臺灣博碩士論文加值系統

隨著晶圓封裝技術的快速進步，特別是在晶片需求量急遽增加的背景下，提升產品質量和製程效率變得特別重要。本論文著重於晶圓封裝製程中，BGA上針腳的自動化檢測。為了滿足不斷變化的工業需求，本系統設計有著靈活的軟硬體架構，使其能夠迅速適應新的製程標準和技術要求。透過PLC控制龍門式三軸滑軌結合工業相機成像技術，本系統實現高效率及精確定位，進而達到高品質的成像效果。本研究採用YOLOv7影像處理技術和機器學習演算法，有效實現對BGA瑕疵的準確識別和分類。YOLOv7模型因其卓越的識別能力和快速處理速度而被選擇，能夠迅速且準確地識別微小瑕疵，如歪針、缺針及針端植球缺陷。透過對大量影像分析，證明了這套系統在提升檢測準確性和降低人工檢測的誤差。本研究的成果不僅提高了晶圓封裝檢測的準確性，也提升了晶圓封裝的質量水平，也為類似高精密度製程中的自動化檢測提供了重要參考。

With the rapid advancement of wafer packaging technology, particularly with the surging demand for chips, it has become particularly vital to improve product quality and process efficiency. This paper focuses on the automated detection of pins on BGA in wafer packaging processes. To meet the change in industrial requirements, the system is designed with a flexible software and hardware architecture, enabling rapid adaptation to new process standards and technological demands. Through PLC control of the three-axis gantry slide combined with industrial camera imaging technology, the system achieves high efficiency and precise positioning, leading to superior imaging quality. This paper uses YOLOv7 image processing technology and machine learning algorithms to accurately identify and categorize defects in BGA. The YOLOv7 model was selected for its exceptional recognition capabilities and fast processing speed, enabling the rapid and accurate identification of small defects such as bent, missing pins, and ball defects at the pin ends. Through analysis of a large number of images, it has been proven that this system can improve detection accuracy and reduce manual detection errors. The results of this paper not only improve the accuracy of wafer packaging inspection but also elevate the quality level of wafer packaging. Furthermore, it provides valuable insights for automated inspection in similar high-precision manufacturing processes.

中文摘要 i
Abstract ii
誌 謝 iii
目 錄 iv
圖目錄 vi
表目錄 viii
第一章 緒論 1
1.1 前言 1
1.2 研究動機 2
1.3 研究目的 2
1.4 文獻回顧 2
1.5 研究方法 6
1.6 論文架構 7
第二章 技術背景和理論基礎 8
2.1 滾珠螺桿滑軌控制系統 8
2.1.1 可程式化邏輯控制器 8
2.1.2 馬達驅動器 10
2.1.3 滾珠螺桿滑軌 10
2.2 機器視覺相機成像技術 12
2.3 物件偵測 13
2.3.1 雙階段(Two-stage)物件辨識 13
2.3.2 單階段(One-stage)物件辨識 15
第三章 系統架構與設計 17
3.1 自動化成像子系統 20
3.1.1 滑軌控制電路的設計與配置 21
3.1.2 龍門式三軸軌道 24
3.1.3 機器視覺相機 25
3.2 BGA檢測子系統 27
3.2.1 即時影像處理技術 28
3.2.2 人機介面 30
第四章 實驗結果 31
4.1 實驗環境 31
4.1.1 資料集建立 32
4.1.2 訓練參數 34
4.2 實驗數據及結果分析 34
4.3 可視化BGA檢測結果 39
第五章 結論與未來展望 42

[1]J. H. Lau, "Recent Advances and Trends in Advanced Packaging," in IEEE Transactions on Components, Packaging and Manufacturing Technology, vol. 12, no. 2, pp. 228-252, Feb. 2022, doi: 10.1109/TCPMT.2022.3144461.
[2]Y. P. Wang and T. D. Her, "Advanced substrate technology for ball grid array in electronic packaging," International Symposium on Electronic Materials and Packaging (EMAP2000) (Cat. No.00EX458), Hong Kong, China, 2000, pp. 335-339, doi: 10.1109/EMAP.2000.904176.
[3]Lejun Wang, Suk Chae Kang, Haiying Li, D. F. Baldwin and C. P. Wong, "Evaluation of reworkable underfills for area array packaging encapsulation," Proceedings International Symposium on Advanced Packaging Materials Processes, Properties and Interfaces (IEEE Cat. No.01TH8562), Braselton, GA, USA, 2001, pp. 29-36, doi: 10.1109/ISAOM.2001.916544.
[4]T. D. Moore, D. Vanderstraeten and P. M. Forssell, "Three-dimensional x-ray laminography as a tool for detection and characterization of BGA package defects," in IEEE Transactions on Components and Packaging Technologies, vol. 25, no. 2, pp. 224-229, June 2002, doi: 10.1109/TCAPT.2002.1010010.
[5]S. T. Rao, "Ball grid array assembly issues in manufacturing," Proceedings of 16th IEEE/CPMT International Electronic Manufacturing Technology Symposium, La Jolla, CA, USA, 1994, pp. 347-348 vol.1, doi: 10.1109/IEMT.1994.404730.
[6]M. Vojíř and L. Beran, "Global data structure for positioning machine controlled by PLC," 2015 IEEE International Workshop of Electronics, Control, Measurement, Signals and their Application to Mechatronics (ECMSM), Liberec, Czech Republic, 2015, pp. 1-6, doi: 10.1109/ECMSM.2015.7208699.
[7]G. Martinov, N. Kozak and S. Evstafieva, "Implementation of Dynamic Changes in Machine Kinematics in the Electroautomatic Subsystem of the CNC System," 2021 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM), Sochi, Russia, 2021, pp. 596-601, doi: 10.1109/ICIEAM51226.2021.9446459.
[8]Y. Yang and G. Cheng, "Research on data acquisition and management of digital workshop management system based on Safety PLC control," 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chongqing, China, 2021, pp. 452-455, doi: 10.1109/IAEAC50856.2021.9391095.
[9]Daniel Burrus, 2017, "The Anticipatory Organization: Turn Disruption and Change into Opportunity and Advantage", Greenleaf Book Group Press.
[10]賀桂芬、黃亦筠，未來製造它說了算！德國的章魚戰略：工業4.0，2015，天下雜誌。
[11]D. Cunico, A. Cenedese, L. Zaccarian and M. Borgo, "Nonlinear Modeling and Feedback Control of Boom Barrier Automation," in IEEE/ASME Transactions on Mechatronics, vol. 27, no. 6, pp. 4752-4763, Dec. 2022, doi: 10.1109/TMECH.2022.3163692.
[12]D. Liu, "Data-driven adaptive sliding mode controller design for nonlinear systems with prescribed performance," 2020 IEEE 9th Data Driven Control and Learning Systems Conference (DDCLS), Liuzhou, China, 2020, pp. 562-566, doi: 10.1109/DDCLS49620.2020.9275172.
[13]W. Li, C. Li, N. Wang, J. Li and J. Zhang, "Energy Saving Design Optimization of CNC Machine Tool Feed System: A Data-Model Hybrid Driven Approach," in IEEE Transactions on Automation Science and Engineering, vol. 19, no. 4, pp. 3809-3820, Oct. 2022, doi: 10.1109/TASE.2021.3136262.
[14]Z. Yang and Z. Yang, "Ghsx-18 Development and Application of Cnc Milling Machine for Rail Weld," 2018 11th International Conference on Intelligent Computation Technology and Automation (ICICTA), Changsha, China, 2018, pp. 396-401, doi: 10.1109/ICICTA.2018.00096.
[15]Y. Huang, W. Hao, Z. Wang and H. Wu, "Engineering Applications based on Industrial Robots and Machine Vision," 2022 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), Xi’an, China, 2022, pp. 496-500, doi: 10.1109/ICICML57342.2022.10009862.
[16]M. J. Seikavandi, "Low-cost 3D scanning using ultrasonic and camera data fusion for CNC Engraving Laser-Based Machine," 2020 International Conference on Machine Vision and Image Processing (MVIP), Iran, 2020, pp. 1-4, doi: 10.1109/MVIP49855.2020.9116903.
[17]C. A. Luna, M. Mazo, J. L. Lazaro and J. F. Vazquez, "Calibration of Line-Scan Cameras," in IEEE Transactions on Instrumentation and Measurement, vol. 59, no. 8, pp. 2185-2190, Aug. 2010, doi: 10.1109/TIM.2009.2031344.
[18]M. Atif and S. Lee, "Adaptive Pattern Resolution for Structured Light 3D Camera System," 2018 IEEE SENSORS, New Delhi, India, 2018, pp. 1-4, doi: 10.1109/ICSENS.2018.8589640.
[19]G. Batchuluun, J. K. Kang, D. T. Nguyen, T. D. Pham, M. Arsalan and K. R. Park, "Deep Learning-Based Thermal Image Reconstruction and Object Detection," in IEEE Access, vol. 9, pp. 5951-5971, 2021, doi: 10.1109/ACCESS.2020.3048437.
[20]R. Girshick, J. Donahue, T. Darrell and J. Malik, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation," 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014, pp. 580-587, doi: 10.1109/CVPR.2014.81.
[21]R. Girshick, "Fast R-CNN," 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015, pp. 1440-1448, doi: 10.1109/ICCV.2015.169.
[22]Ren, S., He, K., Girshick, R.B., & Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, pp. 1137-1149.
[23]J. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 779-788, doi: 10.1109/CVPR.2016.91.
[24]J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 6517-6525, doi: 10.1109/CVPR.2017.690.
[25]S. Huang, X. Li, Z. Jiang, X. Guo and A. Men, "Hyper Feature Fusion Pyramid Network for Object Detection," 2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), San Diego, CA, USA, 2018, pp. 1-6, doi: 10.1109/ICMEW.2018.8551547.
[26]P. Tumas and A. Serackis, "Automated Image Annotation based on YOLOv3," 2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE), Vilnius, Lithuania, 2018, pp. 1-3, doi: 10.1109/AIEEE.2018.8592167.
[27]A. Bochkovskiy, C.-Y. Wang and H.-Y. M. Liao, YOLOv4: Optimal Speed and Accuracy of Object Detection, [online] Available: https://arxiv.org/abs/2004.10934.
[28]D Wang and D He, "Channel pruned YOLO V5s-based deep learning approach for rapid and accurate apple fruitlet detection before fruit thinning[J]", Biosystems Engineering, vol. 210, pp. 271-281, 2021.
[29]C.-Y. Wang, A. Bochkovskiy and H.-Y. Mark Liao, "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors", arXiv:2207.02696, 2022.
[30]明緯企業股份有限公司，2023，明緯導軌型電源全產品線介紹，https://expo.meanwell.com.tw/upload/data/DIN_SeriesIntro.pdf。
[31]H. L. Floyd Ⅱ, "Reflections on a 50-Year Journey in Electrical Safety: Further Steps Toward Risk Reduction," in IEEE Industry Applications Magazine, vol. 29, no. 4, pp. 59-65, July-Aug. 2023, doi: 10.1109/MIAS.2023.3261107.
[32]H. L. Floyd II, "Through the Lens of Systems Safety: The Limitations of a Compliance-Based Safety Culture and Opportunities to Reduce Electrical Injuries," 2023 IEEE IAS Electrical Safety Workshop (ESW), Reno, NV, USA, 2023, pp. 34-36, doi: 10.1109/ESW49992.2023.10188267.
[33]北京時代超群電器科技有限公司，2023，馬達驅動器HB808C-YNN，http://images.100y.com.tw/pdf_file/79-HB808C.pdf
[34]R. Ghassani, Z. Kader, M. Fadel, P. Combes and M. Koteich, "Comparison Study of Rotor Field-Oriented Control and Stator Field-Oriented Control in Permanent Magnet Synchronous Motors," 2023 IEEE International Electric Machines & Drives Conference (IEMDC), San Francisco, CA, USA, 2023, pp. 1-7, doi: 10.1109/IEMDC55163.2023.10239079.
[35]M. Khalid, A. Mohan and B. A. C, "Performance Analysis of Vector controlled PMSM Drive modulated with Sinusoidal PWM and Space Vector PWM," 2020 IEEE International Power and Renewable Energy Conference, Karunagappally, India, 2020, pp. 1-6, doi: 10.1109/IPRECON49514.2020.9315210.
[36]台達電子工業股份有限公司，2019，DVP-ES3系列手冊，https://filecenter.delta-china.com.cn/Products/download/06/060301/Manual/DELTA_IA-PLC_DVP-ES3_OM_TC_20190628.pdf
[37]C. Sun, D. Liu, S. Kang and B. Hui, "Design of Intelligent Dispatching System for Port Gantry Crane," 2021 40th Chinese Control Conference (CCC), Shanghai, China, 2021, pp. 1887-1892, doi: 10.23919/CCC52363.2021.9549610.
[38]J. Mayer, V. Klumpp, J. Hillenbrand and B. Noack, "Statistical Approach for Preload Monitoring of Ball Screw Drives," 2023 IEEE SENSORS, Vienna, Austria, 2023, pp. 1-4, doi: 10.1109/SENSORS56945.2023.10325060.
[39]C. -H. Liu and C. -H. Chiu, "Optimal design of a soft robotic gripper with high mechanical advantage for grasping irregular objects," 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore, 2017, pp. 2846-2851, doi: 10.1109/ICRA.2017.7989332.
[40]上海韌躍電子科技有限公司，2021，RY-605工業相機手冊，http://sh-renyue.com。
[41]SONY, 2018, Sony Releases Stacked CMOS Image Sensor for Smartphones with Industry’s Highest 48 Effective Megapixels Featuring World First Ultra-compact Pixel Size of 0.8 μm, https://www.sony.com/en/SonyInfo/News/Press/201807/18-060E/
[42]J. Solawetz, "What is YOLOv7? A Complete Guide.,' " roboflow, 17 JUL 2022. [Online]. Available: https://blog.roboflow.com/yolov7-breakdown/. [Accessed 1January 2024].