臺灣博碩士論文加值系統

對於CNC工具機產業加工產品，影響加工工件表面精密度的因素很多，刀具磨損會降低製造過程中產品的品質，加工切削參數是影響加工精度和刀具磨損的重要因素，因此，預測刀具磨損可以幫助監測刀具的磨損和刀具最大的使用率。
本論文提出一個倒傳遞類神經網路(BPNN)預測工具機刀具磨損，當使用不同切削參數時，刀具磨損的情況會有一定的變化，運用工具機台的參數，主軸轉速、進給率、切削深度和時間進行刀具磨損實際切削的實驗。
根據實驗結果，倒傳遞類神經網路的均方根誤差(RMSE)小於線性迴歸，決定係數(R^2)也達到0.9964，代表倒傳遞神經網路有很好的能力預測刀具磨損，並且應用在CNC工具機上。

For CNC machine tool industry processing products. There are many factors that affect the precision of the surface of the machined workpiece. Tool wear reduces the quality of the product during manufacturing. Machining cutting parameters are important factors affecting machining accuracy and tool wear. Therefore, predicting tool wear can help monitor tool wear and tool utilization.
This paper proposes a backpropagation neural network (BPNN) to predict tool tool wear. When using different cutting parameters. There will be some variation in the wear of the tool. Using the parameters of the tool machine, i.e.
spindle speed, feed, cutting depth and cutting time experiment on actual cutting of tool wear.
According to the experimental results, root mean square error (RMSE) of backpropagation neural network is less than linear regression, the coefficient of determination (R^2) also reached 0.9964. Representing the inverted neural network has a good ability to predict tool wear.

摘要............i
Abstract............ii
Acknowledgements............iii
Contents............iv
List of Tables............vii
List of Figures............viii
Chapter 1 Introduction............1
1.1 Research Background............1
1.2 Research motivation and purpose............ 1
1.3 Literature Review............2
1.4 Organization of Dissertation............10
Chapter 2 Tool Wear of CNC Machine Tool............11
2.1 Detection and monitoring method of Tool Wear of Machine Tool............11
2.1.1 Direct measurement............11
2.1.2 Indirect measurement............13
2.1.3 Machine internal signal measurement............16
2.2 Cutting force............16
2.3 Causes of Tool wear............17
2.3.1 Tool wear form............19
2.3.2 Stage of tool wear...........20
2.3.3 Cutting parameters and formula............21
Chapter 3 Measurement of Tool Wear............23
3.1 Experiment apparatus............23
3.1.1 Machine tool specifications............24
3.1.2 Tool specifications............26
3.1.3 Z–axis setting............26
3.1.3.1 Model and specifications............26
3.1.3.2 Z-axis setter set zero offset............27
3.1.4 Blum tool setter............29
3.1.4.1 Model and specifications............30
3.1.4.2 Tool wear measurement............31
3.1.5 Workpiece material............33
3.2 Experimental planning and process............34
3.3 Experimental parameters............ 37
Chapter 4 Building of Tool Wear Prediction Model............38
4.1 Backpropagation neural network (BPNN)............39
4.1.1 Theory of backpropagation neural network............39
4.1.2 Mathematical derivation of backpropagation neural network............42
4.2 Linear regression............45
Chapter 5 Analysis of Experimental Results of Tool Wear Prediction Model............47
5.1 Proposed backpropagation neural network............48
5.2 Orthogonal table of experimental parameters............48
5.3 Experimental result data of tool wear............50
5.4 Backpropagation neural network prediction............51
5.5 Comparison of backpropagation neural network parameters............55
Chapter 6 Conclusions and Future Works............61
6.1 Conclusions............61
6.2 Future Works............62
Reference............63
Appendix............70
Abstract............73
Chapter 1 Introduction............74
Chapter 2 Tool Wear of CNC Machine Tool............75
Chapter 3 Measurement of Tool Wear............75
Chapter 4 Building of Tool Wear Prediction Model............76
Chapter 5 Analysis of Experimental Results of Tool Wear Prediction Model............76
Chapter 6 Conclusions............77

[1]R. Corne, C. Nath, M. E. Mansori, and T. Kurfess, “Study of spindle power data with neural network for predicting real-time tool wear/breakage during inconel drilling,” Journal of Manufacturing Systems, vol.43, pp.287-295, Feb.2017.
[2]K. Patra, A.K. Jha, T. Szalay, J. Ranjan, and L. Monostori, “Artificial neural network based tool condition monitoring in micromechanical peck drilling using thrust force signals,” Precision Engineering , vol.48, pp.279-291, Apr.2017.
[3]B. Jose, K. Nikita, T. Patil, S. Hemakumar, and Dr. P. Kuppan, “Online monitoring of tool wear and surface roughness by using acoustic and force sensors,” Materials Today: Proceedings , vol.5, pp.8299-8306, 2018.
[4]K. Patra, A. Jha, and Tibor Szalay, “Tool condition monitoring in micro-drilling using vibration signals and artificial neural network,” International Conference on Industrial Engineering, Applications and Manufacturing, pp.1-5, May 2017.
[5]G.R. Thellaputta, C. S. Raju, P. S. C. Bose, and C.S.P. Rao, “Adaptive neuro fuzzy model development for prediction of cutting forces in milling with rotary tools,” Materials Today: Proceedings, vol.5, no.2, pp.7429-7436, 2018.
[6]T. Ozel and Y. Karpat, “Predictive modeling of surface roughness and tool wear in hard turning using regression and neural networks, ” International Journal of Machine Tools & Manufacture , vol.45, no.4-5, pp.467-479, Apr.2005.


[7]T. Mikołajczyk, K. Nowicki, A. Bustillo, and D. Yu Pimenov, “Predicting tool life in turning operations using neural networks and image processing,” Mechanical Systems and Signal Processing , vol.104, pp.503-513, May.2018.
[8]N. Ghosh , Y.B. Ravi , A. Patra , S. Mukhopadhyay , S. Paul , A.R. Mohanty, and A.B. Chattopadhyay, “Estimation of tool wear during CNC milling using neural network-based sensor fusion,” Mechanical Systems and Signal Processing , vol.21, pp.466-479, Jan.2007.
[9]M. Malekian, S.S. Park, and M.B.G. Jun, “Tool wear monitoring of micro-milling operations,” Journal of Materials Processing Technology, vol.209, pp.4903-4914, Jan.2009.
[10]C. Drouillet, J. Karandikar, C. Nath, A.C. Journeaux, M.E. Mansori, and T. Kurfess, “Tool life predictions in milling using spindle power with the neural network technique,” Journal of Manufacturing Processes , vol.22, pp.161-168, Apr.2016.
[11]J. Liu and G. Li, “Study on Tool Wear Identifying Based on Fuzzy Neural Network,” 2010 Sixth International Conference on Natural Computation, 2010.
[12]R.J. Kuo, “Multi-sensor integration for on-line tool wear estimation through artificial neural networks and fuzzy neural network,” Engineering Applications of Artificial Intelligence, vol.13, pp.249-261, Jan.2000.
[13]S. Karam, P. Centobelli, D. M. D’Addona, and Roberto Teti, “Online prediction of cutting tool life in turning via cognitive decision making,” Procedia CIRP , vol.41, pp.927-932, 2000.
[14]Ahmed A.D. Sarhan, “Adaptive neuro-fuzzy approach to predict tool wear accurately in turning operations for maximum cutting tool utilization,” IFAC-PapersOnLine, vol.48, pp.93-98, 2015.
[15]L.H. Saw , L.W. Ho , M.C. Yew , F. Yusof , N.A. Pambudi , T.C. Ng, and M.K. Yew, “Sensitivity analysis of drill wear and optimization using Adaptive Neuro fuzzy - genetic algorithm technique toward sustainable machining,” Journal of Cleaner Production , vol.172, pp.3289-3298, Jan.2018.
[16]W.Y. Chang, S.J. Wu, and B.S. Lin, “Intelligent prediction platform of lathe machine based on backpropagation neural network,” 2018 IEEE International Conference on Advanced Manufacturing, pp.280-283, 2018.
[17]D.F. Hesser and B. Markert, “Tool wear monitoring of a retrofitted CNC milling machine using artificial neural networks,” Manufacturing Letters, vol.19, pp.1-4, Jan.2019.
[18]M.V. Vardhan, G. Sankaraiah, and M. Yohan, “Prediction of Surface roughness & Material Removal Rate for machining of P20 Steel in CNC milling using Artificial Neural Networks,” Materials Today: Proceedings , vol. 5,pp. 18376-18382, 2018.
[19]W. Wu and Y.M. Zhang, “Application of genetic algorithm optimizing neural networks in machining a group of holes,” International Conference on Intelligent Human-Machine Systems and Cybernetics, Nov. 2009.
[20]A. T. C. Goh, “Back-propagation neural networks for modeling complex systems,” Artificial Intelligence in Engineering, vol.9, pp.143-151, 1995.
[21]E. Akarslan and F.O. Hocaoglu, “Deformation classification of cutting discs using artificial neural networks,” IEEE 22nd Signal Processing and Communications Applications Conference, pp. 622-625, June.2014.
[22]B.Qin, Y.Yang, Y.Lin, and J.Wang, “Improved particle swarm optimized fuzzy neural network based fault diagnosis for computer numerical control machine,” IEEE International Conference on Mechatronics and Automation, pp. 1442-1447, Aug.2015.
[23]I. Kandilli, M. Sonmez, H.M. Ertunc, and B. Cakir, “Online monitoring of tool wear in drilling and milling by multi-sensor neural network fusion,” IEEE International Conference on Mechatronics and Automation, pp. 1388-1394, Aug.2007.
[24]G. Guo and X. Mao, “Research on the milling tool monitoring system based on wavelet neural network,” International Conference on Electronic &Mechanical Engineering and Information Technology, Aug.2011.
[25]Z.N. Shu and Y.Y. Bang , “The application of BP Neural Network model of DNA-Based Genetic Algorithm to monitor cutting tool wear,”2009 International Conference on Measuring Technology and Mechatronics Automation , pp. 338-341, 2009.
[26]K. Martinsen, J. Downey, and I. Baturynska, “Human-machine interface for artificial neural network based machine tool process monitoring,” 48th CIRP Conference on MANUFACTURING SYSTEMS - CIRP CMS 2015 , vol.41, pp. 933-938, 2016.
[27]L.X.Gong and M.Z. Yang, “Application of metallic material machining based on neural network predictive theory,” 2010 Third International Conference on Information and Computing, pp.38-41, 2010.
[28]H. Gao, M. Xu, Y.C. Su, P. Fu, and Q. Liu, “Experimental study of tool wear monitoring based on neural networks,” 2008 7th World Congress on Intelligent Control and Automation ,pp.6906-6910, Aug.2008.
[29]B. Kaya ,C. Oysu, and H.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, pp.76-84, Jan.2011.


[30]R. J. Kuo and P. H. Cohen, “Intelligent tool wear estimation system through artificial neural network and fuzzy modeling,” Artificial Intelligence in Engineering, vol.12, no.3, pp.229-242, July.1998.
[31]M. H. F. A. Hazza, E. Y. T. Adesta, and M. H. Hasan, “Simulation of tool life for ceramic with negative rake angle using neural network,”2013 International Conference on Advanced Computer Science Applications and Technologies, pp.70-73, Dec.2013.
[32]G. Luetzig, M. Sanchez-Castillo, and R. Langari, “On tool wear estimation through neural networks,”Proceedings of International Conference on Neural Networks (ICNN'97), vol.4, pp.2359-2363, June.1997.
[33]C. Chungchoo and D. Saini, “On-line tool wear estimation in CNC turning operations using fuzzy neural network model,” International Journal of Machine Tools & Manufacture, vol.42, no.1, pp.29-40, Jan.2002.
[34]Y.Yao, X.Li, and Z.Yuan, “Tool wear detection with fuzzy classification and wavelet fuzzy neural network,” International Journal of Machine Tools & Manufacture, vol.39, no.10, pp.1525-1538, Oct.1999.
[35]H. Gao, M. Xu, X. Shi, and H. Huang, “Tool wear monitoring based on localized fuzzy neural networks for turning operation, “2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery, pp.417-420, Aug.2009.
[36]C. Sanjay, M.L. Neema, and C.W. Chin, “Modeling of tool wear in drilling by statistical analysis and artificial neural network, “Journal of Materials Processing Technology, vol.170, no.3, pp.494-500, Dec.2005.
[37]A. Iqbal, N. He, N. U. Dar, and L. Li, “Comparison of fuzzy expert system based strategies of offline and online estimation of flank wear in hard milling process,” Expert Systems with Applications, vol.33, no.1, pp.61-66, July.2007.
[38]P. Fu, W. Li, and L. Guo, “Fuzzy clustering and visualization analysis of tool wear status recognition,” 2011 International Conference on Power Electronics and Engineering Application, vol.23, pp.479-486, 2011.
[39]R. Prabha and J. E. R. Dhas, “Fuzzy logic — A decision making tool for wear rate prediction in aluminum composite,”2017 First International Conference on Recent Advances in Aerospace Engineering (ICRAAE), pp.1-4, Mar.2017.
[40]F.R. Biglari and X.D. Fang, “Real-time fuzzy logic control for maximising the tool life of small-diameter drills,” Fuzzy Sets and Systems, vol.72, no.1, pp.91-101, May.1995.
[41]Q.Ren, M.Balazinski, L.Baron, and K.Jemielniak, “TSK fuzzy modeling for tool wear condition in turning processes an experimental study, “Engineering Applications of Artificial Intelligence, vol.24, pp.260-265, Nov.2010.
[42]M. Rizal, J.A. Ghani, M.Z. Nuawi, and C.H.C. Haron, “Online tool wear prediction system in the turning process using an adaptive neuro-fuzzy inference system,” Applied Soft Computing, vol.13, no.4, pp. 1960-1968, Apr.20013.
[43]A.I. Azmi, “Monitoring of tool wear using measured machining forces and neuro-fuzzy modelling approaches during machining of GFRP composites,” Advances in Engineering Software, vol.82, pp.53-64, Jan.2015.
[44]R. Blodorn, M.R. Viotti, and R.B. Schroeter, “Study of the drilling process used in the Hole-drilling Method through thrust force measurement and tool wear analysis,” 23rd ABCM International Congress of Mechanical Engineering, Dec.2015.
[45]D.Kong, Y.Chen, and N.Li, “Gaussian process regression for tool wear prediction,” Mechanical Systems and Signal Processing, vol.104, pp. 556-574, Nov.2017.
[46]H. Shao, H.L. Wang, and X.M. Zhao, “A cutting power model for tool wear monitoring in milling,” International Journal of Machine Tools & Manufacture, vol.44, pp. 1503-1509, Nov.2004.
[47]https://kknews.cc/zh-tw/news/y8x2xrb.html, Apr.2017.