請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/21053
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 李貫銘(Kuan-Ming Li) | |
dc.contributor.author | Yu-Xuan Tu | en |
dc.contributor.author | 凃俞亘 | zh_TW |
dc.date.accessioned | 2021-06-08T03:17:51Z | - |
dc.date.copyright | 2020-08-24 | |
dc.date.issued | 2020 | |
dc.date.submitted | 2020-08-19 | |
dc.identifier.citation | [1] Cho, D., Lee, S. and Chu, C., 1999. The state of machining process monitoring research in Korea. International Journal of Machine Tools and Manufacture, 39(11), pp.1697-1715. [2] Teti, R., 2015. Advanced IT Methods of Signal Processing and Decision Making for Zero Defect Manufacturing in Machining. Procedia CIRP, 28, pp.3-15. [3] 蔡乙陞, 銑削加工振動訊號應用於刀具磨耗監控之研究, 國立台灣大學機械工程學系碩士論文, 2019. [4] 黃耀賢, 主軸振動與聲射訊號於微銑刀具磨耗之應用研究, 國立中興大學機械工程學系碩士論文, 2010. [5] Ghosh, N., Ravi, Y., Patra, A., Mukhopadhyay, S., Paul, S., Mohanty, A. and Chattopadhyay, A., 2007. Estimation of tool wear during CNC milling using neural network-based sensor fusion. Mechanical Systems and Signal Processing, 21(1), pp.466-479. [6] J. T. Roth, and S. M. Pandit, 'Monitoring End-Mill Wear and Predicting Tool Failure Using Accelerometers,' Journal of Manufacturing Science and Engineering, 121(4), pp. 559-567, 1999. [7] P. Lister, and D. Dimla, “On-line metal cutting tool condition monitoring.: I: force and vibration analyses,” International Journal of Machine Tools and Manufacture, pp. 739-768, 2000. [8] Binsaeid, S., Asfour, S., Cho, S. and Onar, A., 2009. Machine ensemble approach for simultaneous detection of transient and gradual abnormalities in end milling using multisensor fusion. Journal of Materials Processing Technology, 209(10), pp.4728-4738. [9] M.S.H. Bhuiyan, I.A. Choudhury, Y. Nukman, ' Tool Condition Monitoring using Acoustic Emission and Vibration Signature in Turning, ' Proceedings of the World Congress on Engineering London, 3 (2012), pp. 1-5 [10] H. Jiang, X. Long, and G. Meng, 'Study of the correlation between surface generation and cutting vibrations in peripheral milling,' Journal of Materials Processing Technology, 208(1), pp. 229-238, 2008 [11] R. Azouzi, and M. Guillot, 'On-line prediction of surface finish and dimensional deviation in turning using neural network based sensor fusion,' International Journal of Machine Tools and Manufacture, 37(9), pp. 1201-1217, 1997. [12] 陳傑, 工具機預估工件銑削品質可行性之研究, 國立中正大學機械工程學系碩士論文, 2014. [13] 洪沛志, 銑削加工振動訊號與表面粗糙度之關聯性, 國立台灣大學機械工程學系碩士論文, 2018. [14] Chae J, Park SS, Freiheit T. Investigation of micro-cutting operations. Int J Mach Tool Manuf 2006;46:313–32. [15] Liu X, Devor RE, Kapoor SG, Ehmann KF. The mechanics of machining at themicroscale: assessment of the current state of the science. Trans ASME J Manuf Sci Eng 2004;126:666–78. [16] Ng, C., Melkote, S., Rahman, M. and Senthil Kumar, A., 2006. Experimental study of micro- and nano-scale cutting of aluminum 7075-T6. International Journal of Machine Tools and Manufacture, 46(9), pp.929-936. [17] Weule, H., Hüntrup, V. and Tritschler, H., 2001. Micro-Cutting of Steel to Meet New Requirements in Miniaturization. CIRP Annals, 50(1), pp.61-64. [18] Filiz, S., Conley, C., Wasserman, M. and Ozdoganlar, O., 2007. An experimental investigation of micro-machinability of copper 101 using tungsten carbide micro-endmills. International Journal of Machine Tools and Manufacture, 47(7-8), pp.1088-1100. [19] Bissacco, G., Hansen, H. and De Chiffre, L., 2006. Size Effects on Surface Generation in Micro Milling of Hardened Tool Steel. CIRP Annals, 55(1), pp.593-596. [20] Aramcharoen, A. and Mativenga, P., 2009. Size effect and tool geometry in micromilling of tool steel. Precision Engineering, 33(4), pp.402-407. [21] Liu, X., Jun, M. B. G., DeVor, R. E., and Kapoor, S. G., 2004, ‘‘Cutting Mechanisms and Their Influence on Dynamic Forces, Vibrations and Stability in Micro-Endmilling,’’ Proc. ASME Manufacturing Engineering Division~ MED-15 ! , ASME International Mechanical Engineering Congress and Exposition, Anaheim CA. Paper No. IMECE2004–62416.20 [22] C. L. Phillips, J. M. Parr, and E. A. Riskin, Signals, systems, and transforms, 3rd ed., Prentice Hall, Upper Saddle River, N.J., 2003 [23] P. D. Welch, “The use of fast Fourier transform for the estimation of power spectra: A method based on time-averaging over short, modified periodograms,”IEEE Trans. Audio Electroacoustics, vol. AU-15,pp. 70-73, 1961. [24] Sciencedirect.com. 2020. Class Separability - An Overview | Sciencedirect Topics. [online] Available at: <https://www.sciencedirect.com/topics/engineering/class-separability> [Accessed 19 July 2020]. [25] Fourier.eng.hmc.edu. 2020. Separability Criteria For Feature Selection. [online] Available at: http://fourier.eng.hmc.edu/e161/lectures/classification/node4.html> [Accessed 19 July 2020]. [26] '費雪的判別分析與線性判別分析', 線代啟示錄, 2020. [Online]. Available: https://ccjou.wordpress.com/2014/03/14/%E8%B2%BB%E9%9B%AA%E7%9A%84%E5%88%A4%E5%88%A5%E5%88%86%E6%9E%90%E8%88%87%E7%B7%9A%E6%80%A7%E5%88%A4%E5%88%A5%E5%88%86%E6%9E%90/. [Accessed: 19- Jul- 2020]. [27] BISHOP, C., 2016. PATTERN RECOGNITION AND MACHINE LEARNING. [Place of publication not identified]: SPRINGER-VERLAG NEW YORK. [28] Rosenblatt, F., 1962. Principles Of Neurodynamics. Washingotn, D.C.: Spartan Books. [29] '電腦也會學習?類神經網路讓您窺知一二!', Bituzi.com, 2020. [Online]. Available: http://www.bituzi.com/2014/11/ann-makes-computer-learn.html. [Accessed: 19- Jul- 2020]. [30] F. Murtagh, 'Multilayer perceptrons for classification and regression', Neurocomputing, vol. 2, no. 5-6, pp. 183-197, 1991. Available: 10.1016/0925-2312(91)90023-5. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/21053 | - |
dc.description.abstract | 近年來,隨著製造業轉型與升級成智慧化的發展,許多研究致力於加工製程的監控、預測機械系統故障及刀具壽命診斷之模型開發。而為了達到監控目的,需仰賴感測器的協助來獲得系統即時資訊。在加工製程監控中,感測器通常被固定在工件上來擷取訊號,並透過模型得到預測結果。然而,這代表感測器與刀具之相對距離不斷地變化,可能導致監控模型判斷失誤。 為了觀察感測器位置對訊號的影響,本研究擬在工件上用兩種方式放置加速規,第一種方式是固定安裝位置,另一種方式則是變動安裝位置,後者會隨著刀具移動到相對應的切削路徑旁收集振動訊號,所以加速規與刀具之相對距離是固定的;並讓兩者加速規在進行直線槽銑時同步收集訊號,以偵測尺寸效應作為加工製程監控之應用情境。針對兩種加速規之訊號分別建立各自的費雪線性區分模型以及非線性之類神經網路模型,來比較不同加速規位置之振動訊號對偵測尺寸效應模型的影響。 分析結果顯示,將兩者加速規之頻域訊號以群組分離準則分別進行特徵選取後,尺寸效應之特徵頻率多數落在刃頻上。而加工監控中,本研究建議加速規與刀具之間的相對距離所造成之能量差異必須考量,否則將造成模型判斷有失誤的疑慮。以進給方向為例,固定安裝位置之加速規辨識率在變換進給位置順序後,準確率降至91.63%。對此,本研究提出的改善方法,即對頻譜總能量實施正規化後可提升辨識率至95.8%,若再利用特徵融合方式整合三個軸向之特徵頻率作為特徵向量,並建立類神經網路模型,更可達到98.1%。透過正規化與非線性模型確實降低了刀具與加速規之相對距離造成的能量誤差以及消除不同進給大小造成的能量差異,提升了模型的穩定性。 | zh_TW |
dc.description.abstract | With the development of smart manufacturing, there are many studies have been devoted to machining processes monitoring, predicting the failures of mechanical system or tool life. In order to get the real-time information from the system relies on the assistance of sensors. Furthermore, the sensor is usually installed at a location where the interference to the cutting process is minimum. However, the sensor location is usually fixed so the distance between the sensor and the tool tip varies all the time. This might lead to errors in decision making based on vibration signals. In this study, the effect of sensor location on detecting size effect with vibration signals in slot milling was investigated. Two different methods were compared. The first method (method A) was to fix the location of the accelerometer. The other method (method B) was to change the sensor position before every cutting test so the sensor remained the same position relative to the cutting tool. The features of vibration signals in method A and method B were compared. Analysis shows that the characteristic frequency of the size effect mostly falls on the tool passing frequency, and the features of signal were different between these two methods. It suggested that the relative positions between the sensor and cutting zone should be taken into consideration in machining process monitoring, otherwise, it would lead to errors in decision making based on vibration signals. Taking the feed direction as an example, the accuracy of the accelerometer in method A is reduced to 91.63% after changing the feed position sequence. As a result, a recommended solution is proposed in this study, that is, use energy normalization process. The results show that it is possible to increase the accuracy to 95.8%, and then establish a neural network model with feature fusion method, which can effectively improve the average accuracy rates of 98.1%. | en |
dc.description.provenance | Made available in DSpace on 2021-06-08T03:17:51Z (GMT). No. of bitstreams: 1 U0001-1808202014395000.pdf: 7630502 bytes, checksum: 2230be2b0f3f9e51ca6d78f7a0a54def (MD5) Previous issue date: 2020 | en |
dc.description.tableofcontents | 口試委員審定書 i 誌謝 ii 摘要 iii ABSTRACT iv 目錄 vi 圖目錄 ix 表目錄 xiii 第1章 緒論 1 1.1 前言 1 1.2 文獻回顧 2 1.2.1 加工製程監控 2 1.2.2 監控與預測表面品質 3 1.2.3 尺寸效應 4 1.3 研究動機與目的 6 1.4 論文章節架構 7 第2章 研究方法 8 2.1 研究架構 8 2.2 振動訊號擷取與分析 9 2.2.1 訊號擷取理論 | 奈奎斯特定理 (Nyquist Theorem) 9 2.2.2 訊號前處理 (Signal Processing) 11 2.2.3 快速傅立葉轉換 | Welch Method 12 2.3 特徵選取 (Feature Selection) 13 2.3.1 群組分離準則 (Class Mean Scatter Criteria) 13 2.3.2 費雪線性區分法 (Fisher’s Linear Discriminant Analysis) 15 2.3.3 感知器疊代演算法 (The Perceptron Algorithm) 18 2.4 類神經網路 (Artificial Neural Network) 20 2.4.1 類神經網路概念 20 2.4.2 類神經網路架構 21 2.4.3 模型訓練 22 第3章 實驗設備與規劃 24 3.1 實驗架構 24 3.2 實驗設備 25 3.2.1 刀具 (Tool) 25 3.2.2 工件 (Workpiece) 26 3.2.3 三軸加速規 (Accelerometer) 26 3.2.4 磁座 (Magnetic Mounting Base) 27 3.2.5 工具機 (Machining Center) 27 3.2.6 PXI Express 同步取樣高速資料儲存系統 28 3.2.7 濾波放大器 29 3.2.8 扭力板手 (Torque Wrench) 31 3.2.9 Mitutoyo表面粗糙度儀 31 3.3 實驗規劃 32 3.3.1 銑削加工 | 進給變化 32 3.3.2 訊號分析流程 34 3.3.3 表面粗糙度量測方式 35 3.3.4 數據標記標準 | 尺寸效應(Size Effect) 35 第4章 實驗結果與討論 37 4.1 預實驗 | 同進給 37 4.1.1 預實驗之時域分析 38 4.1.2 預實驗之頻域分析 39 4.2 實驗(一) | 變進給 41 4.2.1 數據集(Dataset) 42 4.2.2 特徵選取 42 4.2.3 建立模型 | 費雪線性區分法 44 4.2.4 測試實驗 | 改變進給順序 47 4.2.5 小結 51 4.3 正規化後的實驗分析 52 4.3.1 特徵選取 54 4.3.2 建立模型 | 費雪線性區分法 56 4.3.3 測試實驗 | 改變進給順序 59 4.3.4 小結 62 4.4 改善正規化後線性不可分之情況 63 4.4.1 數據擴增 63 4.4.2 特徵融合 63 4.4.3 建立模型 | 類神經網路 64 4.4.4 測試實驗 | 改變進給順序 65 4.4.5 小結 65 第5章 結論與未來展望 66 5.1 總結 66 5.2 未來展望 67 REFERENCE 68 | |
dc.language.iso | zh-TW | |
dc.title | 加速規位置對銑削加工製程監控的影響 | zh_TW |
dc.title | Effect of Sensor Location on Machining Process Monitoring in Milling | en |
dc.type | Thesis | |
dc.date.schoolyear | 108-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 蔡孟勳(Meng-Shiun Tsai),盧銘詮(Ming-Chyuan Lu) | |
dc.subject.keyword | 加速規位置,尺寸效應,群組分離準則,費雪線性區分法,類神經網路,正規化, | zh_TW |
dc.subject.keyword | Sensor location,Size effect,Class mean scatter criteria,Fisher’s linear discriminant analysis,Neural network,Normalization, | en |
dc.relation.page | 70 | |
dc.identifier.doi | 10.6342/NTU202003973 | |
dc.rights.note | 未授權 | |
dc.date.accepted | 2020-08-20 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 機械工程學研究所 | zh_TW |
顯示於系所單位: | 機械工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-1808202014395000.pdf 目前未授權公開取用 | 7.45 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。