Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/2569
DC FieldValueLanguage
dc.contributor蔡孟勳zh_TW
dc.contributorMeng-Syun Tsaien_US
dc.contributor曾柏昌zh_TW
dc.contributorBwo-Chang Dzengen_US
dc.contributor.advisor盧銘詮zh_TW
dc.contributor.advisorMing-Chyuan Luen_US
dc.contributor.author萬秉勳zh_TW
dc.contributor.authorWan, Bing-Syunen_US
dc.contributor.other中興大學zh_TW
dc.date2011zh_TW
dc.date.accessioned2014-06-05T11:43:34Z-
dc.date.available2014-06-05T11:43:34Z-
dc.identifierU0005-2908201016354500zh_TW
dc.identifier.citation[1] Taraman, K., Swando, R., and Yamauchi, W., 1974, ‘‘Relationship Between Tool Forces and Flank Wear,’’ SME Tech Pap, March, 15p. [2] Fromson, R., and Shum, L. Y., 1984, ‘‘Tool Wear and Tool Failure Monitoring System,’’ Westinghouse Electric Corp., USA, USP 04442494. [3] Liang, S. Y., and Dornfeld, D. A., 1989, ‘‘Tool Wear Detection Using Time Series Analysis of Acoustic Emission,’’ ASME J. Eng. Ind., 111, pp. 199. [4] El-wardany, T. I., Gao, D., and Elbestawi, M. A., 1996, ‘‘Tool Condition Monitoring in Drilling Using Vibration Signature Analysis,’’ Int. J. Mach. Tools Manuf., 36, pp. 687–711. [5] Dornfeld, D. A., 1990, ‘‘Neural Network Sensor Fusion for Tool Condition Monitoring,’’ CIRP Ann., 39~1!, pp. 101–105. [6] Wang, Z., and Dornfeld, D. A., 1992, ‘‘In-process Tool Wear Monitoring Using Neural Networks,’’ Japan/USA Symposium on Flexible Automation, 1, pp. 263–269. [7] Kuo, R. J., and Cohen, P. H., 1998, ‘‘Intelligent Tool Wear Estimation System Through Artificial Neural Networks and Fuzzy Modeling,’’ Artif. Intell. Eng., 12~31, pp. 229–242. [8] Li, X. L., Tso, S. K., 2000, ‘‘Real-time tool condition monitoring using wavelet transforms and fuzzy techniques, ‘‘ Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, Vol.30(3), pp. 352-357. [9] Kannatey-Asibu, E. Jr. and Emel, E., 1987, ‘‘Linear discriminant function analysis of acoustic emission signals for cutting tool monitoring,” Mechanical Systems and Signal Processing, Vol.1(4), pp. 333-347. [10] P. Baruah and R. B. Chinnam, 2005 ,‘‘HMMs for diagnostics and prognostics in machining processes,’’ International Journal of Production Research, v 43, n 6, p 1275-1293. [11] Antonio G. Vallejo Jr., Juan A. Nolazco-Flores, 2005,Ruben Morales-Menendez, L. Enrique Sucar, and Ciro A. Rodrıguez, ‘‘Tool-wear monitoring based on continuous hidden markov models,’’ Lecture Notes in Computer Science, v 3773, p 880-890. [12] Jing, K., and Ni, K., 2008, ‘‘Pattern Recognition of Tool Wear and Failure Prediction,’’ Proceedings of the World Congress on Intelligent Control and Automation (WCICA), p 6000-6005. [13] Zhu, K. P., Wong, Y. S., and Hong, G.. S., 2009, ‘‘Multi-category micro-milling tool wear monitoring with continuous hidden Markov models,’’ Mechanical Systems and Signal Processing, v 23, n 2, p 547-560. [14] Huseyin M. Ertunc, Kenneth A. Loparo Hasan Ocak, 2001, ‘‘Tool wear condition monitoring in drilling operations using hidden Markov models (HMMs),’’ International Journal of Machine Tools and Manufacture, v 41, n 9, p 1363-1384. [15] Zhu, K. P., Wong, Y. S., and Hong, G.. S., 2008, ‘‘A comparative study of feature selection for hidden Markov model-based micro-milling tool wear monitoring,’’ Machining Science and Technology, v 12, n 3, p 348-369. [16] Zhang, C. L., Yue, X., and Zhang, X. W., 2009, ‘‘Cutting chatter monitoring using hidden Markov models,’’ International Conference on Control, Automation and Systems Engineering, p 504-507. [17] Atlas, L., Mari, O., Gary, D. B., 2000, ‘‘Hidden Markov models for monitoring machine tool-wear,’’ International Conference on Acoustics, Speech and Signal Processing - Proceedings, v 6, p 3887-3890. [18] Natarajan, U., Arun, P., Dr Periasamy, V. M., 2007, ‘‘On-line tool wear monitoring in turning by hidden Markov model (HMM),’’ Journal of the Institution of Engineers (India), Part PR: Production Engineering Division, v 87, n MAR., p 31-35. [19] 張旺榮,2004,利用隱藏馬可夫樹模式以提昇製程監控效能,私立中原大學化學工程研究所,碩士論文。 [20] 陳信宏,2005,發展隱藏式馬可夫樹模式之即時批次監控系統,私立中原大學化學工程研究所,碩士論文。 [21] 李明興,2009,整合聲音訊號與自組特徵映射網路於微細刀具磨耗狀態之應用研究,國立中興大學機械工程研究所,碩士論文。 [22] Matlab, 2008, Wavelet Toolbox User’s Guide [23] Haykin, S., Van Veen, B., 2003, Signals and Systems, John Wiley & Sons. [24] Schilling, R. J. and Harris, S. L., 2005, Fundamentals of Digital Signal Processing Using MATLAB, Thomson. [25] Yen, C. L., Lu, M. C., Lin, C. Y., and Chen, T. H., 2008, ‘‘Draft-Experimental Study of sound signal for tool condition monitoring in micro milling processes,’’ Proceedings of the 2008 International Manufacturing Science And Engineering Conference. [26] Wang , L. T., Mostafa G. Mehrabi, Elijah Kannatey-Asibu, 2002, ‘‘Hidden Markov model-based tool wear monitoring in turning,’’ Journal of Manufacturing Science and Engineering, Transactions of the ASME, v 124, n 3, p 651-658. [27] 謝萬皓,2009,應用類神經網路與振動之微銑刀具狀態偵測系統開發,國立中興大學機械工程研究所,碩士論文。zh_TW
dc.identifier.urihttp://hdl.handle.net/11455/2569-
dc.description.abstract隨著微細加工應用持續增加,微細切削加工精度的要求也逐漸提高,而微細切削加工過程中,刀具的磨耗比一般傳統刀具來得快速,影響產品的精度極大。於加工時對刀具磨耗之監測,在機械自動化之發展中已受到相當的重視,不僅可以提升加工品質及效率,進而更能夠減少對環境的衝擊。過去商業應用中,多將切削時量測之訊號分析,利用訊號在時域和頻域訊號能量大小變化判定刀具狀態,對於工具機加工時所產生一些不穩定之系統振動或是其他對於訊號產生干擾之因子,往往無法分辨而造成系統誤判。隱藏式馬可夫模型藉著觀察一序列的特徵訊號,建立包含特徵對於隱藏狀態之統計參數以及時間連續訊號彼此之關連性參數,對於短暫不穩定之系統振動較不受於影響,處理速度也較類神經系統快。 本研究探討隱藏式馬可夫模型在微銑刀具狀態偵測應用之性能,建立之偵測系統包含量測模組、訊號轉換分析、特徵選取與處理以及分類器設計。本研究之研究平台由NSK-EM30 S60000內藏式電動主軸所組成,轉速可達六萬轉,使用之實驗刀具為直徑700μ m之微銑刀,工件材料為SK2高碳鋼。切削時之訊號擷取以外掛於主軸和工件之聲射感應器量測切削過程中因刀具狀態改變之聲射訊號變化,以及使用麥克風量測其聲音變化,所取得的訊號採用快速傅立葉轉換後,觀看其刀具磨耗之頻域訊號變化,接續選取與刀具磨耗相關之訊號特徵。在特徵選取方面,則利用群組分離準則計算訊號隨磨耗改變之變異量,決定最佳之頻域特徵訊號,分類器則使用隱藏式馬可夫模型。 研究結果顯示聲射訊號與聲音訊號在刀具磨耗時之訊號變動,兩者時域訊號皆隨著刀具磨耗量增加逐漸提升。在聲射訊號方面,頻帶寬度、特徵值數量和觀察訊號序列個數等參數對於辨識系統之影響度較大,主軸之聲射訊號於選擇頻帶寬度64KHz、特徵值1個和觀察訊號序列10個以及頻帶寬度32KHz、特徵值5個和觀察訊號序列30個之辨識效果最佳,辨識率為100%;工件之聲射訊號於選擇頻帶寬度64KHz、特徵值5個和觀察訊號序列30個之辨識效果最佳,辨識率為100%。在聲音訊號方面,頻帶寬度選擇12KHz之辨識性能最好,於頻帶寬度12KHz,以特徵值選取3個之辨識效果為最好,而觀察訊號序列個數選擇10個之辨識性能最好,其隱藏狀態數量對於系統辨識之影響不大。綜合聲射訊號和聲音訊號之辨識度比較,工件之聲射訊號辨識度與聲音訊號略同,且明顯高於主軸之聲射訊號。 與應用費雪線性區分法(FLD)之刀具辨識度比較,當HMM之觀察訊號序列個數和FLD之測試訊號樣本數皆為30個時,頻帶寬度均為64KHz和32KHz之條件下,HMM之辨識度明顯大於FLD約20%,而工件之聲射訊號之平均辨識度更大於FLD約30%,其結果顯示由觀察長時間連續訊號之隱藏式馬可夫模型對於短暫雜訊干擾影響較小,進而提高系統之辨識效能。zh_TW
dc.description.tableofcontents誌謝.......................................................i 摘要.......................................................i Abstract..................................................iv 目錄......................................................vi 圖目錄..................................................viii 表目錄.....................................................x 符號表說明................................................xi 第一章、緒論...............................................1 1.1 前言..............................................1 1.2 研究目的與內容....................................1 1.3 文獻回顧..........................................2 第二章、訊號處理...........................................4 2.1 傅立葉轉換........................................4 2.2 準位均化..........................................6 2.3 群組分離準則......................................7 2.4 隱藏式馬可夫模型..................................8 2.4.1 HMM 機率計算...............................11 2.4.2 正算-逆算程序(Forward-backward procedure)..12 2.4.3 波式演算法(Baum-Welch algorithm)...........14 2.4.4 維特比演算法(Viterbi algorithm)............16 第三章、實驗設計和辨識系統設計............................18 3.1 微型加工研究平台.................................18 3.2 量測模組.........................................18 3.3 實驗規劃.........................................19 3.4 刀具磨耗狀態辨識系統設計.........................21 第四章、刀具磨耗實驗結果分析與討論........................25 4.1 刀具磨耗原始訊號分析.............................25 4.2 聲射訊號對刀具狀態辨識度之分析...................33 4.2.1 頻帶寬度對刀具狀態辨識度之影響.............38 4.2.2 特徵值數量對刀具狀態辨識度之影響...........42 4.2.3 觀察訊號序列個數對刀具狀態辨識度之影響.....43 4.2.4 隱藏狀態數量對刀具狀態辨識度之影響.........45 4.3 聲音訊號對刀具狀態辨識度之分析...................46 4.3.1 頻帶寬度對刀具狀態辨識度之影響.............49 4.3.2 特徵值數量對刀具狀態辨識度之影響...........51 4.3.3 觀察訊號序列個數對刀具狀態辨識度之影響.....52 4.3.4 隱藏狀態數量對刀具狀態辨識度之影響.........52 4.4 隱藏式馬可夫模型與費雪線性區分法之刀具狀態辨識度比較........................................................53 第五章、結論與未來展望....................................55 5.1 結論.............................................55 5.2 未來展望.........................................56 參考文獻..................................................58zh_TW
dc.language.isoen_USzh_TW
dc.publisher機械工程學系所zh_TW
dc.relation.urihttp://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-2908201016354500en_US
dc.subjectMicro cuttingen_US
dc.subject微細加工zh_TW
dc.subjectHidden Markov modelsen_US
dc.subjectTool wear monitoringen_US
dc.subject隱藏式馬可夫模型zh_TW
dc.subject刀具磨耗偵測zh_TW
dc.title隱藏式馬可夫模型應用於微細刀具磨耗狀態偵測之研究zh_TW
dc.titleApplication of Hidden Markov Models for Tool Wear Monitoring in Micro Millingen_US
dc.typeThesis and Dissertationzh_TW
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.openairetypeThesis and Dissertation-
item.cerifentitytypePublications-
item.fulltextno fulltext-
item.languageiso639-1en_US-
item.grantfulltextnone-
Appears in Collections:機械工程學系所
Show simple item record
 
TAIR Related Article

Google ScholarTM

Check


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