in the amount of model parameters, and has a accuracy of 1.39% and a 12.35% lead in F1-Score.
顯示於類別:	[電機工程研究所] 博碩士論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	78	檢視/開啟

在NCUIR中所有的資料項目都受到原著作權保護.

社群 sharing

資料載入中.....