臺灣博碩士論文加值系統

　　本研究主要是應用倒傳遞類神經網路，做為錫球外形瑕疵判斷依據，提升外形檢測的準確率，同時開發二維BGA光學檢測系統，並以Visual Basic配合Halcon影像處理函式庫做為開發工具。檢測系統能在BGA基板偏移及任意角度偏轉的情形下，正確量測錫球外型尺寸與位置並以此分類錫球之瑕疵，檢測瑕疵項目包含：球偏移、多球、球過大、球過小、球變形、球相連以及缺球。
　　在自動檢測系統的研究方法與處理程序方面，首先影像經由前處理及次像素逼近錫球邊緣，獲得精確的錫球座標位置、近似橢圓長短軸大小、緊密度(Compactness)、錫球半徑、BGA基板偏轉角度等資訊。藉由條件法則判斷錫球尺寸及位置瑕疵，以及使用倒傳遞類神經網路來辨識及分類外形瑕疵之錫球。實驗結果證明倒傳遞類神經網路能正確的分類出錫球外形瑕疵，尤其是對一般最難辨識的球變形與球相連的缺陷，達到自動檢測及高效率辨識能力的需求。

　　This study is mainly utilizing Back-Propagation Neural Network technology to identify the shape of defective tin ball and to promote the accuracy of the inspection. By developing two dimensional BGA optical inspecting system, incorporate with Halcon which developed by Visual Basic as developing tool of function database for image process. Inspecting system is capable of detecting the shape of tin ball and its location precisely and classifying its quality under the condition of BGA board offsetting and rotating at any angle. Inspecting items include, ball offset, ball presence, over size, under size, ball deformation, ball bridging and ball absence.
　　For the study and processing procedure developments of the automatic inspecting system, image is processed by preprocess and sub-pixel basing on its grey value to identify the edge accuracy in order to acquire the coordinate of the tin ball precisely, the nearly ellipse axis scale, compactness, radius of tin ball, BGA board bias angle relevant information. Based on the predefined criteria, defines the dimension and location defects of the tin ball and utilizes Back-Propagation Neural Network technology identifying and classifying the shape defects of the tin ball. Experiments within this study prove that Back-Propagation Neural Network technology can correctly identify and classify the shape defects of the tin ball which also can achieve and contribute the requirements for the automatic inspection and high efficiency of identification capabilities.

中文摘要....................................................i
英文摘要....................................................ii
誌謝........................................................iv
目錄........................................................v
表目錄......................................................viii
圖目錄......................................................ix
第一章 緒論.................................................1
1.1 前言....................................................1
1.2 研究動機與目的..........................................2
1.3 文獻回顧................................................3
1.4 研究方法與步驟..........................................7
1.5 論文架構................................................8
第二章 BGA構裝技術介紹......................................9
2.1 BGA構裝的發展...........................................9
2.2 BGA構裝分類.............................................12
2.3 BGA構裝流程.............................................14
2.4 BGA錫球檢測項目.........................................15
第三章 BGA檢測之影像處理技術................................16
3.1 影像校正................................................16
3.2 影像分割................................................17
3.2.1 Mode Method...........................................18
3.2.2 P-tile Method.........................................19
3.2.3 疊代法(Iterative Method)..............................19
3.2.4 類間變異數法(Within-Class Method).....................20
3.3 區塊分析................................................22
3.4 次像素邊緣偵測..........................................23
3.4.1 空間矩量法............................................24
3.5 最佳橢圓逼近............................................25
3.6 IC偏轉修正..............................................28
3.6.1 中心位置與旋轉角度計算................................28
3.6.2 座標轉換..............................................30
第四章 類神經網路介紹.......................................31
4.1 類神經網路發展..........................................31
4.2 人工神經元..............................................31
4.3 倒傳遞類神經網路........................................34
第五章 系統建立與實驗結果...................................36
5.1 系統整合................................................36
5.1.1 硬體架構..............................................36
5.1.2 軟體架構..............................................37
5.2 環境光源................................................38
5.3 CCD參數校正.............................................40
5.4 錫球外型瑕疵分類系統建立................................42
5.4.1 倒傳遞類神經網路架構..................................42
5.4.2 訓練樣本參數建立......................................44
5.4.3 網路參數訓練..........................................46
5.5 實驗結果................................................50
5.5.1 外形瑕疵分類方法比較..................................51
5.5.2 BGA錫球瑕疵檢測.......................................54
第六章 結論與未來展望.......................................59
6.1 結論....................................................59
6.2 未來展望................................................60
參考文獻....................................................61

[1]張志誠，模糊神經網路於半導體BGA影像辨識系統的製作，碩士論文，元智大學，工業工程研究所，1998。
[2]梁有燈，機器視覺在BGA銲球尺寸量測上之應用，碩士論文，中華大學，機械與航太工程研究所，1999。
[3]許淳熙，BGA線上檢測系統之開發，碩士論文，國立交通大學，機械工程系研究所，2000。
[4]陳佳良，線上BGA影像檢測之探討與改進，碩士論文，國立交通大學，機械工程系研究所，2001。
[5]鄭森勵，BGA檢測系統之發展與評估，碩士論文，國立臺灣大學，機械工程學研究所，2002。
[6]林錫寬、張上淵，應用電腦視覺與類神經網路於BGA檢測系統，2002 PCB 製造與管理技術研討會，中壢，第99-106頁，2002。
[7]周明孝，具任意角度偏轉之BGA瑕疵檢測系統開發研究，碩士論文，國立台灣科技大學，自動化及控制研究所，2003。
[8]蔡明忠、陳維翰，應用倒傳遞類神經網路於BGA 瑕疵檢測系統，AOI Forum & Show 2005，新竹，第249-255頁，2005。
[9]陳詩豐、莊豐閣，利用人工智慧之SVM法則於BGA錫球檢測，AOI Forum & Show 2005，新竹，第341-351頁，2005。
[10]P. Kim, S. Rhee, "Three-Dimensional Inspection of Ball Grid Array Using laser Vision System," IEEE Transactions on Electronics Packaging Manufacturing, Vol.22, pp.151-155, 1999.
[11]M. Yu, G.-Y. Jiang, S.-L. He, B.-K. Yu, R.-D. Fu, "New Approach to Vision-Based BGA Package Inspection," Proceedings of 2002 International Conference on Machine Learning and Cybernetics, Beijing, China, Vol.2, pp.1107-1110, 2002.
[12]M. Zhao, N. Guo and W. Chen, "A Novel Frequency-Shift Moiré Fringe Method for 3D Inspection of BGA Packaging," JSME International Journal, Series A: Solid Mechanics and Material Engineering, Vol.45, pp.240-244, 2002.
[13]C.-W. Ruo, C.-L. Shih, "Locating and Checking of A BGA Pin's Position Using Gray Level," Proceedings of the 2003 IEEE International Conference on Robotics & Automation, Taipei, Taiwan, Vol.3, pp.3523-3528, 2003.
[14]Cao Qixin, Fu Zhuang, Xia Nianjiong, F.L. Lewis, "A Binocular Machine Vision System for Ball Grid Array Package Inspection," Assembly Automation, Vol.25, No.3, pp.217-222, 2005.
[15]鍾文仁、陳佑任，IC封裝製程與CAE應用，全華科技，2005。
[16]N. C. Lee, "Reflow Soldering Processes and Troubleshooting SMT, BGA, CSP and Flip Chip Technologies," Newnes, pp.189-198, 2001.
[17]"Joint Electron Device Engineering Council," http://www.jedec.org/.
[18]T. W. Ridler, S. Calvard, "Picture Thresholding Using An Iterative Selection Method," IEEE Transactions on Systems, Man and Cybernetics, Vol.8, No.8, pp.630-632, 1978.
[19]N. Otsu, "A Threshold Selection Method From Gray-Level Histograms," IEEE Transaction on System, Man, and Cybernetics, Vol.9, No.1, pp.62-66, 1979.
[20]E. P. Lyvers, O. R. Mitchell, M. L. Akey, A. P. Reeves, "Subpixel Measurements Using A Moment-Based Edge Operator," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.11, No.12, pp.1293-1309, 1989.
[21]W. S. McCulloch, W. Pitts, "A Logical Calculus of The Ideas Immanent in Nervous Activity," Bulletin of Mathematical Biophysics, Vol.5, pp.115-133, 1943.
[22]D. O. Hebb, "The Organization of Behavior : A Neuropsychological Theory," Wiley, New York, 1949.
[23]F. Rosenblatt, "The Perceptron : A Probabilistic Model for Information Storage and Organization in The Brain," Psychological Review, Vol.65, pp.386-408, 1958.
[24]B. Widrow, M. E. Hoff, Jr., "Adaptive Switchang Circuits," IRE WESCON Convention Record, pp.96-104, 1960.
[25]D. E. Rumelhart, G. E. Hinton, R. J. Williams, "Learning Internal Representations By Error Propagation," in Paralleled Distributed Processing, Vol.1, pp.318-362, Cambridge, MA : MIT Press, 1986.
[26]張斐章，張麗秋，黃浩倫，類神經網路理論與實務，臺北市，東華書局，2003。
[27]葉怡成，類神經網路模式應用與實作，台北市，儒林，1999。