Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/2008
標題: 應用振動訊號與模糊演算法偵測刀具狀態之研究
A Study on Identifying Tool Condition by Vibration Signal and Fuzzy Logic
作者: 林敬偉
Lin, Jing-Wei
關鍵字: Vibration Signal;振動訊號;Class Scatter Criterion;Self-Organizing Map;Fuzzy Decision;群組分離準則;自組織映射圖;模糊決策
出版社: 機械工程學系所
引用: [Aygen et al., 1999] Z. E. Aygen, S. Seker, M. Bagnyanik, F. G. Bagnyanik and E. Ayaz,“Fault Section Estimation in Electrical Power Systems Using Artificial Neural Network Approach, "Transmission and Distribution Conference of IEEE, Vol.2, pp.466 - 469, 1999. [Cho & Park, 1997] H. J. Cho and J. K. Park,“An Expert System for Fault Section Diagnosis of Power Systems Using Fuzzy Relations,"IEEE Transactions on Power Systems, Vol. 12, pp.342 – 348, 1997. [El-Wardany et al., 1996] T. I. El-Wardany, D. Gao and M. A. Elbestawi, “Tool Condition Monitoring in Drilling Using Vibration Signature Analysis,” International Journal of Machine Tools and Manufacture, Vol.36, pp.687-711, 1996. [Ezugwu et al., 1995] E. O. Ezugwu, S. J. Arthur and E. L. Hines, “Tool-Wear Prediction Using Artificial Neural Networks,” Journal of Materials Processing Technology, Vol.49, pp.255-264, 1995. [Fanni et al., 1993] A. Fanni, A. Giua and E. Sandoli,“Neural Networks for Multiple Fault Diagnosis in Analog Circuits, "The IEEE International Workshop on Defect and Fault Tolerance in VLSI Systems, pp.303 – 310, 1993. [Freitas, 2002] A. Freitas, “A Survey of Evolutionary Algorithms for Data Mining and Knowledge Discovery, ” Advances in Evolutionary Computation, pp.819-845, August, 2002. [Goddu et al., 1998] G. Goddu, B. Li, M.Y. Chow and J.C. Hung,“Motor Bearing Fault Diagnosis by a Fundamental Frequency Amplitude Based Fuzzy Decision System,” Proceedings of the 24th Annual Conference of the IEEE, Vol. 4, pp.1961 - 1965, 1998. [Huang et al., 2007] R. Huang, L. Xi, X. Li, C. R. Liu, H. Qiu and J. Lee, “Residual Life Predictions for Ball Bearings Based on Self-Organizing Map and Back Propagation Neural Network Methods”, Mechanical Systems and Signal Processing, v 21, n 1, January, pp. 193-207, 2007. [Issam, 2003] A. M. Issam, “Drilling Wear Detection and Classification Using Vibration Signals and Artificial Neural Network,” International Journal of Machine Tools and Manufacture, Vol.43, pp.707-720, 2003. [Lee et al., 2004] J. Lee, H. Qiu, J. Ni and D. Djurdjanovic, “Infotronics Technologies and Predictive Tools for Next-Generation Maintenance Systems,” Proceedings of the 11th IFAC Symposium on Information Control, 2004. [Lee et al., 2006] J. Lee, J. Ni, D. Djurdjanovic, H. Qiu, and H. Liao, “Intelligent Prognostics Tools and E-Maintenance,” Computers in Industry, Vol. 57, pp. 476-489, 2006. [Li et al., 2000] X. Li, S. K. Tso and J. Wang, “Real-Time Tool Condition Monitoring Using Wavelet Transforms and Fuzzy Techniques,” IEEE, vol.30, No.3, August, pp.352-357, 2000. [Liu & Anantharaman, 1994] T. I. Liu and K. S. Anantharaman, “Intelligent Classification and Measurement of Drill Wwear,” Journal of Engineering for Industry, Transactions of the ASME, vol.116, No.3, August, pp.392-397, 1994. [Lou & Loparo, 2004] X. Lou and K. A. Loparo, “Bearing Fault Diagnosis Based on Wavelet Transform and Fuzzy Inference,” Mechanical Systems and Signal Processing, vol.18, No.5, September, pp.1077-1095, 2004. [Shaw, 1984] C. M. Shaw, Metal Cutting Principles, Clarendon Press, 1984. [Mendel, 1995], J. M. Mendel, “Fuzzy Logic Systems for Engineering: A Tutorial”, Proceedings of the IEEE, Vol.83, No.3, March 1995. [Haykin, 1994] S. Haykin, Neural Networks :A Comprehensive Foundation, Macmillan, 1994. [Sokolowski, 2004] A. Sokolowski, “On Some Aspects of Fuzzy Logic Application in Machine Monitoring and Diagnostics”, Engineering Application of Artificial Intelligence, p 429-437, 2004. [Timothy, 2004] J. R. Timothy, Fuzzy Logic with Engineering Application, John Wiley&Sons Ltd, 2004. [Xie et al., 2002] D. M. Xie, X. Song, H. L. Zhou and M. W. Guo,“Fuzzy Vibration Fault Diagnosis System of Steam Turbo-Generator Rotor,"Proceedings of International Conference on Machine Learning and Cybernetics, Vol.1, pp. 411 – 415, 2002. [Yao et al., 1999] Y. Yao, X. Li, Z. Yuan, “Tool Wear Detection with Fuzzy Classification and Wavelet Fuzzy Neural Network,” Machine Tools and Manufacturer, pp. 1525-1538, 1999. [Zadeh, 1965] L. A. Zadeh, “Fuzzy Sets,” Information Control, Vol.8, pp. 338-353, 1965. [丁,1992] 丁嘉人,以神經網路進行鑽削刀具磨耗監測模式之研究,國立清華大學動力機械系碩士論文,1992。 [王,2005] 王信誌,螺旋刃球型銑刀之切削表面粗糙度探討,國立中興大學機械工程學系碩士論文,2005。 [林,1993] 林士傑,面銑削刀具磨耗之監測,國立清華大學動力機械系碩士論文,1993。 [林,2000] 林星佑,應用函數分解法作資料分類,私立輔仁大學資訊工程系碩士論文,2000。 [黃,1993] 黃崑峰,“預知式維護與振動分析法",機械月刊,第19卷第7期,1993年7月,128-141頁。 [黃,2004] 黃晉緯,應用適應性演算法則於旋轉機械之故障診斷,私立大葉大學機械工程系碩士論文,2004。 [馬 & 李,2007] 馬寧元、李元中,“刀具磨損之探討",機械工業雜誌,2007年6月,155-157頁。 [郭,2002] 郭家榮,資料壓縮技術應用於類神經網路之研究,私立中國文化大學資訊管理研究所碩士論文,2002。 [張等人,2003] 張裴章,張麗秋,黃浩倫,類神經網路理論與實務,東華書局,2003。 [張,2005] 張智傑,齒輪故障診斷之模糊類神經網路,私立中園大學機械工程系碩士論文,2005。 [馮 & 任,2007] 馮國臣、任麗偉,模糊理論基礎與應用,新文京開發出版社,2007。 [惠,2004] 惠汝生,LabVIEW 7.1 Express 圖控程式應用含自動量測及硬體應用,全華科技圖書股份有限公司,2004。 [賴,2007] 賴姿吟,利用刀具狀態監測探討鑽頭不同磨耗的振動特徵,國立高雄應用科技大學模具工程學系碩士論文,2007。 [顏,2008] 顏嘉良,應用類神經網路於微細切削刀具狀態偵測之研究,國立中興大學機械工程學系碩士論文,2008。 [蕭等人,2004] 蕭子健、王智昱、儲昭偉,虛擬儀控程式設計 LabVIEW 7x,高立圖書有限公司,2004。
摘要: 
工具機加工過程中,有許多影響產品加工品質的因素,而刀具的磨損程度是直接影響產品的重要因素,因此,監測刀具在切削中的狀態變化,是個亟需研究的課題。本研究針對上述課題,目標在於發展一套於切削過程中可辨識刀具狀態的系統,並驗證該系統之可行性,未來在實際加工過程中,能夠即時掌握刀具的狀況,立即作適當的處置。
本研究首先探討刀具切削狀態、資料分類與辨識技術,並據此發展一切削刀具狀態辨識軟體系統,最後規劃實驗以驗證該系統之可行性。研究內容則包含刀具狀態量化指標建立、訊號轉換與特徵選取方法、自組織映射圖(Self-Organizing Map, SOM)模型與Fuzzy辨識模型建立、人機介面與系統整合規劃設計與建置、測試平台建構與系統驗證。研究利用刀具每切削100mm所拍攝刀具刀刃圖片,量化刀具在不同切削刀次下能夠表現出其差異作為指標,結果顯示當切削刀次(長度)增加,刀具磨損的程度呈現非線性增加。為進一步驗證此理論,選擇主軸振動訊號之頻譜作為判斷基準,分別以一把刀單獨訓練、兩把刀同時訓練及第一、二、三把刀同時訓練進行探討,驗證結果顯示,若以第一把刀單獨訓練,系統最終判斷結果正確率為68.8%;以第一把與第二把同時訓練,系統判斷成功率為84.4%,以第一把、第二把及第三把刀同時訓練,系統判斷成功率為87.5%,顯示利用主軸振動訊號之頻譜,透過適當的資料分類訓練,可作為判斷刀具的切削狀態。

During machine tool processing, there are several factors would effect the quality of the finish products. And, the arrtition of cutting tools is the most crucial facts among these them. Therefore, monitoring the change of the form of cutting tools during a cutting process is an important subject for research. According to this subject, this research targets to develop a system to recognize the condition of cutting tools during processing and to verify the feasibility of this system. In the future, the system could help us to control the status of cutting tools and do the needful action promptly.
In this research, we will examine different conditions of cutting tools, information classification, and recognition technics. With the study we will develop a software of “Cutting Tool Status Recognition System”, and to plan experiment for feasibility of this system. This research contains: Building quantification for cutting tool status index. Signal transfer and method for characteristic selection. Self-Organizing Map (SOM) molding and Fuzzy identification model construction. Building Human-Machine Interface (HMI) and system integration. Construction of Testing Platform and System Verification. The result shows the following: From the photo of the edge of cutting tools taken from every 100mm cutting process, we quantify the variation of each drill of a cutting tool during the processing. When the length of cutting process increase, the arrtition of cutting tools shows non-linear increase. For the verification of the system, we judge by the spectrum of spindle vibration signal. One side we use one cutter only, and 2 cutters and 3cutters in the other side for testing. The result indicates: if we use 1 cutter only, the Accuracy Ratio of the system is 68.8%; when using 2 cutters together, the Accuracy Ratio is 84.4%. when using 3 cutters together, the Accuracy Ratio is 87.5%, Therefore, we can see that with the spectrum of spindle vibration signal, and adequate training for information classification, we can estimate the status of cutters during processing.
URI: http://hdl.handle.net/11455/2008
其他識別: U0005-0902200919201400
Appears in Collections:機械工程學系所

Show full item record
 

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.