研究生: |
吳佳祐 Jia-You Wu |
---|---|
論文名稱: |
以深度學習辨識之加工特徵進行自動化製程規劃 Automated Process Planning Using Machining Features Recognized from Deep Learning Models |
指導教授: |
林清安
Ching-An Lin |
口試委員: |
張復瑜
Fuh-Yu Chang 小林博仁 Hirohito Kobayashi |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 機械工程系 Department of Mechanical Engineering |
論文出版年: | 2023 |
畢業學年度: | 111 |
語文別: | 中文 |
論文頁數: | 136 |
中文關鍵詞: | 電腦輔助製程規劃 、特徵辨認 、深度學習 、刀具加工路徑 、CAD/CAM |
外文關鍵詞: | Computer aided process planning, Feature recognition, Deep learning, Cutting tool path, CAD/CAM |
相關次數: | 點閱:264 下載:14 |
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 |
製程規劃是機械加工的一項重要工作,目前商用的電腦輔助製造軟體雖然具備完善功能,但需要擁有專業製程知識與加工經驗的人員進行設定,且繁瑣的操作流程使得此類軟體的操作效率低且入門門檻高,因此本論文著眼於自動化製程規劃系統之開發,首先使用深度學習技術自動化由3D幾何模型辨識出五種類別的加工特徵:圓孔特徵、口袋特徵、階梯特徵、盲槽特徵與通槽特徵,接著針對不同的加工特徵選用適當之加工刀具,然後安排合理之加工順序與加工工法,最後自動化產生刀具加工路徑。
本論文除了詳述如何使用經過訓練的深度學習模型進行加工特徵辨識、如何分析加工特徵之幾何資訊進行刀具選用、如何設定加工前處理及如何安排特徵之加工順序與加工工法,也透過Siemens NX的二次開發工具NXOpen建立一套自動化產生加工刀具路徑的電腦系統,並利用兩個3D CAD模型做為實例,驗證所開發系統的實用性。研究結果顯示此系統適用於多種加工特徵,能對特徵產生正確且合理的加工路徑,並大幅節省軟體操作時間。
Process planning plays a crucial role in mechanical machining. While commercial computer-aided manufacturing software offers comprehensive functionalities, it requires individuals with professional process knowledge and machining experience for proper configuration. Additionally, the software's complex operational procedures result in low efficiency and high entry barriers. Therefore, this thesis focuses on the development of an automated process planning system. Initially, deep learning techniques are employed to automatically recognize five types of machining features from 3D geometric models: hole features, pocket features, step features, blind slot features, and through slot features. Subsequently, suitable machining tools are selected for different machining features, followed by organizing appropriate machining sequences and methods. Ultimately, the system automatically generates tool paths for machining.
In addition to proposing the utilization of trained deep learning models for feature recognition, the thesis analyzes geometric information for tool selection, establishes preprocessing procedures, and arranges machining sequences and methods. To accomplish this, the thesis leverages NXOpen, using the application programming interface of Siemens NX to establish an automatic tool path generation system. Two 3D CAD models are utilized as examples to validate the practicality of the developed system. The research demonstrates that the system adapts well to various machining features, is capable of generating accurate and logical machining paths, and significantly reduces software operation time.
[1]Yusof, Y. and Latif, K., “Survey on computer-aided process planning,” International Journal of Advanced Manufacturing Technology, Vol. 75, pp. 77-89, 2014.
[2]Al-wswasi, M., Ivanov, A. and Makatsoris, H., “A survey on smart automated computer-aided process planning (ACAPP) techniques,” International Journal of Advanced Manufacturing Technology, Vol. 97, pp. 809-832, 2018.
[3]Isnaini, M.M. and Shirase, K., “Review of computer-aided process planning systems for machining operation - future development of a computer-aided process planning system,” International Journal of Automation Technology, Vol. 8, No. 3, pp. 317-332, 2014.
[4]Shi, Y., Zhang, Y., Xia, K. and Harik, R., “A critical review of feature recognition techniques,” Computer-Aided Design and Applications, Vol. 17, No. 5, pp. 861-899, 2020.
[5]Joshi, S. and Chang, T.C., “Graph-based heuristics for recognition of machined features from a 3D solid model,” Computer-Aided Design, Vol. 20, No. 2, pp. 58-66, 1988.
[6]Kim, Y.S., “Recognition of form features using convex decomposition,” Computer-Aided Design, Vol. 24, No. 9, pp. 461-476, 1992.
[7]Shah, J.J., Anderson, D., Kim, Y.S. and Joshi, S., “A discourse on geometric feature recognition from CAD models,” Journal of Computing and Information Science in Engineering, Vol. 1, No. 1, pp. 41-51, 2000.
[8]Zhang, Y., Zhang, Y., He, K., Li, D., Xu, X. and Gong, Y., “Intelligent feature recognition for STEP-NC-compliant manufacturing based on artificial bee colony algorithm and back propagation neural network,” Journal of Manufacturing Systems, Vol. 62, pp. 792-799, 2022.
[9]Zhang, Z., Jaiswal, P. and Rai, R., “FeatureNet: Machining feature recognition based on 3D Convolution Neural Network,” Computer-Aided Design and Applications, Vol. 101, pp. 12-22, 2018.
[10]Shi, P., Qi, Q., Qin, Y., Scott, P.J. and Jiang X., “A novel learning-based feature recognition method using multiple sectional view representation,” Journal of Intelligent Manufacturing, Vol. 31, pp. 1291-1309, 2020.
[11]陳正岳,「以特徵編碼之深度學習進行加工特徵辨識」,碩士論文, 臺灣科技大學機械工程系,台北市,2022。
[12]Rui, H. and Shusheng, Z., “An effective adaptive dynamic evolution computing approach of roughing process for part with complex pockets,” International Journal of Advanced Manufacturing Technology, Vol. 96, pp. 3279-3293, 2018.
[13]Xu, C., Zhang, S., Huang, B., Li, X. and Huang, R., “NC process reuse oriented effective subpart retrieval approach of 3D CAD models,” Computers in Industry, Vol. 90, pp. 1-16, 2017.
[14]Huang, R., Jiang, J., Huang, B. and Zhang, S., “Multilevel structured NC machining process model based on dynamic machining feature for process reuse.” International Journal of Advanced Manufacturing Technology, Vol. 104, pp. 2045-2060, 2019.
[15]Xu, C., Zhang, S., Huang, R., Huang, B. and Li, X., “NC process reuse-oriented flexible process planning optimization approach for prismatic parts.” International Journal of Advanced Manufacturing Technology, Vol. 87, pp. 329-351, 2016.
[16]張書庭,「木工樑柱加工之自動化製程規劃」,碩士論文, 臺灣科技大學機械工程系,台北市,2021。
[17]Hua, G.R., Zhou, X.H. and Ruan, X.Y., “GA-based synthesis approach for machining scheme selection and operation sequencing optimization for prismatic parts,” International Journal of Advanced Manufacturing Technology, Vol. 33, pp. 594-603, 2006.
[18]Salehi, M. and Tavakkoli-Moghaddam, R., “Application of genetic algorithm to computer-aided process planning in preliminary and detailed planning,” Engineering Applications of Artificial Intelligence, Vol. 22, pp. 1179-1187, 2009.
[19]Guo, Y.W., Mileham, A.R., Owen, G.W., Maropoulos, P.G. and Li, W.D., “Operation sequencing optimization for five-axis prismatic parts using a particle swarm optimization approach,” Proceedings of the Institution of Mechanical Engineers Part, B: Journal of Engineering Manufacture, Vol. 223, pp. 485-497, 2009.
[20]Guo, Y.W., Mileham, A.R., Owen, G.W. and Li, W.D., “Operation sequencing optimization using a particle swarm optimization approach,” Proceedings of the Institution of Mechanical Engineers Part, B: Journal of Engineering Manufacture, Vol. 220, pp. 1945-1958, 2006.
[21]Hu, Q., Qiao, L. and Peng, G., “An ant colony approach to operation sequencing optimization in process planning,” Proceedings of the Institution of Mechanical Engineers Part, B: Journal of Engineering Manufacture, Vol. 231, pp. 470-489, 2016.
[22]Gopala Krishna, A. and Mallikarjuna Rao, K., “Optimisation of operations sequence in CAPP using an ant colony algorithm,” International Journal of Advanced Manufacturing Technology, Vol. 29, pp. 159-164, 2006.
[23]NX Open, Siemens PLM Software Inc., Plano, TX, USA., 2014.