跳到主要內容

臺灣博碩士論文加值系統

(44.222.64.76) 您好!臺灣時間:2024/06/16 04:36
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

: 
twitterline
研究生:劉彥維
研究生(外文):Liu, Yan-Wei
論文名稱:具未知類別感測能力之印刷電路板新元件瑕疵偵測技術
論文名稱(外文):Unknown-aware Defect Detection of New Components in Printed Circuit Board
指導教授:馬清文馬清文引用關係
指導教授(外文):Ma, Ching-Wen
口試委員:謝君偉林柏宏林緯馬清文
口試委員(外文):Hsieh, Jun-WeiLin, Po-HungLin, WeiMa, Ching-Wen
口試日期:2022-10-27
學位類別:碩士
校院名稱:國立陽明交通大學
系所名稱:智慧與綠能產學研究所
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:2022
畢業學年度:111
語文別:英文
論文頁數:60
中文關鍵詞:瑕疵檢測度量學習未知類別偵測深度學習高斯混合模型
外文關鍵詞:Defect detectionMetric learningUnknown detectionDeep learningGaussian Mixture Model
相關次數:
  • 被引用被引用:0
  • 點閱點閱:114
  • 評分評分:
  • 下載下載:4
  • 收藏至我的研究室書目清單書目收藏:0
瑕疵偵測技術已經被廣泛運用於電子業的生產線當中,印刷電路板元件焊接所產生的瑕疵,為成品去留的關鍵因素。在生產階段就即時偵測出瑕疵,避免這些瑕疵產品流出,是相當重要的課題。監督式學習方法在待測樣本來自舊元件時,其偵測性能相當優異,但是面臨新元件時,其瑕疵偵測性能大幅下降。在本研究當中,我們提出了解決方案,解決神經網路在面臨新元件之瑕疵偵測性能下降的問題。我們提出了一個混合式專家(Hybrid Expert) 架構,其具備兩組獨立的分支,交替訓練瑕疵分類器與元件嵌入層。最後,它還應用了高斯混合模型(Gaussian Mixture Model),提升神經網路面對新元件瑕疵的偵測性能。 本研究在電子公司的真實資料集中進行模擬,驗證所提出之方法的性能,藉此改善產業遭遇到的瑕疵偵測難題。
Defect detection has been widely used on assembly lines in the electronics manufacturing industry. Solder defects in printed circuit boards are a key consideration for the retention of the finished product. It is crucial to detect defects in the manufacturing stage to prevent them from leaving the assembly lines. The supervised learning method has excellent detection performance when the samples are old components. However, its defect detection performance decreases significantly when the samples are of new components. In this study, we propose a solution to improve defect detection performance when new component samples are encountered. We propose a Hybrid Expert architecture with two separate branches to train the defect classifier and the component embedding layer alternately. Finally, the Gaussian mixture model is also applied to detect defects in new components, improving the defect detection performance. This study validates the performance of the proposed method by simulating it on a real dataset from an electronic company, improving the defect detection performance in the industry.
摘要. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i
Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii
Table of Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii
List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . v
List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . viii
1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.3 Goal . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.4 Contribution and Limitation . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
1.5 Thesis Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2 Related Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2.1 Image Classification . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2.2 Metric Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2.3 Compositional Zero-Shot Learning . . . . . . . . . . . . . . . . . . . . . . . . 7
2.4 Defect Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3 Method . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.1 Model Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.2 MobileNetV3 Large . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
3.3 Expert 1: Discriminative Model . . . . . . . . . . . . . . . . . . . . . . . . . 15
3.4 Expert 2: Generative Model . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
3.4.1 Gaussian mixture model . . . . . . . . . . . . . . . . . . . . . . . . . 19
3.4.2 Retargeting Estimator . . . . . . . . . . . . . . . . . . . . . . . . . . 25
3.5 Hybrid Expert: Combining Expert 1 and Expert 2 . . . . . . . . . . . . . . . . 27
4 Experiment and Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33
4.1 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33
4.2 Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38
4.3 Experiment Setup . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
4.4 Experiment (I): Expert 1 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
4.5 Experiment (II): Expert 2 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43
4.6 Experiment (III): Hybrid Expert . . . . . . . . . . . . . . . . . . . . . . . . . 43
4.7 Experiment (IV): Ablation study . . . . . . . . . . . . . . . . . . . . . . . . . 45
4.8 Overall Comparison . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48
5 Conclusions and Future Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . 56
References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57
[1] S. Zakaria, A. Amir, N. Yaakob, and S. Nazemi, “Automated detection of printed circuit boards (pcb) defects by using machine learning in electronic manufacturing: Current approaches,”
in IOP Conference Series: Materials Science and Engineering, vol. 767, no. 1. IOP Publishing, 2020, p. 012064.
[2] K. W. Tai, J. H. Chuah, H. Leong, and N. H. Kamarudin, “A pcb soldering joint defect recognition system using convolutional neural network,” in 2021 Innovations in Power and Advanced Computing Technologies (i-PACT). IEEE, 2021, pp. 1–6.
[3] N. Aggarwal, M. Deshwal, and P. Samant, “A survey on automatic printed circuit board defect detection techniques,” in 2022 2nd International Conference on Advance Computing
and Innovative Technologies in Engineering (ICACITE). IEEE, 2022, pp. 853–856.
[4] Y.-S. Deng, A.-C. Luo, and M.-J. Dai, “Building an automatic defect verification system using deep neural network for pcb defect classification,” in 2018 4th International Conference
on Frontiers of Signal Processing (ICFSP). IEEE, 2018, pp. 145–149.
[5] A. Howard, M. Sandler, G. Chu, L.-C. Chen, B. Chen, M. Tan, W. Wang, Y. Zhu, R. Pang, V. Vasudevan et al., “Searching for mobilenetv3,” in Proceedings of the IEEE/CVF International
Conference on Computer Vision, 2019, pp. 1314–1324.
[6] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014.
[7] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition. arxiv. 2015. doi: 10.48550,” arXiv preprint arXiv.1512.03385, 2015.
[8] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE conference on computer vision and pattern
recognition, 2017, pp. 4700–4708.
[9] J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7132–7141.
[10] Y. Movshovitz-Attias, A. Toshev, T. K. Leung, S. Ioffe, and S. Singh, “No fuss distance metric learning using proxies,” in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 360–368.
[11] Q. Qian, L. Shang, B. Sun, J. Hu, H. Li, and R. Jin, “Softtriple loss: Deep metric learning without triplet sampling,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 6450–6458.
[12] R. Hadsell, S. Chopra, and Y. LeCun, “Dimensionality reduction by learning an invariant mapping,” in 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), vol. 2. IEEE, 2006, pp. 1735–1742.
[13] F. Schroff, D. Kalenichenko, and J. Philbin, “Facenet: A unified embedding for face recognition and clustering,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 815–823.
[14] X. Wang, X. Han, W. Huang, D. Dong, and M. R. Scott, “Multi-similarity loss with general pair weighting for deep metric learning,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 5022–5030.
[15] I. Misra, A. Gupta, and M. Hebert, “From red wine to red tomato: Composition with context,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1792–1801.
[16] S. Purushwalkam, M. Nickel, A. Gupta, and M. Ranzato, “Task-driven modular networks for zero-shot compositional learning,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 3593–3602.
[17] Y.-L. Li, Y. Xu, X. Mao, and C. Lu, “Symmetry and group in attribute-object compositions,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11 316–11 325.
[18] X. Li, X. Yang, K. Wei, C. Deng, and M. Yang, “Siamese contrastive embedding network for compositional zero-shot learning,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9326–9335.
[19] Y. Xian, C. H. Lampert, B. Schiele, and Z. Akata, “Zero-shot learning—a comprehensive evaluation of the good, the bad and the ugly,” IEEE transactions on pattern analysis and machine intelligence, vol. 41, no. 9, pp. 2251–2265, 2018.
[20] S. Cheon, H. Lee, C. O. Kim, and S. H. Lee, “Convolutional neural network for wafer surface defect classification and the detection of unknown defect class,” IEEE Transactions on Semiconductor Manufacturing, vol. 32, no. 2, pp. 163–170, 2019.
[21] G. Zhang, K. Cui, T.-Y. Hung, and S. Lu, “Defect-gan: High-fidelity defect synthesis for automated defect inspection,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 2524–2534.
[22] M. Habibpour, H. Gharoun, A. Tajally, A. Shamsi, H. Asgharnezhad, A. Khosravi, and S. Nahavandi, “An uncertainty-aware deep learning framework for defect detection in casting products,” arXiv preprint arXiv:2107.11643, 2021.
[23] Y.-C. Hsu, J.-T. Wang, and W.-S. Huang, “Upon human’s unknown, can ai help to address uncertainty? a practice on package substrate aoi defect detection,” in 2021 16th International Microsystems, Packaging, Assembly and Circuits Technology Conference (IMPACT). IEEE, 2021, pp. 42–45.
[24] F. Ulger, S. E. Yuksel, and A. Yilmaz, “Anomaly detection for solder joints using β-vae,” IEEE Transactions on Components, Packaging and Manufacturing Technology, vol. 11, no. 12, pp. 2214–2221, 2021.
[25] Q. Zhou, J. Mei, Q. Zhang, S. Wang, and G. Chen, “Semi-supervised fabric defect detection based on image reconstruction and density estimation,” Textile Research Journal, vol. 91, no. 9-10, pp. 962–972, 2021.
[26] S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in International conference on machine learning. PMLR, 2015, pp. 448–456.
[27] F. Nogueira, “Bayesian Optimization: Open source constrained global optimization tool for Python,” 2014–. [Online]. Available: https://github.com/fmfn/BayesianOptimization
[28] L. Van der Maaten and G. Hinton, “Visualizing data using t-sne.” Journal of machine learning research, vol. 9, no. 11, 2008.
[29] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in 2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009, pp. 248–255.
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
無相關期刊