簡易檢索 / 詳目顯示

研究生: 劉國偉
Guo-Wei Liu
論文名稱: 基於GigE視覺之印刷電路板自動光學檢測系統
An Automatic Optical Inspection System with GigE Vision for Print Circuit Board
指導教授: 蔡超人
Chau-Ren Tsai
口試委員: 蘇順豐
Shun-Feng Su
郭景明
Jing-Ming Guo
王乃堅
Nai-Jian Wang
李祖添
none
學位類別: 碩士
Master
系所名稱: 電資學院 - 電機工程系
Department of Electrical Engineering
論文出版年: 2012
畢業學年度: 100
語文別: 中文
論文頁數: 118
中文關鍵詞: 高解析度自動光學檢測數位信號處理器
外文關鍵詞: AOI, High-Resolution, DSP
相關次數: 點閱:324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
  • 由於自動化的趨勢,全球都在致力發展取代人力的設備,進而增進產線的效能和降低開發成本。目前許多家廠商發展出非常多功能的自動光學檢測(Automated Optical Inspection, AOI)設備,但由於設備皆採用工業等級的電腦當作主要運作系統,導致成本居高不下、機器體積龐大且消耗功率過大不符合節約能源的趨勢,廠商也極力地找出可能解決的方法。隨著數位信號處理器(Digital Signal Processor, DSP)的發展,擁有處理速度更快、體積更小、功能完善且低成本的DSP產品,漸漸地取代高成本的工業電腦設備,而DSP所建構的系統在大量且複雜的運算處理上有著高準確度及高效能的表現,尤其「低功率」能達到節約能源的效果。本研究主要目標是利用GigE高解析度攝影機,建立起獨立的自動光學檢測系統,後端連接DM6437開發平台,將攝影機所擷取到的影像畫面傳送到DSP進行影像處理,分析及辨別電路板上的瑕疵,經由乙太網路,提供檢測結果至人機介面,讓使用者更快速地獲取得電路板上的資訊。


    Due to the trend of automation, people throughout the world have been concentrating on creating the equipment to replace human resource, and further increase the efficiency of production lines and reduce the cost. Manufacturers have developed a variety of equipments for Automated Optical Inspection (AOI). However, most of the facilities use industrial PCs as the main operating system, which lead to high costs, huge volume of machine, and high power consumption. In order to achieve energy savings, manufacturers are giving efforts to find out solutions for the problem. As Digital Signal Processor (DSP) become faster, smaller, more capable and low-cost, they gradually replace the usage of high-cost industrial computer equipments. Additionally, DSP-based System can perform large complex operation processing more accurately and efficiently, especially to achieve energy savings with its "low power." The purpose of this study is to use high-resolution GigE Vision cameras to set up independent AOI systems. This system will combine DM6437 Evaluation Module with GigE camera to transfer raw image data to DSP for image processing as well as to analyze and identify any detected flaws. Through the network , the analyze results will be sent to the human-machine interface so users can receive the information on PCB quickly.

    摘 要 I Abstract II 致謝 III 目 錄 IV 圖 索 引 VII 表 索 引 XIV 第一章 緒論 1 1.1 研究動機與目的 1 1.2 研究方法 2 1.3 論文架構 3 第二章 系統架構 5 2.1 影像擷取程序 6 2.2 定位點計算程序 8 2.3 樣板建立模式 9 2.4 瑕疵檢測模式 11 2.5 網路傳輸程序 12 2.6 硬體規格與配置 13 第三章 GigE攝影機的數位影像擷取 18 3.1 建立與攝影機連線 19 3.1.1 GigE Vision的網路模型 19 3.1.2 GVCP攝影機控制封包 21 3.1.3 GVSP影像資料封包 24 3.1.4 攝影機連線方法 26 3.2 攝影機影像品質調整 29 3.2.1 影像品質之影響 30 3.2.2 攝影機影像品質調整方法 32 3.3 攝影機影像傳輸 34 3.3.1 影像格式與參數設定 35 3.3.2 使用EDMA排序影像資料 37 3.3.3 Ping-Pong Buffer架構 40 3.3.4 影像封包重傳方法 41 第四章 定位點計算與樣板建立 43 4.1 電路板定位點計算 43 4.1.1 YCr二值化 44 4.1.2 形態學處理 46 4.1.3 定位點計算 48 4.2 線路樣板建立 50 4.2.1 色彩空間比較 51 4.2.2 HSV轉換查表法[19] 53 4.2.3 建立顏色資訊 55 4.2.4 色彩濾除 58 4.3 焊墊樣板建立 59 4.3.1 灰階門檻值選取 59 4.3.2 焊墊影像萃取方法 63 4.4 雜訊處理 64 第五章 電路板瑕疵檢測 66 5.1 印刷電路板檢測技術 66 5.2 樣板比對 68 5.3 邊緣雜訊濾除 70 5.4 瑕疵形態分類 72 5.4.1 缺陷區塊連通標記法 72 5.4.2 缺陷區塊選取 75 5.4.3 分類法則[7] 77 第六章 DM6437周邊模組應用 80 6.1 I2C EEPROM 80 6.1.1 I2C工作原理 80 6.1.2 I2C EEPROM資料儲存 82 6.2 Flash燒錄 84 6.2.1 Flash操作方式 86 6.2.2 Flash燒錄實現 87 第七章 系統實現與效能測試 92 7.1 系統網路傳輸架構 92 7.1.1 網路資料傳輸流程 92 7.1.2 人機介面介紹 96 7.2 系統實現 98 7.3 系統執行效能 106 7.4 檢測誤差 108 第八章 結論 110 8.1 研究成果 110 8.2 未來發展 113 參 考 文 獻 114

    [1] Texas Instruments Inc., TMS320DM643x DMP Enhanced Direct Memory Access (EDMA3) Controller, March 2008.
    [2] J. P. Serra, “Image Analysis and Mathematical Morphology,” Academic Press, pp. 155-130, 1982.
    [3] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Prentice-Hall, New Jersey, pp. 116-123, 2002.
    [4] N. Otsu, “A Threshold Selection Method from Gray-level Histograms,” IEEE Transactions on Systems, Man and Cybernetics, Vol. 9, No. 1, pp. 377-393, 1979.
    [5] M. Moganti, E. Fikert, H. D. Cihan and T. Shou, “Automatic PCB Algorithms: A Survey,” Computer Vision and Image Understanding, Vol. 63, No. 2, pp. 287-313, 1996.
    [6] W. A. Bentley, “The Inspection: An Automatic Optical Printed Circuit Board (PCB) Inspection,” In Proceedings of the Society of Photo-Optical Instrumentation Engineers, Vol. 201, pp. 37-47, 1979.
    [7] W. Y. Wu, M. J. Wang and C. M. Liu, “Automated Inspection of Printed Circuit Boards Through Machine Vision,” Computers in Industry, Vol. 28, No. 2, pp. 103-111, 1996.
    [8] Automated Imaging Association, GigE Vision 2.0 Specification, November 2011.
    [9] Basler Vision Technologies, Installation and Setup Guide for Cameras Used with Basler’s Pylon API, February 2008.
    [10] U. Lamping, R. Sharpe, and E. Warnicke, Wireshark User's Guide : for Wireshark 1.7, 2011.
    [11] Texas Instruments Inc., TMS320C6000 TCP/IP Network Developer’s Kit User’s Guide, June 2003.
    [12] Basler Vision Technologies, The Elements of GigE Vision, May 2007.
    [13] 李慶銘,“即時影音教學傳播系統的實現,”國立台灣科技大學電機工程系碩士論文, pp. 30-38, 2011.
    [14] Basler Vision Technologies, User’s Manual for GigE Camera, July 2011.
    [15] Basler Vision Technologies, Controlling Packet Transmission Timing with the Interpacket and Frame Transmission Delays on Basler GigE Vision Cameras Application Notes, July 2008.
    [16] R. O. Duda and P. E. Hart, “Use of the Hough Transformation to Detect Lines and Curves in Pictures,” Communications of the Association for Computing Machinery, Vol. 15, No. 1, pp. 11-15, 1972.
    [17] T. C. Chen and K. L. Chung, “An Efficient Randomized Algorithm for Detecting Circles,” Computer Vision and Image Understanding, Vol. 63, No. 83, pp. 172-191, 2001.
    [18] Y. Wand and B. Yuan, “A Novel Approach for Human Face Detection from Color Images under Complex Background,” Pattern Recognition, Vol. 34, No. 10, pp.1983-1992, 2011.
    [19] 劉一方, 劉兆廣, 王婭芳, 何晨, 楊陽,“一種基於定點DSP的YCbCr到HSV的快速轉換算法,”計算機應用研究, Vol. 29, No. 2, pp.741-743, 2012.
    [20] 林裕超,“遠端影像監控之立體視覺目標物追蹤與量測系統,”國立台灣科技大學電機工程系碩士論文, pp. 35-43, 2011.
    [21] D. Hear. and M. P. Baker, Computer Graphics, 2nd Edition, Prentice-Hall, New York, pp. 49-81, 1994.
    [22] 郭振鵬,“以系統單晶片架構做印刷電路板銅箔缺陷檢測系統之設計,”國立成功大學電機工程系碩士論文, pp. 3-11, 2004.
    [23] A. Albiol and J. Serra, “Morphological Image Enlargements,” Journal of Visual Communication and Image Representation, Vol. 8, No. 4, pp. 367-383, 1997.
    [24] C. S. Chuah and J. J. Leou, “An Adaptive Image Interpolation Algorithm for Image/Video Processing,” Pattern Recognition, Vol. 34, No.12, pp. 2383-2393, 2001.
    [25] Texas Instruments Inc., TMS320DM643x DMP Inter-Integrated Circuit (I2C) Peripheral User’s Guide, March 2011.
    [26] Catalyst Semiconductor Inc., CAT24C256 256-Kb I2C CMOS Serial EEPROM, February 2006.
    [27] Spectrum Digital Inc., TMS320DM6437 Evaluation Module Technical Reference, December 2006.
    [28] Spansion Advance Information, S29GLxxxN MirrorBitTM Flash Family, October 2003.
    [29] Texas Instruments Inc., Using the TMS320DM643x Bootloader, May 2008.

    QR CODE