(3.237.97.64) 您好!臺灣時間:2021/03/03 06:46
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:李郁晨
研究生(外文):Yu-Chen Lee
論文名稱:晶圓圖缺陷分類與嵌入式系統實現
論文名稱(外文):Wafer Map Defect Pattern Classification and its Embedded System Implementation
指導教授:蔡宗漢蔡宗漢引用關係
指導教授(外文):Tsung-Han Tsai
學位類別:碩士
校院名稱:國立中央大學
系所名稱:電機工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2019
畢業學年度:108
語文別:中文
論文頁數:46
中文關鍵詞:晶片缺陷神經網路深度可分離卷積
外文關鍵詞:wafer defectneural networkdepthwise separable convolution
相關次數:
  • 被引用被引用:0
  • 點閱點閱:70
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
在半導體工業中,晶圓測試扮演不可或缺的一環,於生產的最後階段會進行不同電性的測試以確保產品的功能性,而測試結果再結合晶圓形狀所產生的圖形稱作晶圓圖(Wafer Map),可以決定是否進行後續封裝等動作。然而,判斷產生的缺陷(defect)大多仰賴人工來執行,不僅耗費時間且需要經驗豐富之工程師。
本論文分別對網路上公開資料集WM-811K,以及公司合作所建立的資料集,進行晶圓圖缺陷分類。研究可分成兩個部分,一是神經網路的訓練,二是嵌入式系統上實現。神經網路部分,採用深度可分離卷積(depth separable convolution)的結構為基礎,設計出具有低參數量之神經網路,針對WM-811K中8類不同缺陷進行分類,最終可達97.01%準確度。在自行建立的資料集中,一共蒐集了16388張晶圓圖,定義21個缺陷類別,並對其進行擴增與分類,最終達87.4%準確度。系統方面,建立的資料使用MongoDB資料庫進行管理,放置於嵌入式板Jetson Nano,可連結遠端server進行訓練,回傳模型於嵌入式板執行推理(inference).此系統可以令使用者持續更新資料集,並對原模型進行優化,對於現今各公司晶圓缺陷定義不同,以及標注資料緩慢等問題,提供初步解決方案。
In the semiconductor industry, wafer testing plays an indispensable role. There are different electrical tests in the final stages to ensure the functionality of the product. The results with the wafer shape is called Wafer Map. This map could decide whether to go to next step – package. However, most judgments of the defect rely on human to execute, which is time-consuming and requires experienced engineers.
In this paper, the wafer defect classification is carried out on the open dataset WM-811K. The dataset established by the cooperation with a company. The research can be divided into two parts, one is the training of neural network, and the other is implementation on embedded system. The neural network part is based on deep separable convolution. We design an architecture with low amount of parameters, which can classify the 8 different defects in WM-811K. It can finally achieve 97.01% accuracy. In the established dataset, a total of 16,388 wafers were collected, 21 defect categories were defined, and the data are augmented and classified. The final accuracy is 87.4% accuracy. On the system side, the established data is managed using the MongoDB database, placed on the embedded board Jetson Nano, which can be linked to remote servers for training and then it returns the model and performed on the embedded board to execute inference. This system enables users to continuously update the dataset and optimize the parameter model. It provides preliminary solutions to the different definition of wafer defects in today's companies and solves the problem of slow labeling time.
摘要-----------------------------------------------I
ABSTRACT------------------------------------------II
1. 序論---------------------------------------1
1.1. 研究背景與動機------------------------------1
1.2. 論文架構-----------------------------------4
2. 文獻探討-----------------------------------5
2.1. 基於WM811K資料集---------------------------5
2.2. 基於自定義資料集----------------------------6
3. 網路模型設計與結果--------------------------9
3.1. 資料集-------------------------------------9
3.2. 資料前處理---------------------------------12
3.3. 數據增強策略-------------------------------16
3.4. 缺陷分類網路模型設計------------------------18
3.5. 訓練策略與結果-----------------------------24
4. 系統架構設計-------------------------------29
4.1. 產學合作----------------------------------29
4.2. 標注與訓練平台-----------------------------30
4.3. NVIDIA JETSON NANO執行結果----------------33
5. 結論--------------------------------------35
參考文獻------------------------------------------36

表目錄
表 1:CNN自編碼詳細參數 17
表 2:DWC1模型參數量 20
表 3:擴展模塊維度表 22
表 4:DWC2模型參數量 23
表 5:論文準確度比較表 25
表 6:DWC1參數量比較表 26
表 7:分割資料集準確度比較表 28
表 8:DWC2參數量比較表 28
表 9:NVIDIA JETSON NANO規格表 33
表 10:執行時間表 34

圖目錄
圖 1:晶圓測試階段示意圖 1
圖 2:CNN網路模型 3
圖 3:WM811K可視化與雷登變化特徵 5
圖 4:SVE流程圖 6
圖 5:自定義21類缺陷晶圓圖 7
圖 6:BIN2VEC結果示意圖 8
圖 7:WM-811K資料集 10
圖 8:WM-811K資料集數量結構 10
圖 9:自定義資料集(GUI可視化) 11
圖 10:資料轉換示意圖 12
圖 11:歐式距離轉換示意圖 13
圖 12:CHANNEL3晶圓圖 13
圖 13:RESIZED晶圓圖 14
圖 14:邊緣破碎圖 14
圖 15:修補後晶圓圖 15
圖 16:CNN自編碼器架構圖 16
圖 17:自編碼器生成晶圓圖 17
圖 18:旋轉生成晶圓圖 18
圖 19:標準CNN與深度可分離卷積架構圖 19
圖 20:DWC1網路架構 19
圖 21:RESIDUAL 與 INVERTED RESIDUAL 21
圖 22:DWC2模塊架構圖 22
圖 23:DWC2網路架構 23
圖 24:DWC1準確度訓練曲線 25
圖 25:DWC1 LOSS收斂曲線 25
圖 26:DWC2準確度訓練曲線 27
圖 27:DWC2 LOSS收斂曲線 27
圖 28:訓練流程圖 10
圖 29:MONGODB資料庫 31
圖 30:GUI介面圖 31
圖 31:系統資料傳遞圖 32
圖 32:NVIDIA JETSON NANO照片 34
圖 33:JETSON NANO執行結果圖 34
[1] A. Krizhevsky, I. Sutskever, and G. E Hinton. “Imagenet classification with deep convolutional neural networks,” In Advances in Neural Information Processing Systems, pages 1097–1105, 2012.
[2] S. Ren, K. He, R. Girshick, and J. Sun. “Faster r-cnn: Towards real-time object detection with region proposal networks,” In Advances in Neural Information Processing Systems, pages 91–99, 2015.
[3] J. Long, E. Shelhamer, and T. Darrell. “Fully convolutional networks for semantic segmentation,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3431– 3440, 2015.
[4] M.-J. Wu, J.-S. R. Jang, and J.-L. Chen, “Wafer map failure pattern recognition and similarity ranking for large-scale data sets,” IEEE Trans. Semicond. Manuf., vol. 28, no. 1, pp. 1–12, Feb. 2015.
[5] M. Saqlain , J. Y. Lee and B. Jargalsaikhan, “A Voting Ensemble Classifier for Wafer Map Defect Patterns Identificationin Semiconductor Manufacturing,” IEEE Trans. Semicond. Manuf, vol. 32, no. 2, May 2019
[6] T. Nakazawa and D. V. Kulkarni, “Wafer Map Defect Pattern Classification and Image Retrieval Using Convolutional Neural Network,” Applied Sciences, vol. 9, issue 3, February 2019.
[7] J. Kim, H. Kim, J. Park, K. Mo and P. Kang, “Bin2Vec: A Better Wafer Bin Map Coloring Scheme for Comprehensible Visualization and Effective Bad Wafer Classification,” IEEE Trans. Semicond. Manuf., vol. 31, no. 2, May 2018.
[8] A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T Weyand, M. Andreetto, H. Adam, “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications” in CVPR, 2017
[9] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4510-4520
[10] L.-C. Chen, G. Papandreou, F. Schroff, and H. Adam. “Rethinking atrous convolution for semantic image segmentation,” arXiv:1706.05587, 2017.
[11] L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” arXiv:1802.02611, 2018.
[12] Chi Geng, JianXin Song, “Human action recognition based on convolutional neural networks with a convolutional auto-encoder,” International Conference on Computer Sciences and Automation Engineering (ICCSAE 2015)
[13] Deep Feature Consistent Variational Autoencoder, “Deep feature consistent variational autoencoder,” Applications of Computer Vision (WACV), IEEE Workshop 2017
[14] Min Chen, Xiaobo Shi, Yin Zhang, Di Wu, Mohsen Guizani, “Deep features learning for medical image analysis with convolutional autoencoder neural network,” IEEE Transactions on Big Data, June 2017.
[15] G. Lin, A. Milan, C. Shen, and I. Reid, “Refinenet: Multipath refinement networks with identity mappings for highresolution semantic segmentation,” arXiv:1611.06612, 2016.
[16] L. Sifre and S. Mallat, “Rigid-motion scattering for texture classification,” arXiv:1403.1687 [cs], Mar. 2014.
[17] J. Su et al., “Redundancy-reduced mobilenet acceleration on reconfigurable logic for ImageNet classification,” in Proc. Appl. Reconfig. Comput. Archit. Tools Appl., 2018, pp. 16–28.
[18] M. Everingham, L. V. Gool, C. K. I. Williams, J. Winn, and A. Zisserman, “The PASCAL Visual Object Classes (VOC) Challenge,” International Journal of Computer Vision, 88(2), 303-338, 2010.
[19] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 770–778, 2016.
[20] K. He, X. Zhang, S. Ren, J. Sun, “Deep residual learning for image recognition,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016, pp. 770–778.
[21] C. A. Mack, “Fifty years of Moores law,” IEEE Trans. Semicond. Manuf., vol. 24, no. 2, pp. 202–207, May 2011.
[22] F.-L. Chen and S.-F. Liu, “A neural-network approach to recognize defect spatial pattern in semiconductor fabrication,” IEEE Trans.Semicond. Manuf., vol. 13, no. 3, pp. 366–373, Aug. 2000.
[23] G. Choi, S.-H. Kim, C. Ha, and S. J. Bae, “Multi-step ART1 algorithm for recognition of defect patterns on semiconductor wafers,” Int. J. Prod. Res., vol. 50, no. 12, pp. 3274–3287, Dec. 2012.
[24] C.-F. Chien, W.-C. Wang, and J.-C. Cheng, “Data mining for yield enhancement in semiconductor manufacturing and an empirical study,” Expert Syst. Appl., vol. 33, no. 1, pp. 192–198, Jul. 2007.
[25] C.-H. Wang, S.-J. Wang, and W.-D. Lee, “Automatic identification of spatial defect patterns for semiconductor manufacturing,” Int. J. Prod.Res., vol. 44, no. 23, pp. 5169–5185, Dec. 2006.
[26] Adly, F.; Alhussein, O.; Yoo, P.D.; Al-Hammadi, Y.; Taha, K.; Muhaidat, S.; Jeong, Y.S.; Lee, U.; Ismail, M.Simplified subspaced regression network for identification of defect patterns in semiconductor wafer maps. IEEE Trans. Ind. Inf. 2015, 11, 1267–1276.
[27] F. Adly et al., “Simplified subspaced regression network for identification of defect patterns in semiconductor wafer maps,” IEEE Trans. Ind. Informat., vol. 11, no. 6, pp. 1267–1276, Dec. 2015
[28] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, “Going deeper with convolutions,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Boston, MA, USA, 7–12 June 2015, pp. 1–9.
[29] M. Rastegari, V. Ordonez, J. Redmon, A. Farhadi, “XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks” in CVPR, 2016
[30] Data Science & Business Analytics Lab, School of Industrial Management Engineering, College of Engineering, Korea University http://dsba.korea.ac.kr/main
[31] https://en.wikipedia.org/wiki/Convolutional_neural_network
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關論文
 
無相關期刊
 
無相關點閱論文
 
系統版面圖檔 系統版面圖檔