請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92962完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 傅楸善 | zh_TW |
| dc.contributor.advisor | Chiou-Shann Fuh | en |
| dc.contributor.author | 張婷淇 | zh_TW |
| dc.contributor.author | Ting-Chi Chang | en |
| dc.date.accessioned | 2024-07-09T16:08:43Z | - |
| dc.date.available | 2024-07-10 | - |
| dc.date.copyright | 2024-07-09 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-06-11 | - |
| dc.identifier.citation | [1] P. Virtanen, R. Gommers, T. E. Oliphant et al., “SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python,” Nature Methods, vol. 17, no. 3, pp. 261-272, doi: 10.1038/s41592-019-0686-2, 2020.
[2] L. Breiman, “Random forests,” Machine Learning, vol. 45, pp. 5-32, 2001. [3] G. D. Clifford, C. Liu, B. Moody, L. H. Lehman, I. Silva, Q. Li, A. Johnson, and R. G. Mark, “AF Classification from a Short Single Lead ECG Recording: The PhysioNet Computing in Cardiology Challenge,” Computing in Cardiology, vol. 44, pp. 1-4, doi: 10.22489/CinC.2017.065-469, 2017. [4] K. Kazemi, J. Laitala, I. Azimi, P. Liljeberg and A. M. Rahmani, “Robust PPG Peak Detection Using Dilated Convolutional Neural Networks,” Sensors, vol. 22, no. 16, pp. 6054, doi: 10.3390/s22166054, 2022. [5] M. Ragab, E. Eldele, W. L. Tan, C.-S. Foo, Z. Chen et. al., “ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data,” ACM Transactions on Knowledge Discovery from Data, vol. 17, no. 8, pp. 1-18, 2023. [6] E. Tseng, F. Yu, Y. Yang, F. Mannan, K. S. Arnaud, D. Nowrouzezahrai, J. F. Lalonde and F. Heide, “Hyperparameter Optimization in Black-Box Image Processing Using Differentiable Proxies,” ACM Trans. Graph., vol. 38, no. 4, pp. 27-1, 2019. [7] P. Tchatchoua, G. Graton, M. Ouladsine and J. F. Christaud, “Application of 1D ResNet for Multivariate Fault Detection on Semiconductor Manufacturing Equipment,” Sensors, vol. 23, no. 22, 9099, pp. 1-19, 2023. [8] N. Konz and M. Mazurowski, “Reverse Engineering Breast MRIs: Predicting Acquisition Parameters Directly from Images,” Proceedings of Conference on Medical Imaging with Deep Learning, Nashville, TN, vol. 54, pp.1-17, 2023. [9] F. Qiao, L. Zhao and X. Peng, “Learning to Learn Single Domain Generalization,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, pp. 12556-12565, 2020. [10] G. Bai, C. Ling, and L. Zhao, “Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks,” Proceedings of International Conference on Learning Representations, Kigali, Rwanda, pp. 1-19, 2022. [11] G. E. Hinton and R. R. Salakhutdinov, “Reducing the Dimensionality of Data with Neural Networks,” Science, vol. 313, no. 5786, pp. 504-507, 2006. [12] D. P. Kingma and M. Welling, “Auto-Encoding Variational Bayes,” arXiv:1312.6114, 2013. [13] I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative Adversarial Networks,” arXiv:1406.2661, 2014. [14] C. L. Tee and A. Pascual, “Impact of Quad Flat No Lead package (QFN) on automated X-ray inspection (AXI),” Proceedings of IEEE International Test Conference, Santa Clara, CA, pp. 1-10, doi: 10.1109/TEST.2007.4437601, 2007. [15] K. He, X. Zhang, S. Ren, J. Sun, “Deep Residual Learning for Image Recognition,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, pp. 770-778. 2016. [16] T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “Optuna: A Next-generation Hyperparameter Optimization Framework,” Proceedings of International Conference on Knowledge Discovery and Data Mining, Anchorage, AK, pp. 2623–2631, 2019. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92962 | - |
| dc.description.abstract | 印刷電路板（PCB）元件檢測對於電子產業中的品質和功能保證至關重要。本研究旨在開發一個自動化的PCB引腳缺陷檢測算法參數推薦系統，重點在於準確識別引腳元件資料中的heel和toe位置。傳統的算法參數調整方法高度依賴產線工程師的經驗，這種方法既不一致又耗時。為了解決這個問題，我們提出了張參數演算法，結合了一維變分自編碼器（1D VAE）進行數據生成和一維殘差網絡（1D ResNet）進行模型訓練。
1D VAE被用來生成多樣化的數據，增強訓練數據集並提升模型的泛化能力。隨後，1D ResNet在原始數據和生成數據上進行訓練，以準確預測heel和toe的位置。我們進行了綜合實驗來評估所提出算法在不同PCB資料集上的性能。結果顯示，張參數演算法能有效提升模型的泛化能力，適應各種PCB配置，提供可靠的參數推薦。 | zh_TW |
| dc.description.abstract | The inspection of Printed Circuit Board (PCB) components is critical in the electronics industry to ensure the quality and functionality of electronic devices. This study aims to develop an automated parameter recommendation system for PCB pin defect inspection algorithms, focusing on accurately identifying heel and toe positions in pin component data. Traditional methods for adjusting algorithm parameters rely heavily on the experience of production line engineers, which can be inconsistent and time-consuming. To address this, we propose ChangParameter algorithm, which uses a combination of a one-dimensional Variational Auto-Encoder (1D VAE) for data generation and a one-dimensional Residual Network (1D ResNet) for model training.
The 1D VAE is employed to generate diverse data, enhancing the training dataset and improving the model's generalization capabilities. The 1D ResNet is then trained on both the original and generated data to predict the heel and toe positions accurately. We conduct comprehensive experiments to evaluate the performance of the proposed algorithm across different PCB datasets. The results demonstrate that ChangParameter algorithm effectively enhances the model's ability to generalize and adapt to various PCB configurations, providing reliable parameter recommendations. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-07-09T16:08:42Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-07-09T16:08:43Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 誌謝 i
中文摘要 ii ABSTRACT iii CONTENTS v LIST OF FIGURES viii LIST OF TABLES x Chapter 1 Introduction 1 1.1 Overview 1 1.2 Introduction to Pin Component Data and Parameters 2 1.3 Challenges in Parameter Recommendation 4 1.4 Thesis Organization 6 Chapter 2 Related Works 7 2.1 Mathematical Statistical Analysis Methods 7 2.2 Regression Analysis Methods 9 2.3 Deep Learning-Based Methods 11 2.3.1 Deep Learning of One-Dimensional Sequences 11 2.3.2 Regression with Deep Learning 13 2.3.3 Domain Adaptation in Deep Learning 15 2.3.4 Data Generation in Deep Learning 17 Chapter 3 Background 20 3.1 Description of Pin Component Data 21 3.2 Reason for Using Deep Learning in Parameter Recommendation 24 Chapter 4 Methodology 26 4.1 Overview 26 4.2 Data Preprocessing 27 4.2.1 Hybrid Sampling Method 27 4.2.2 Data Normalization 30 4.3 Data Generation 31 4.3.1 1D VAE Model Principle 31 4.3.2 1D VAE Model Architecture 33 4.4 Model Training 35 4.4.1 1D Resnet Model Principle 35 4.4.2 1D ResNet Model Architecture 37 4.4.3 Hyperparameter Tuning with Optuna 40 Chapter 5 Experimental Results 42 5.1 Computer Hardware Configuration 42 5.2 Evaluation Metrics 43 5.2.1 MAE (Mean Absolute Error) 44 5.2.2 MSE (Mean Squared Error) 44 5.2.3 R² (Coefficient of Determination) 45 5.2.4 Entropy 46 5.3 Experimental Setup 47 5.3.1 Datasets 47 5.3.2 Data Generation Datasets 48 5.3.3 Experiment Configurations 51 5.4 Parameter Recommendation Results 53 5.4.1 Experimental Evaluation Metrics 54 5.4.2 Comparison of Experimental Results of Successful Predictions 56 5.4.3 Comparison of Experimental Results of Unsuccessful Predictions 64 Chapter 6 Conclusion and Future Works 69 References 70 | - |
| dc.language.iso | en | - |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 印刷電路板（PCB）元件檢測 | zh_TW |
| dc.subject | 參數推薦 | zh_TW |
| dc.subject | 一維殘差網絡 | zh_TW |
| dc.subject | 一維變分自編碼器 | zh_TW |
| dc.subject | one-dimensional Variational Autoencoder | en |
| dc.subject | one-dimensional Residual Network | en |
| dc.subject | Parameter Recommendation | en |
| dc.subject | Deep Learning | en |
| dc.subject | PCB Inspection | en |
| dc.title | 張參數：印刷電路板瑕疵檢測演算法參數推薦 | zh_TW |
| dc.title | ChangParameter: Printed Circuit Board Defect Inspection Algorithm Parameter Recommendation | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 巫宗昇;方瓊瑤 | zh_TW |
| dc.contributor.oralexamcommittee | Zong-Sheng Wu;Chiung-Yao Fang | en |
| dc.subject.keyword | 印刷電路板（PCB）元件檢測,深度學習,一維變分自編碼器,一維殘差網絡,參數推薦, | zh_TW |
| dc.subject.keyword | PCB Inspection,Deep Learning,one-dimensional Variational Autoencoder,one-dimensional Residual Network,Parameter Recommendation, | en |
| dc.relation.page | 72 | - |
| dc.identifier.doi | 10.6342/NTU202401133 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2024-06-12 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 生醫電子與資訊學研究所 | - |
| 顯示於系所單位： | 生醫電子與資訊學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf 未授權公開取用 | 2.77 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。