成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	葉大維 Yeh, Ta-Wei
論文名稱：	以機械視覺檢測運轉中刀具 Turning Tool Monitoring using Machine Vision
指導教授：	連震杰 Lien, Jenn-Jier
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 資訊工程學系 Department of Computer Science and Information Engineering
論文出版年：	2016
畢業學年度：	104
語文別：	英文
論文頁數：	108
中文關鍵詞：	影像處理、刀具旋轉檢測、霍夫轉換、尺度不變特徵轉換、維納濾波
外文關鍵詞：	Image Processing, Tool Rotating Detection, Hough Transform, SIFT, Wiener filter
相關次數：	點閱：145 下載：4
分享至:	分享至facebook 分享至twitter

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

在目前工業4.0的時代，自動化乃為目前機械生產最基本的需求，本論文目的是建立一個可線上即時擷取動態旋轉刀具影像進行影像幾何分析，並實行量測刀具自動化功能，於檢測完畢後補正刀具的數據，再進行切削修整。本論文都是以擷取動態旋轉刀具來進行檢測，一開始分兩種為背光檢測與正光檢測，兩種檢測達到的功能不一樣。在背光檢測中，攝影機拍攝旋轉刀具，進行前處理，運用累加方法、二值化與ROI來找出刀具影像，接著由直線霍夫轉換偵測來去除刀具毛邊影響，並使用直線霍夫轉換的直線來找出刀徑量測、刀長量測、主軸傾斜檢測、斷刀檢測與磨耗檢測。在正光檢測中，我們使用SIFT來拼出整張刀具展開圖，運用這張刀具展開圖，期望可以做出一些刀具表面檢測。假設遇到高轉速使得刀具影像有模糊情況，可使用Wiener filter來復原。最後我們收集了一些實驗結果，未來期望可以將刀具動態檢測做的更完善，也期望在動態檢測刀具這方面也能有更進一步的發展。

In recent years of Industry 4.0, Automation machinery production is currently the most basic request. The purpose of this thesis is to establish an online real-time capturing dynamic rotating tool image for image geometric analysis, and implement measurement tool automation. After the completion of the detection, correcting tool data and repairing to cut. This thesis is to capture dynamic rotating tool to detect. Two types of back light detection and frontlight detection are not the same functions. In the backlight, the camera capture rotating tool , then using pre-processing and cumulative methods, binary and ROI (region of interest) to find tool images. Then using line Hough transform to deburr tool image and find the tool radius measurement, tool length measurement, the spindle inclination detectors, tool breakage detection and tool wear detection. In the frontlight, using SIFT to stitch expanded view of tool, then expect to make some tool surface detection.
If tool image has a blur situation from high speed rotation, using Wiener filter to recover. Finally, collecting some results and expect the tool detection to be better and further development in the future.

Content
摘要..................................................I
Abstract..................................................II
誌謝..................................................III
Table of Contents..................................................IV
List of Figures..................................................VII
List of Tables..................................................XII
Chapter 1. Introduction..................................................1
1 Motivation..................................................1
2 Related Work..................................................3
3 System Architecture..................................................5
4 Organization of Thesis..................................................8
Chapter 2. Introduction of Machine Equipment..................................................9
1 Introduction of Machine..................................................10
2 Introduction of Tool..................................................11
3 System Setup of Tool Detection..................................................13
4 Camera and Lens..................................................15
5 Light Selection..................................................19
6 Hardware..................................................21
Chapter 3. Back-Light-Based Turning Tool Monitoring..................................................22
1 Dynamic Backlight Capturing Mode..................................................23
2 Preprocessing..................................................26
3 Tool Boundary Deburring using Line Hough Transform..................................................31
3.1 Edge Detection using Canny Edge Detector..................................................32
3.2 Line Detection using Line Hough Transform..................................................35
3.3 Line Filter by Line Slope..................................................37
3.4 Find Tool Edge Boundary..................................................39
4 Functions of Turning Tool Wear Monitoring..................................................41
4.1 Tool Diameter Detection..................................................42
4.2 Tool Length Detection..................................................43
4.3 Spindle Deflection Detection..................................................44
4.4 Tool Breakage Detection..................................................45
4.5 Tool Wear Detection..................................................46
Chapter 4. Frontal-Light-Based Turning Tool Monitoring..................................................48
1 Dynamic Frontlight Capturing Mode..................................................49
2 SIFT-Based Panoramic Image of Turning Tool using Stitching..................................................51
2.1 Feature Extraction using SIFT..................................................53
2.2 Pair-wise Image Feature Matching using Kd-Tree..................................................54
2.3 Image Stitching using RANSAC for Local Geometric Registration..................................................55
2.4 Panoramic Image Stitching base on Multi-Band Blending..................................................56
3 Expected Functions of Turning Tool Wear Monitoring..................................................57
3.1 Analyzing Tool Flutes..................................................57
3.2 Surface Breakage Detection..................................................58
3.3 Wear Detection at the Tool Tip..................................................59
3.4 Helix Angle of Tool Detection..................................................60
4 Motion Deblurring of Turning Tool using Wiener Filter..................................................61
4.1 Find Blur Direction..................................................66
4.2 Find Blur Extent..................................................67
4.3 Wiener Filter Restoration..................................................70
Chapter 5. Experimental Results..................................................72
1 Data Collection..................................................73
2 Experiment of Back-Light Monitoring..................................................75
2.1 Back-Light Monitoring of Standard Rod..................................................76
2.2 Back-Light Monitoring of Original End Mill..................................................79
2.3 Back-Light Monitoring of Worn End Mill..................................................82
3 Experiment of Frontal-Light Monitoring using Wiener Filter..................................................83
4 Experiment of Additional PCB Tools..................................................86
Chapter 6. Conclusion and Future Works..................................................89
Reference..................................................91
                                    

[1] M.R. Banham and A.K. Katsaggelos, "Digital image restoration," IEEE Signal Processing Magazine, Vol. 14, No.2, pp. 24-41, 1997.
[2] J. Canny, "A computational approach to edge detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, No. 6, pp. 679-698, 1986.
[3] Z.K. Chen, "The study of easy-using detector for tool geometry," MSc thesis, National Formosa University, 2009.
[4] R.O. Duda, and P.E. Hart, "Use of the Hough transformation to detect lines and curves in pictures," Communications of the ACM 15.1: pp. 11-15, 1972.
[5] J.H. Friedman, J.L. Bentley, and R.A. Finkel, "An algorithm for finding best matches in logarithmic expected time," ACM Transactions on Mathematical Software, pp. 209-226, 1977.
[6] M. Fischler and R. Bolles, "Random sample consensus: a paradigm for model fitting applications to image analysis and automated cartography," Proceedings: Image Understanding Workshop, pp. 71-88, 1980.
[7] C.K. Huang, L.G. Wang, H.C. Tang and Y.S. Tarng, "Automatic laser inspection of outer diameter, run-out and taper of micro-drills," Journal of Materials Processing Technology, 171, pp. 306–313, 2006.
[8] C.Y. Hung, "An AOI system for microdrill and coated router measurement," MSc thesis, National Chiao Tung University, 2005.
[9] K.M. Hsu, "Router features measurement by using machine vision method," MSc thesis, National Chiao Tung University, 2008.
[10] P.V. Hough. "Method and means for recognizing complex patterns," U.S. Patent No. 3,069,654, Dec. 18, 1962.
[11] Y.C. Hsiao, "The research of miniaturized device profile measurement," MSc thesis, Tamkang University, 2004.
[12] D. Kundur and D. Hatzinakos, "Blind image deconvolution," IEEE Signal Processing Magazine, Vol. 13, No. 3, pp.43-64, 1996.
[13] J.H. Kim, D.K. Moon, D.W. Lee, J.S. Kim, M.C. Kang and K.H. Kim, "Tool wear measuring technique on the machine using CCD and exclusive jig," Journal of Materials Processing Technology, 130–131, pp. 668–674, 2002.
[14] S. Kurada and C. Bradley, "A machine vision system for tool wear assessment," Tribology International Vol. 30, No. 4, pp. 295-304, 1997.
[15] C.C. Liao, "The study of automatic measurement of end-mill," MSc thesis, Chung Hua University, 2011.
[16] C.S. Lin, "The study of on-line image inspection system for tool geometry in the five-axis tool grinder," MSc thesis, National Formosa University, 2011.
[17] C.Y. Lin, and S.H. Lai, "A novel blind motion deblurring algorithm for restoring an image with uniform motion blur," 18th IPPR Conference on Computer Vision, Graphics and Image Processing, 2005.
[18] D.G. Lowe, "Distinctive image features from scale-invariant keypoints," International Journal of Computer Vision, pp. 91-110, 2004.
[19] D.G. Lowe, "Object recognition from local scale-invariant features," Proceeding Seventh International, International Conference Computer Vision, pp. 1150-1157, 1999.
[20] H. Lim, K.C. Tan, and B.T.G. Tan, "Edge errors in inverse and Wiener filter restorations of motion-blurred images and their windowing treatment," CVGIP: Graph. Models Image Process, vol. 53, no. 2, pp. 186–195, 1991.
[21] N. Otsu, "A threshold selection method from gray-level histograms," IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-9, no. 1, pp. 62-66, January 1979.
[22] F. Wei, "Design and development of an automatic optical inspection machine for scrolls," MSc thesis, National Chiao Tung University, 2008.
[23] Y. Zhou, X.S. Zhou, S.W. Dai and Z.Y. Peng, "An improved motion-blurred image restoration algorithm," Computer Engineering & Science, Vol. 31, No. 10, 2009.

校內：2021-12-31公開
校外：不公開電子論文尚未授權公開，紙本請查館藏目錄

簡易檢索 / 詳目顯示

相關論文