銲接技術在工業界一直佔有一席之地，已被廣泛地應用於許多相關產業。在執行焊接動作前，需要規劃銲接路徑以及挑選銲接方式，並將欲銲接之零件移動至工作區域，前置作業相當的繁瑣。隨著自動化技術不斷地提升，以往需要透過人工處理之作業，逐漸可由機械取代之，過往的手工銲接技術也已逐步邁向自動化。
本論文提出透過零件之3D CAD模型來分析其銲接點與銲接路徑，並使用影像處理技術獲取欲銲接之零件擺放於工作台上的實際方位，進而減少銲接動作之前置作業。本論文之研究主要分為三個部份：(1)電腦輔助銲接路經規劃：利用3D CAD軟體分析零件的幾何（點、線、面），並採用佈點方式取得3D CAD模型之銲接點分布，接著透過演算法求出銲接路徑；(2)自動判定零件於工作台上之方位：將零件實物擺放於工作台，利用相機取得零件影像，透過影像處理技術計算出零件之實際方位；(3)使用機械手臂進行銲接動作之模擬。
本論文除詳述如何以3D CAD模型求取銲接路徑以及影像處理技術求取零件方位之外，並以滑鼠模型及輪胎模具模型為案例，驗證所開發系統之實用性。

Welding technology has always taken a place in industry and has been widely used in many companies. Before executing the welding operations, it is necessary to manually plan the welding path and select the welding method, which is quite time-consuming. With the continuous improvement of automation technology, operations that previously require manual processing can be gradually replaced by machinery, and the past manual welding technology has gradually moved towards automation.
This thesis aims to generate the welding path from the 3D CAD model of the part to be processed, and use image processing techniques to obtain the actual orientation of the part placed on a working table, thereby reducing the setup time before welding. The research of this thesis is mainly divided into three parts: (1) computer aided path planning: using a 3D CAD software to analyze the geometry of the part (points, curves and surfaces) to obtain the distribution of welding points, (2) automatic determination of the part’s orientation: placing the part on a working table, using a camera to obtain the image of the part, and then calculating the actual orientation of the part through image processing techniques, and (3) simulation of the welding path by a manipulator.
Besides elaborating on the algorithm of generating welding path from a 3D CAD model and determining the part’s orientation on a working table, this thesis also uses a computer mouse and a mold as examples to verify the practicability of the developed system.

[1] Parametric Technology Corporation (2015), “PTC Creo Parametric TOOLKIT 3.0 User’s Guide Datecode M030,” Needham, MA, USA.
[2] Hart, P.E., Nilsson, N.J. and Raphael, B. (1968), “A formal basis for the heuristic determination of minimum cost paths,” IEEE Transactions on Systems Science and Cybernetics, Vol. 4, Issue 2, pp. 100-107.
[3] Kim, J.S., Son, T.K., Cho, H.S. and Koh, K.I. (1995), “A robust method for vision-based seam tracking in robotic arc welding,” IEEE Proceedings of Tenth International Symposium on Intelligent Control, August 27-29, 1995, Monterey, CA, USA, pp. 363-368.
[4] Ding, D, Shen, C., Pan, Z., Cuiuri, D., Li, H. and Larkin, N. (2016), “Towards an automated robotic arc-welding-based additive manufacturing system from cad to finished part,” Computer-Aided Design, Vol. 73, pp. 66-75.
[5] Larkin, N., Short, A., Pan, Z. and Duin, S.V. (2018), “Automated programming for robotic welding,” Transactions on Intelligent Welding Manufacturing, Singapore, pp. 48-59.
[6] Ferreira, L.A., Figueira, Y.L., Iglesias, I.F. and Souto, M.A. (2017), “Offline CAD-based robot programming and welding parametrization of a flexible and adaptive robotic cell using enriched CAD/CAM system for shipbuilding,” International Conference on Flexible Automation and Intelligent Manufacturing, June 27-30, 2017, Modena, Italy.
[7] https://www.freecadweb.org/
[8] Jang, H.Y., Moradi, H., Hong, S., Lee, S. and Han, J. (2006), “Spatial reasoning for real-time robotic manipulation,” Proceedings of Institute of Electrical and Electronics Engineers International Conference on Intelligent Robots and Systems, October 9-15, 2006, Beijing, China.
[9] Alam, M.A., Ali, M.M., Musaddeque, A.S., Nawaj S. and Rahaman, M.A. (2014), “An algorithm to detect and identify defects of industrial pipes using image processing,” International Conference on Software, Knowledge, Information Management and Applications, December 18-20, 2014, Dhaka, Bangladesh.
[10] Kaur, B. and Jindal, S. (2014), “An implementation of feature extraction over medical images on open cv environment,” IEEE International Conference on Devices Circuits and Communications, September 12-13, 2014, Ranchi, India.
[11] Phadtare, L.K., Kushalnagar, R.S. and Cahill, N.D. (2012), “Detecting hand-palm orientation and hand shapes for sign language gesture recognition using 3D images,” IEEE Western New York Image Processing Workshop, November 11, 2012, Rochester, NY, USA.
[12] Belongie, S., Malik, J. and Puzicha, J. (2002), “Shape matching and object recognition using shape contexts,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 4, pp. 509-522.
[13] https://opencv.org/
[14] http://www.nde-ed.org/
[15] https://neon.epson-europe.com/robots/products/product.php?id=10884&content=547
[16] https://www.logitech.com/zh-tw/product/c922-pro-stream-webcam