簡易檢索 / 詳目顯示

回結果列表
研究生： 葉俊吾
Yeh, Junwu
論文名稱： 運用類神經網路建構SMT錫膏印刷製程品質管制系統
Using Artificial Neural Networks to Build a Quality Control System of SMT Stencil Printing Process
指導教授： 楊大和
Yang, Taho
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 製造工程研究所
Institute of Manufacturing Engineering
論文出版年： 2002
畢業學年度： 90
語文別： 中文
論文頁數： 105
中文關鍵詞： 錫膏印刷 、類神經網路 、表面黏著技術 、實驗設計
外文關鍵詞： Neural Networks, Design of Experiment, Stencil Printing, SMT
相關次數： 點閱：105  下載：5 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 為因應現今消費性電子產品的輕、薄、短、小趨勢，電子組裝技術亦隨著不斷改進。表面黏著組裝技術 (Surface Mount Technology, SMT) 已加速地取代傳統波焊製程 (Wave Soldering) ，儼然成為現代電子組裝產業主流，其製程優點在於降低生產成本並製造出高品質之電子產品。但於極端複雜的表面黏著組裝技術生產環境裡，製程中充滿著許多不確定的生產變數組合，尤其是在高密度之電子元件組裝，更成為基板組裝業之重大課題。若無法妥善控管製程參數及原物料特性，極可能產生不良焊性 (Solderability) ，導致產品品質下降、增加額外之生產成本；根據文獻及業界資深工程師的經驗得知，52%~71%之焊性不良源起於錫膏印刷製程 (Solder Paste Printing Process)。
    本研究針對錫膏印刷製程單元，利用8個重要參數(錫膏黏度、鋼板厚度、零件腳距、鋼板與銲墊比例、間隙、印刷速度、刮刀壓力、錫膏顆粒)以分析錫膏印刷製程。並運用實驗設計及類神經網路以建構一套製程品質管制之衡量標準，並可配合統計製程品管(SPC)軟體以提昇焊性及產品品質。

    Surface Mount Technology (SMT) assembly is the placement and attachment of electronic components to the surface of a printed circuit board, and it has become the key technology to transform manufacturing in the electronics industry to continuously respond to the needs of the global market. The relationship between the input/output variables in SMT acts nonlinearly and severely. The stencil printing is one of the most critical stages and accounts for 52~71% of overall soldering defects.
    This research will help in understanding the solder paste stencil printing process and identifying the critical variables that influence the volume of deposited solder paste. Through design of experiment and neural networks, a quality control system of stencil printing is established that helps engineers in troubleshooting the malfunctioned process and to improve solderability.

    中文摘要 i 英文摘要 ii 誌 謝 iii 目 錄 iv 圖目錄 vii 表目錄 ix 第一章 緒論 1 1.1 簡介 1 1.2 研究背景與動機 1 1.3 印刷電路板製程簡介 2 1.3.1 表面黏著組裝技術 3 1.3.2 表面黏著生產線機器配置 3 1.3.3 表面黏著製程 4 1.3.4 波焊製程 8 1.3.5 自動測試 8 1.4 研究目的 9 1.5 研究方法與流程 9 1.6 論文架構 11 第二章 文獻回顧 12 2.1 表面黏著技術 12 2.1.1電子組裝之品質控管—表面黏著組裝技術 12 2.1.2電子組裝之品質控管—錫膏印刷製程 12 2.2 類神經網路 25 2.2.1類神經網路基本概念 25 2.2.2類神經網路在生產規劃與管制上之應用 27 2.3 實驗設計 30 2.3.1 基本原理 30 2.3.2 實驗設計之目的 31 2.3.3 部分因子設計 32 第三章 模式理論與系統架構 34 3.1 錫膏印刷製程系統架構 34 3.1.1 問題描述 34 3.1.2印刷垂直與平行方向 35 3.2 類神經網路 36 3.2.1類神經網路模式 38 3.2.2 倒傳遞類神經網路 42 3.2.2.1 倒傳遞類神經網路架構 43 3.2.2.2 倒傳遞類神經網路學習演繹法 44 3.3類神經網路模式之建構 48 3.3.1 網路模式選擇 48 3.3.2 網路參數設定 49 3.3.3決定終止條件 50 3.3.4 進行訓練 51 3.3.5 網路績效評估與製程能力指標之導入 51 第四章 實例說明 53 4.1實例環境資料 53 4.2 錫膏印刷品質管制系統模式之構建 54 4.2.1 運用實驗設計建立與蒐集結構化製程資料 55 4.2.2 建立類神經網路的預測模式 57 4.2.3 預測與分析 62 4.2.4 網路績效評估指標 62 4.3 執行結果 63 4.3.1 水平方向 63 4.3.1.1 選取網路架構 63 4.3.1.2交叉驗證法 64 4.3.2 垂直方向 65 4.3.2.1 選取網路架構 65 4.3.2.2交叉驗證法 66 4.4資料分析與比較 67 4.5倒傳遞網路與通用迴歸網路之比較 73 4.5.1 通用迴歸型類神經網路 73 4.5.2 網路績效比較 74 4.6製程能力指標 、 75 第五章 結論 79 5.1 結論 79 5.2 未來研究方向 80 參考文獻 82 附錄A：243筆實驗因子水準組合程式碼 88 附錄B：243筆實驗因子水準直交表組合 90

    參考文獻
    1. 葉怡成，類神經網路模式應用與實作，儒林圖書公司，民國八十二年二月.
    2. Anthony W. and Daniel F. B., “Initial investigation into low-cost ultra-fine pitch solder printing process based on innovative laser printing technology,” IEEE transactions on electronics packaging manufacturing, pp.303-307, 1999
    3. Dagli, C. et al., “Enhancing the Performance of Neural Network Models for the Wire Bonding Process,” Intelligent Engineering Systems through Artificial Neural Networks, Vol. 4, pp.1041-1047, 1994.
    4. Danielsson, H., “Surface Mount Technology with Fine Pitch Components,” Chapman & Hall, New York, 1995.
    5. Diane, E. K., “Machine Learning,” Training & development Journal, Vol. 44, No. 12, pp.24-29, December, 1990.
    6. Dubravka, R., Vinko S., and Janeta F. P., “Solder Paste for Fine Line Printing in Hybrid Microelectronics,” Microelectronics Journal, Vol. 26, pp.441-447, 1995.
    7. Ekere, N. N., Ismail, I., Lo. E. K., and Mannan, S. H., “Experimental Study of Stencil/Substrate Separation Speed in On-contact Solder Paste Printing for Reflow Soldering,” Journal of Electronics Manufacturing, Vol. 3, pp.25-29, 1993.
    8. Franklin, M. F., “Constructing Tables of Minimum Aberration P n-m Design,” Technometrics, Vol. 26, No. 3, August, 1984.
    9. Fujiuchi, Shin’ichi nad Toriyama, kazushige, “Collective Screen Printing for Carrier Bump and SMT Pads,” Proceedings of IEEE/CPMT International Electronics Manufacturing Technology Symposium, pp.109-112, 1994.
    10. Geman, S., Bienenstock, E., and Doursat, R., “Neural Networks and the Bias/Variance Dilemma,” Neural Computation, Vol. 4, pp.1-58, 1992.
    11. He, D., Ekere, N.N., and Currie, M.A., “The Behavior of Solder Pastes in Stencil Printing with Vibrating Squeegee,” IEEE Transactions on Components, Packaging, and Manufacturing Technology-Part C, 21, No.4, pp.317-324, 1998.
    12. Henson, T., Huxhold, W., and Bowman, D., “An Enhanced Neural Network Learning Algorithm with Simulated Annealing,” Third Workshop on Neural Networks：Academic/Industrial/NASA/Defense, pp.87-94, February, 1992.
    13. Hinch, S. W., “Handbook of Surface Mount Technology,” Longman Scientific and Technical, UK, 1988.
    14. Hou, T. H., Lin, L., and Scott, P. D., “A Neural Network-based Automated Inspection System with an Application to Surface Mount Devices,” International Journal of Production Research, Vol. 31, No. 5, pp.1171-1187, 1993.
    15. Huang, S, and Zhang, H., “Neural Networks in Manufacturing: A Survey,” IEEE/CPMT International Electronics Manufacturing Technology Symposium, pp.177-190, 1993.
    16. Hush, D. R., and Horne, B. G., “Progress in Supervised Neural Networks：What’s New since Lippmann,” IEEE Signal Processing Magazine, pp.8-39, January, 1993.
    17. Huston, S., “Surface Mount Technology Market Forecasting,” Journal of Industrial Technology, Vol. 17, No. 1, pp.2-7, November 2000 to January 2001.
    18. Hwang, J.S., “Solder Paste In Electronics Packaging,” Van Nostrand Reinhold, New York, 1992.
    19. Itoh, M., “General Information on Solder Paste”, Technical Report, Tokyo, Japan, 1999.
    20. Juran, J. M., Jurans Quality Control Handbook, McGraw-Hill, New York, 1974.
    21. Kane, V. E., “Process Capability Indices,” Journal of Quality Technology, Vol. 18, pp.41-45,1986.
    22. Kim, B. and May, G. S., “An Optimal Neural Network Process Model for Plasma Etching,” IEEE Transactions on Semiconductor Manufacturing, Vol. 7, No. 1, pp.12-21, 1994.
    23. Kruschke, J. K., and Movellan, J. R., “Benefits of gain：Speeded Learning and Minimal Hidden Layers in Back-propagation networks,” IEEE Transactions on Systems Man& Cybernetics, Vol. 21, pp.273-280, 1991.
    24. Lau, J. H., “Handbook of Fine Pitch Surface Mount Technology,” Van Nostrand Reinhold, Chapter 1, New York, 1994.
    25. Lee, Y.H. and Kim, S., “Neural Network Applications for Scheduling Jobs on Parallel Machines,” Computers and Industrial Engineering, Vol. 25, pp.227-230, 1993.
    26. Lewis, C. D., Industrial and Business Forecasting Method, Butterworth Scientific, London, 1982.
    27. Li, Y., Mahajan, R. L., and Tong, J., “Design Factors and Their Effect on PCB Assembly Yield- Statistical and Neural Network Predictive Models,” IEEE/CHMT International Electronics Manufacturing Technology Symposium, pp.353-361, 1993.
    28. Lideen, J. D. and Dahl, A. O., “Printing Techniques for Fine Pitch Screen Printing,” Proceedings of the Technical Program- NEPCON West, pp. 1862-1877.
    29. Liu, D. and Dong, J., “Dispatching Rule Selection Using Artificial Neural Networks for Dynamic Planning and Scheduling,” Journal of Intelligent Manufacturing, Vol. 7, pp.243-250, 1996.
    30. Manko, H.H., “Soldering Handbook for Printed Circuits and Surface Mounting,” Van Nostrand Reinhold, New York, 1995.
    31. Mannan, S. H.; Ekere, N. N.; Ismail, I.; and Lo, E. K., “Squeegee Deformation Study in the Stencil Printing of Solder Pastes,” IEEE Transactions on Components, Hybrids, and Manufacturing Technology- Part A, Vol. 17, No. 3, pp.470-475, 1994.
    32. Markstein, H. W., “Controlling the Variables in Stencil Printing,” Electronic Packaging & Production, Vol. 37, No. 2, pp.48-56, 1997.
    33. Martinez, E. E., Smith, A. E., and Idanda, B., “Reducing Waste in Casting with a Predictive Neural Model,” Journal of Intelligent Manufacturing, Vol. 5, No. 4, pp.277-286, 1994.
    34. May, G. S., Forbes, H. C., Hussain, N., and Charles, A., “Modeling Component Placement Errors in Surface Mount Technology Using Neural Networks,” IEEE Transactions on Components, Packaging, and Manufacturing Technology- Part C, Vol. 21, No. 1, January, 1998.
    35. Montgomery, D. C., Introduction to Statistical Quality Control, New York, 1996.
    36. Morris, J.R. and Wojcik, T., “Stencil Printing of Solder Paste for Fine-Pitch Surface Mount Assembly,” IEEE Transactions on Components, Hybrids, and Manufacturing Technology, Vol. 14, No. 3, pp. 560-566, 1991.
    37. Nadi, F., Agogino, A. and Hodges, D., “Use of Influence Diagrams and Neural Networks in Modeling Semiconductor Manufacturing Processes,” IEEE Transactions on Semiconductor Manufacturing, Vol. 4, pp.124-129, 1991.
    38. Owen, M., “2-D and 3-D Inspections Catch Solder-Paste Problems,” Test & Measurement World, February, 2000.
    39. Pan, J., Tonkay, G. L., Storer, R. H., Sallade, R. M., Leandri, D. J., “Critical Variables of Solder Paste Stencil Printing for Micro-BGA and Fine Pitch QFP,” IEEE/CPMT International Electronics Manufacturing Technology Symposium, pp.94-101, 1999.
    40. Pan, J., and Tonkay, G. L., “A Study of the Aperture filling Process in Solder Paste Stencil Printing,” Proceedings of the 1999 ASME International Mechanical Engineering Congress and Exposition, Nashville, Tennessee, November 14-19, pp.75-82, 1999.
    41. Pan, J., Tonkay, G. L., Storer, R. H., Sallade, R. M., Leandri, D. J., “Experimental Study of Solder Paste Stencil Printing for Fine Pitch and Ultra-Fine Pitch QFP and BGA,” Proceedings of 13th Conference with Industry: Competing in a Global Manufacturing Environment, Lehigh University, Bethlehem, PA, USA, May 24 & 25, pp.59-66, 1999.
    42. Pan, J., “Modeling and process optimization of solder paste stencil printing for Micro-BGA and fine pitch surface mount assembly,” Ph.D. dissertation, Lehigh university, 2000.
    43. Ries, B., “3-D Post-Printing Inspection,” Circuits Assembly, June, pp.40-48, 1998.
    44. Sabuncuoglu, I., and Gurgun, B., “A Neural Network Model for Scheduling Problems,” European Journal of Operation Research, Vol. 93, No. 2, pp.288-299, 1996.
    45. Sahay, C., Head, L. M., Shereen, R. Dujari, P., Constable, J. H., and Westby, G., “Study of Print Release Process in Solder Paste Printing,” Journal of Electronic Packaging, Vol. 117, pp.230-234, 1995.
    46. Sette, S., Boullart, L., and Langenhove, L., “Optimising a Production Process by a Neural Network/Genetic Algorithm Approach,” Journal of Engineering Application in Artificial Intelligence, Vol. 9, No. 6, pp.681-689, 1996.
    47. Shang, J. S., and Tadikamalla, P. R., “Output Maximization of a CIM System：Simulation and Statistical Approach,” International Journal of Production Research, Vol. 31, No. 1, pp.19-41, 1993.
    48. Soto, H. P., “Study of the thermal behavior of a printed circuit board during the reflow process inside a surface mount technology oven,” Master thesis, University of Puerto Rico, 1998.
    49. Tsai, T., “Solder Defect Analysis,” Technical Report, Kaohsiung, Taiwan, 2000.
    50. Tsai, T., Liu, S. and Yang, T., “A SMT Reflow Soldering Diagnosis System Using Neurofuzzy Approach,” International Journal of Fuzzy Systems, Vol. 3, No. 4, December, 2001.
    51. Twomey, J. M., Smith, A. E., and Redfern, M. S., “A Predictive Model for Slip Resistance Using Artificial Neural Networks,” IIE Transactions, Vol. 27, pp.374-381, 1995.
    52. Vaithyanathan, S. and Ignizio, J. P., “A Stochastic Neural Network for Resource Constrained Scheduling,” Computers and Operations Research, Vol. 19, pp.241-254, 1992.
    53. Wada, Y., and Kawato, M., “Estimation of Generalization Capability by Combination of New Information Criterion and Cross Validation,” Proceedings of International Conference Neural Networks, Vol. 2, pp.1-6, 1991.
    54. Wang, Q., Sun, X., Golden, B., DeSilets, L., Wasil, E., Luco, S., and Peck, A., “A Neural Network Model for the Wire Bonding Process,” Computers Operations Research, Vol. 20, No. 8, pp.879-888, 1993.
    55. Wang, S., “An Insight into the Standard Back-propagation Neural Network Model for Regression Analysis,” International Journal of Management Science, Vol. 26, No. 1, pp.133-140, 1998.
    56. Whitmore, Mark; Mackay, Colin, and Hobby, Alan, “Plastic Stencils for Bottom-Side Chip Attach,” Electronic Packaging & Production, Vol. 37, No. 13, pp.68-72, 1997.
    57. Williams, R. J., and Zipser, D., “A Learning Algorithm for Continually Running Fully Recurrent Neural Networks,” Neural Computation, Vol. 1, pp.271-279, 1989.
    58. Wilson, T. and Bloomfield, D., “An Optimistic Outlook for Ultra Fine Pitch-Part I,” Electronic Production, February, pp. 39-42, 1995.
    59. Wray, B. A., Rakes, T. R., and Rees, L. P., “Neural Network Identification of Critical Factors in a Dynamic Just-in-time Kanban Environment,” Journal of Intelligence Manufacturing, Vol. 8, No. 2, pp.83-96, 1997.
    60. Xiao, M., Lawless, K. J., and Lee, N. C., “Prospects of Solder Paste in the Ultra Fine Pitch Era,” Soldering & Surface Mount Technology, No. 15, pp.4-13, 1993.
    61. Yang, T., Su C., and Feng, Y., “In Search of a Product Mix for Semiconductor Wafer Fabrication Facilities by a Combined Simulation/Neural Network Approach,” International Journal of Industrial Engineering, Vol. 8, No. 2, pp.142-149, 2001.
    62. Zhang, H. C., and Huang, S. H., “Applications of Neural Networks in Manufacturing,” International Journal of Production Research, Vol. 33, No. 3, pp.705-728, 1995.
    63. “Neural Computing：A Technology Handbook for Neural Works Professional II/ Plus,” Neural Ware, August, 2000.

    下載圖示 校內：立即公開
    校外：2002-06-24公開
    QR CODE