Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/91457
標題: Application of Acoustic Emission Signals for Surface Roughness of Zirconia Ceramic in the Precision Grinding
應用聲射訊號用於精密研磨之氧化鋯表面粗糙度研究
作者: 吳東晨
Dong-Chen Wu
關鍵字: zirconia
plane grinding
acoustic emission (AE)
surface roughness
neural networks
氧化鋯
平面磨削
聲射(AE)
表面粗糙度
類神經網路
引用: [1] P.S Sreejith, B.K.A Ngoi, 'Material removal mechanisms in precision machining of new materials', International Journal of Machine Tools and Manufacture, Vol. 41, Issue 12, September 2001, pp. 1831-1843. [2] Muhammad Arif, Zhang Xinquan, Mustafizur Rahman, Senthil Kμmar, 'A predictive model of the critical undeformed chip thickness for ductile–brittle transition in nano-machining of brittle materials', Journal of Materials Processing Technology, Vol. 209, Issue 7, 1 April 2009, pp. 3306-3319. [3] J. Xie, H.F. Xie, X.R. Liu, T.W. Tan, 'Dry micro-grooving on Si wafer using a coarse diamond grinding', International Journal of Machine Tools and Manufacture, Vol. 61, October 2012, pp. 1-8. [4] Mingjun Chen, Qingliang Zhao, Shen Dong, Dan Li, 'The critical conditions of brittle–ductile transition and the factors influencing the surface quality of brittle materials in ultra-precision grinding', Journal of Materials Processing Technology, Vol. 168, Issue 1, 15 September 2005, pp. 75-82. [5] Li Xu,Shubo Liu, 'Grinding Engineering Ceramics Research', IEEE International Conference on Electronic & Mechanical Engineering and Information Technology,2011, pp. 1619-1622. [6] E. Brinksmeier, Y. Mutlugunes, F. Klocke, J.C. Aurich, P. Shore, H. Ohmori,'Ultra-precision grinding', Precision Engineering, Vol. 35, Issue 4, October 2011, pp. 554-565. [7] T. G. Bifano, T. A. Dow, R. 0. Scattergood, 'Ductile-Regime Grinding: A New Technology for Machining Brittle Materials', Transactions of the ASME, Vol. 113,May 1991, pp. 184-189. [8] H.K. Tonshoff, T. Friemuth, J.C. Becker,'Process Monitoring in Grinding', CIRP Annals - Manufacturing Technology, Vol. 51, Issue 2, 2002, pp. 551-571. [9] Guo Bi, Yinbiao Guo, Jing Lin, Wei Han, Maojiang Zheng, Xin Chen.'Principles of An In-process Monitoring System for Precision Grinding Machine', IEEE National High Technology Project,2011, pp. 7546-7549. [10] Changfei Lv, Haolin Li,'Acoustic Emission Signal Processing of Grinding Monitor',IEEE International Congress on Image and Signal Processing,2010, pp. 3836-3838. [11] H.K Tonshoff, M Jung, S Mannel, W Rietz,'Using acoustic emission signals for monitoring of production processes', Ultrasonics, Vol. 37, Issue 10, 1 July 2000, pp. 681-686. [12] J. Webster, W.P. Dong, R. Lindsay,'Raw Acoustic Emission Signal Analysis of Grinding Process', CIRP Annals - Manufacturing Technology, Vol. 45, Issue 1, 1996, pp. 335-340. [13] J.F. Gomes de Oliveira, D.A. Dornfeld,'Application of AE Contact Sensing in Reliable Grinding Monitoring', CIRP Annals - Manufacturing Technology, Vol. 50, Issue 1, 2001, pp. 217-220. [14] H. H. Tsai, H. Hocheng,'Monitoring of creep-in depth beyond the initial wheel/workpiece contact in surface grinding by acoustic emission', Machining Science and Technology: An International Journal,1997, pp. 15-31. [15] D.E. Lee, I. Hwang, C.M.O. Valente, J.F.G. Oliveira, D.A. Dornfeld,'Precision manufacturing process monitoring with acoustic emission', International Journal of Machine Tools and Manufacture, Vol. 46, Issue 2, February 2006, pp. 176-188. [16] Rowe, W. B.,'Principles of modern grinding technolog',2009, pp. 59–78. [17] D.E. Lee, I. Hwang, C.M.O. Valente, J.F.G. Oliveira, D.A. Dornfeld,'Precision manufacturing process monitoring with acoustic emission', International Journal of Machine Tools & Manufacture , Vol. 46,2006, pp. 176–188. [18] Xuesong Han ,Tianyu Wu,'Analysis of acoustic emission in precision and high-efficiency grinding technology', Springer-Verlag London, 2012. [19] Amin A Mokbel, T.M.A Maksoud,'Monitoring of the condition of diamond grinding wheels using acoustic emission technique', Journal of Materials Processing Technology, Vol. 101, Issues 1–3, 14 April 2000, pp. 292-297. [20] Egon Susič, Igor Grabec,'Characterization of the grinding process by acoustic emission', International Journal of Machine Tools and Manufacture, Vol. 40, Issue 2, January 2000, pp. 225-238. [21] W. Konig, Y. Altintas, F. Memis,'Direct adaptive control of plunge grinding process using acoustic emission (AE) sensor', International Journal of Machine Tools and Manufacture, Vol. 35, Issue 10, October 1995, pp. 1445-1457. [22] Javad Akbari, Yoshio Saito, Tadaaki Hanaoka, Shizuichi Higuchi, Shinzo Enomoto,'Effect of grinding parameters on acoustic emission signals while grinding ceramics',Journal of Materials Processing Technology, Vol. 62, Issue 4, December 1996, pp. 403-407. [23] L. Prades-Martell, J. Serrano-Mira, R. Sanchis Llopis,'Grinding Monitoring System Based on Power and Acoustic Emission Sensors', CIRP Annals - Manufacturing Technology, Vol. 49, Issue 1, 2000, pp. 235-240. [24] Jae-Seob Kwak, Ji-Bok Song,'Trouble diagnosis of the grinding process by using acoustic emission signals', nternational Journal of Machine Tools and Manufacture, Vol. 41, Issue 6, May 2001, pp. 899-913. [25] Qiang Liu, Xun Chen, Nabil Gindy,'Investigation of acoustic emission signals under a simulative environment of grinding burn', International Journal of Machine Tools and Manufacture, Vol. 46, Issues 3–4, March 2006, pp. 284-292. [26] Qiang Liu, Xun Chen, Nabil Gindy,'Fuzzy pattern recognition of AE signals for grinding burn', International Journal of Machine Tools and Manufacture, Vol. 45, Issues 7–8, June 2005, pp. 811-818. [27] Paulo R. Aguiar1 Paulo J. A. Serni, Eduardo C. Bianchi, Fabio R. L. Dotto,'In-process grinding monitoring by acoustic emission',IEEE,2004, pp. 405-408. [28] R. Babel , P.Koshy , M.Weiss ,'Acoustic emission spikes at workpiece edges in grinding: Origin and applications', International Journal of Machine Tools & Manufacture, Vol. 64 ,2013, pp. 96–101. [29] Arul Saravanapriyan ,L. Vijayaraghavan , R. Krisburthy,'On-line Detection of Grinding Burn by Integrated Sensing', IEEE,2001, pp. 89-94. [30] E. Brinksmeier, J.C. Aurich, E. Govekar, C. Heinzel, H.-W. Hoffmeister, F. Klocke, J. Peters, R. Rentsch, D.J. Stephenson, E. Uhlmann, K. Weinert, M. Wittmann,'Advances in Modeling and Simulation of Grinding Processes', CIRP Annals - Manufacturing Technology, Vol. 55, Issue 2, 2006, pp. 667-696. [31] W.Brian Rowe, Y. Li, B. Mills, D.R. Allanson,'Application of intelligent CNC in grinding', Computers in Industry, Vol. 31, Issue 1, 30 October 1996, pp. 45-60. [32] R Deiva Nathan, L Vijayaraghavan, R Krishnamurthy,'In-process monitoring of grinding burn in the cylindrical grinding of steel', Journal of Materials Processing Technology, Vol. 91, Issues 1–3, 30 June 1999, pp. 37-42. [33] Azlan Mohd Zain, Habibollah Haron, Safian Sharif,'Prediction of surface roughness in the end milling machining using Artificial Neural Network', Expert Systems with Applications, Vol. 37, Issue 2, March 2010, pp. 1755-1768. [34] Bulent Kaya, Cuneyt Oysu, Huseyin M. Ertunc, 'Force-torque based on-line tool wear estimation system for CNC milling of Inconel 718 using neural networks', Advances in Engineering Software, Vol. 42, Issue 3, March 2011, pp. 76-84. [35] W. Brian Rowe, Yan Li, X. Chen, B. Mills, 'An Intelligent Multiagent Approach for Selection of Grinding Conditions',CIRP Annals - Manufacturing Technology, Vol. 46, Issue 1, 1997, pp. 233-238. [36] T. M.A. Maksoud, M. R. Atia,M. M. Koura,'Applications of Artificial Intelligence to Grinding Operations via Neural Networks', Machining Science and Technology: An International Journal, Vol. 3, pp. 361-387. [37] Jae-Seob Kwak, Man-Kyung Ha,'Neural network approach for diagnosis of grinding operation by acoustic emission and power signals', Journal of Materials Processing Technology, Vol. 147, Issue 1, 30 March 2004, pp. 65-71. [38] Zhen Wang, Peter Willett, Paulo R. DeAguiar, John Webster,'Neural network detection of grinding burn from acoustic emission', International Journal of Machine Tools and Manufacture, Vol. 41, Issue 2, January 2001, pp. 283-309. [39] 林登文,'應用田口法對氧化鋯平面磨削表面粗糙度參數最佳化研究,國立中興大學,碩士論文,2012。 [40 ] Weibin Gu, Zhenqiang Yao, Haolin Li,'nvestigation of grinding modes in horizontal surface grinding of optical glass BK7', Journal of Materials Processing Technology, Vol. 211, Issue 10, October 2011, pp. 1629-1636. [41] 李輝煌,田口方法-品質設計的原理與實務,高立圖書有限公司。 [42] 廖允在,'腦波及十監控系統開發-音樂對腦波影響之案例研究',國立雲林科技大學,碩士論文。 [43] 王明,'基於小波分析的聲放射信號處理在損傷診斷中的應用',江蘇大學,碩士論文。 [44] 王強,'基於聲放射技術及小波分析的砂輪鈍化狀態監測方法研究',中國海洋大學,碩士論文。 [45] 黃啟榮,'切削路徑應用主軸聲射與振動訊號之銑削刀具磨耗偵測系統之影響分析',國立中興大學,碩士論文,2012。 [46] 許育瑋,'應用主軸振動與聲射訊號於鑽頭狀態偵測之研究',國立中興大學,碩士論文,2012。 [47] Ruqiang Yan, Robert X. Gao, Xuefeng Chen,'Wavelets for fault diagnosis of rotary machines: A review with applications', Signal Processing, Vol. 96, Part A, March 2014, pp. 1-15. [48] 邱奕琛,'類神經田口法在加工毛邊預測及最佳化參數之應用',國立中興大學,碩士論文,2001。 [49] 謝萬澔,'應用類神經網路與振動訊號之微銑刀具狀態偵測系統開發',國立中興大學,碩士論文,2008。 [50] Indrajit Mukherjee, Srikanta Routroy,'Comparing the performance of neural networks developed by using Levenberg–Marquardt and Quasi-Newton with the gradient descent algorithm for modelling a multiple response grinding process', Expert Systems with Applications, Vol. 39, Issue 3, 15 February 2012, pp. 2397-2407. [51] 廖國忠,'氧化鋯陶瓷延性加工之特性研究',國立中興大學機械工程系碩士論文,2008。 [52] J.M. Longbottom, J.D. Lanham,'A review of research related to Salomon's hypothesis on cutting speeds and temperatures', International Journal of Machine Tools and Manufacture, Vol. 46, Issue 14, November 2006, pp. 1740-1747. [53] Diana Emang, Mahendran Shitan, Awang Noor Abd. Ghani, Khamurudin M. Noor,'Forecasting with Univariate Time Series Models: A Case of Export Demand for Peninsular Malaysia's Moulding and Chipboard', Journal of Sustainable Development, Vol. 3, No. 3; September 2010. [54] 曾盈憲,'聲射訊號在輪磨監測之應用',國立中興大學,碩士論文,1999。
摘要: Due to advances in the technology industry, subtle manufacturing technology continues to improve, zirconia such brittle materials used in high-precision parts more extensive and grinding technology also needs to follow the high-precision, high efficiency working in high-precision grinding improve processing efficiency, quality, and reduce processing costs is seen as key to improving competitiveness, so the precision grinding of automation and intelligent systems is one of the conditions. This study aimed to analyze investigate AE (Acoustic Emission) signal in the application of the grinding surface roughness characteristics.This experiment in Taguchi method, AE signals interception zirconia grinding processing, the AE signals do Fourier transform, and root mean average (RMS) , the zirconia surface with grinding message after the signal correlation of roughness for the final will have relevance AE signal input neural network to predict the zirconia surface roughness. In the experimental analysis of acoustic emission signals , the surface roughness of the assessment made the following points, primarily to determine the roughness of the grinding poor basis: First, most of the high frequency(200kHz-320kHz) has peaks, and the second is high frequency(200kHz-320kHz) has high energy, and finally in the low frequency(50kHz-100kHz) with high energy. The experimental results show that AE signals for neural network to predict the surface roughness 10μm wheel,10-10-1 network architecture with the greatest difference is 0.0124μm, the minimμm difference is 0.0007μm, an average difference of 0.0061 μm, MSE (mean square error) is 0.0001, MAPE (Mean absolute percentage error) is 0.04%, R (Sample Correlation Coefficient) of 0.6988, with the wheel 10μm AE signal is applied to the neural network to predict the surface roughness MAPE 0.04% to reach a very low error. In 25μm wheel of 4-4-1 network architecture with the greatest difference is 0.0144μm, the minimμm difference is 0.0015μm, the average difference was 0.0086μm, MSE is 0.0001, MAPE is 0.11%, R is 0.6194, at 25μm wheel with AE signals for neural network to predict the surface roughness is 0.11% MAPE error value is quite low, observed that AE signals for grinding surface roughness prediction is a high correlation.
由於科技產業的進步,精微製造技術不斷提升,氧化鋯屬於硬脆材料,廣泛運用在高精密零件如半導體、光電、LED等產業,而磨削技術也跟著需求往高精度、高效率著手,在高精密磨削中,提升加工效率、品質以及降低加工成本是視為提高競爭力的關鍵,因此在高精度磨削中的自動化與智能化系統是必須要具備的條件之一。 本研究目標為分析探討聲射(Acoustic Emission,AE)訊號在磨削的表面粗糙度之應用特性。實驗主要以田口實驗規畫,在磨削氧化鋯過程中擷取AE訊號,將AE訊號做傅立葉轉換、平均方根(RMS)等訊號處理,將訊號處理的訊息跟磨削過後的氧化鋯表面粗糙度作相關性探討,最後將AE訊號輸入類神經網路來輸出氧化鋯表面粗糙度,預估磨削的氧化鋯表面粗糙度之辦別。 在本實驗的AE訊號分析中,作出對氧化鋯表面粗糙度評估以下幾個要點,主要來斷定磨削後的表面粗糙度不佳的依據:首先是在200kHz-320kHz具有多數峰值且有高能量發生,其次50kHz-100kHz也有高能量發生。 本實驗結果得知類神經網路預測表面粗糙度,在磨粒10μm的砂輪下的實驗中,10-10-1網路架構以最大差值為0.0124μm、最小差值為0.0007μm、平均差值為0.0061μm、MSE(mean square error)為0.0001、MAPE(Mean absolute percentage error)為0.04%、R(Sample Correlation Coefficient)為0.6988,AE訊號應用於類神經網路是可預測表面粗糙度到MAPE為0.04%,達到相當低的誤差值。 在磨粒25μm砂輪的實驗中,4-4-1網路架構以最大差值為0.0144μm、最小差值為0.0015μm、平均差值為0.0086μm、MSE為0.0001、MAPE為0.11%、R為0.6194,類神經網路是可預測表面粗糙度的MAPE為0.11%,誤差值相當低,觀察得知AE訊號作磨削的表面粗糙度預測是具有高相關性。
URI: http://hdl.handle.net/11455/91457
文章公開時間: 2017-02-06
Appears in Collections:機械工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



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