跳到主要內容

臺灣博碩士論文加值系統

(44.201.99.222) 您好!臺灣時間:2022/12/03 23:48
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:郭維峰
研究生(外文):Wei-Feng Kuo
論文名稱:工具機加工性能指標估測:使用實驗設計及數據驅動
論文名稱(外文):Estimation of Milling Performances for CNC Machine Tools Based on Experimental Design and Data-Driven Approach
指導教授:李慶鴻
口試委員:周至宏林俊良陳世樂林正堅
口試日期:2020-01-20
學位類別:碩士
校院名稱:國立中興大學
系所名稱:機械工程學系所
學門:工程學門
學類:機械工程學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:英文
論文頁數:114
中文關鍵詞:CNC工具機性能指標神經網路數學模型優化加工參數智能估測
外文關鍵詞:CNC Machine ToolsPerformance IndexNeural NetworkModel-basedOptimizationMilling ParametersIntelligentEstimation
相關次數:
  • 被引用被引用:3
  • 點閱點閱:186
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
隨著科技的進步,雖然許多新的技術與工具也日新月異,但CNC工具機的地位仍然無可取代,任何產業凡是需要加工製造,都會使用到工具機進行加工。而業界通常會以加工時數、產品的表面粗糙度以及幾何精度作為產品的性能指標,由於每一種產品皆有不同的品質需求,所以會將加工參數進行調整,但卻無法立即評估該參數組合的加工品質,只能經由經驗或者實際測試加工後進行量測,造成不便。
本研究旨在開發利用數據驅動與實驗設計建立工具機加工性能指標預測系統及參數優化系統。首先,由於估測性能指標時須要有各段加工路徑長度及轉彎角度值,需進行NC-code解譯處理;接著分別以空跑(未實際加工)的方式收集不同加工參數下的光學尺數據,經由分析計算獲得相對應之性能指標;而因實際加工量測為少量數據,本文運用倒傳遞類神經網路(back-propagation neural network, BPNN)學習性能指標與加工參數關係,並利用轉移學習(transfer learning)技術將該模型轉移至預測實際加工品質的模型,便可在較少量的數據中順利評估精度與粗糙度。最後,本文利用曲線擬合速度規劃並搭配反應曲面法(response surface method, RSM)估測加工時間。基於上述分析,本文使用已訓練好的估測系統結合粒子群演算法(particle swarm optimization, PSO)及穩健優化法,建立一套智能加工助理,可提供一組符合需求下最快加工參數給使用者,解決調整加工參數不便之議題。最後,由所設計的實驗,驗證本文的預測系統及加工助理的性能。
In general, the machining industry regards the milling cycle time, accuracy, and surface roughness as performance indices of milling products. Users should properly adjust the milling parameters to meet the specific requirements of performances. Therefore, this thesis utilizes experimental design and data-driven approach to establish the estimated system of performance indices of milling products. This system is divided into two models, estimated system of accuracy and surface roughness by neural network and the cycle time estimation by model-based approach. At first, we collect the calculated (without milling data) and measured data by linear scale and measuring instrument, respectively. Then, we adopt the back propagation neural network (BPNN) and the transfer learning approach to obtain the relationship between CNC milling parameters and performance indices. The cycle time estimation refers to the velocity profile and then the response surface method is used to merge other parameters for estimation. Finally, we combine the estimation systems, particle swarm optimization (PSO) algorithm, and robust optimal approach to establish the intelligent milling assistant (IMA). IMA can provide the milling parameters to users for accuracy and surface roughness specification based on minimal cycle time. Finally, we verify our proposed estimation model and IMA by our experiments.
中文摘要 i
Abstract ii
Contents iii
List of Figures v
List of Tables ix
Chapter One Introduction 1
Chapter Two Research Platform and Milling Parameters Analysis 6
2.1. Overview 6
2.2. Specification of CNC Machining Tool System, Cut Tool, and Workpiece 7
2.2.1 Specification of CNC Machining Tool System 7
2.2.2 Cutting Tool and Workpiece Material 8
2.3. Definition of Milling Performance Indices 10
2.4. CNC Milling Parameters Analysis 13
2.5. Conclusions 25
Chapter Three Estimation of Accuracy and Surface Roughness Via Virtual Milling System 26
3.1 Overview 26
3.2 Back Propagation Neural Network 28
3.3 Virtual Milling System for Estimation 31
3.3.1 Experiment Design and Data Collection 32
3.3.2 Virtual Milling System Development 40
3.4 Experimental Results 43
3.5 Conclusions 55
Chapter Four Cycle Time Estimation System 56
4.1 Overview 56
4.2 The Model-based Approximates the Velocity Planning 57
4.3 Create the RSM Model by Other Milling Parameters 62
4.4 Create the RSM for Effect of Speed Profile Interpolation Variation 69
4.5 Cycle Time Estimation System 75
4.6 Experimental Results 77
4.7 Conclusions 80
Chapter Five Intelligent Milling Assistant 81
5.1 Overview 81
5.2 Particle Swarm Optimization Algorithm 83
5.3 Intelligent Milling Assistant System 86
5.4 Experimental Results 89
5.5 Conclusions 91
Chapter Six Conclusions and Future Work 92
6.1. Conclusions 92
6.2. Future Research Directions 94
References 96
Appendix A 103
Appendix B 106
Appendix C 108
Appendix D 110
Appendix E 112
[1]C. H. Yeung, A Three-axis Virtual Computer Numerical-controlled (CNC) System, Master Thesis, University of British Columbia, Machanical Engineering, Vancouver, Canada, 2004.
[2]R. Schmidt, M. Möhring, R. C. Härting, C. Reichstein, P. Neumaier, and P. Jozinović, “Industry 4.0-potentials for Creating Smart Products: Empirical Research Results,” Int. Conf.on Business Information Systems, pp. 16-27, 2015.
[3]J. Lee, B. Bagheri, and H. A. Kao, “A Cyber-physical Systems Architecture for Industry 4.0-based Manufacturing Systems,” Manufacturing Letters, Vol. 3, pp. 18-23, 2015.
[4]W. Tang, G. Yan, X. Xu, D. Yu, Z. Wang, and H. Chu, “A Research on NC Machining Cutting Parameters Optimization,” First Int. Conf. on Information Sciences, Machinery, Materials and Energy, pp. 1791-1797, 2015.
[5]T. Stock and G. Seliger, “Opportunities of Sustainable Manufacturing in Industry 4.0,” Procedia CIRP, Vol. 40, pp. 536-541, 2016.
[6]W. Y. Chang and S. J. Wu, “Investigated Information Data of CNC Machine Tool for Established Productivity of Industry 4.0,” 5th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI), pp. 1088-1092, 2016.
[7]S. H. Suh, S. K. Kang, D. H. Chung, and I. Stroud, Theory and Design of CNC Systems. Springer Science and Business Media, 2008.
[8]P. G. Benardos and G. C. Vosniakos, “Predicting Surface Roughness in Machining: A Review,” Int. J. of Machine Tools and Manufacture, Vol. 43, No. 8, pp. 833-844, 2003.
[9]T. Y. Wu and K. W. Lei, “Prediction of Surface Roughness in Milling Process Using Vibration Signal Analysis and Artificial Neural Network,” Int. J. of Advanced Manufacturing Technology, Vol. 102, No. 1, pp. 305-314, 2019.
[10]S. Lin and M. Chang, “A Study on The Effects of Vibrations on the Surface Finish Using a Surface Topography Simulation Model for Turning,” Int. J. of Machine Tools and Manufacture, Vol. 38, No. 7, pp. 763-782, 1998.
[11]W. Grzesik, “A Revised Model for Predicting Surface Roughness in Turning,” Wear, Vol. 194, No. 1-2, pp. 143-148, 1996.
[12]D. Y. Jang, Y. G. Choi, H. G. Kim, and A. Hsiao, “Study of the Correlation Between Surface Roughness and Cutting Vibrations to Develop an On-line Roughness Measuring Technique in Hard Turning,” Int. J. of Machine Tools and Manufacture, Vol. 36, No. 4, pp. 453-464, 1996.
[13]J. P. Davim, “A Note on the Determination of Optimal Cutting Conditions for Surface Finish Obtained in Turning Using Design of Experiments,” J. of Materials Processing Technology, Vol. 116, No. 2-3, pp. 305-308, 2001.
[14]V. Gopan, K. L. D. Wins, and A. Surendran, “Integrated ANN-GA Approach for Predictive Modeling And Optimization of Grinding Parameters with Surface Roughness as the Response,” Materials Today: Proceedings, Vol. 5, No. 5, Part 2, pp. 12133-12141, 2018.
[15]ASTM International, B209-14 Standard Specification for Aluminum and Aluminum-Alloy Sheet and Plate (Metric), 2014.
[16]ASME, B46.1 Surface Texture (Surface Roughness, Waviness, and Lay), 1995.
[17]J. Raja, B. Muralikrishnan, and S. Fu, “Recent Advances in Separation of Roughness, Waviness and Form,” Precision Engineering, Vol. 26, No. 2, pp. 222-235, 2002.
[18]H. W. Chiu, Intelligent Machining Expert System Based on CNC Controller Parameters and Optimization, Master Thesis, Taiwan National Chung Hsing University, Mechanical Engineering, Taiwan, 2017.
[19]H. W. Chiu and C. H. Lee, “Prediction of Machining Accuracy and Surface Quality for CNC Machine Tools Using Data Driven Approach,” Advances in Engineering Software, Vol. 114, pp. 246-257, 2017.
[20]P. Suresh, P. V. Rao, and S. Deshmukh, “A Genetic Algorithmic Approach for Optimization of Surface Roughness Prediction Model,” Int. J. of Machine Tools and Manufacture, Vol. 42, No. 6, pp. 675-680, 2002.
[21]P. Werbos, Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences, Doctor Thesis, Harvard University, Statistics, USA, 1974.
[22]D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning Representations by Back-propagating Errors,” Nature, Vol. 323, No. 9, pp 533–536, 1986.
[23]M. Riedmiller and H. Braun, “A Direct Adaptive Method for Faster Backpropagation Learning: the RPROP Algorithm,” IEEE Int. Conf. on Neural Networks, pp. 586-591, 1993.
[24]L. Y. Pratt, “Discriminability-based Transfer Between Neural Networks,” Advances in Neural Information Processing Systems, pp. 204-211, 1993.
[25]J. T. Huang, J. Li, D. Yu, L. Deng, and Y. Gong, “Cross-language Knowledge Transfer Using Multilingual Deep Neural Network with Shared Hidden Layers,” IEEE Int. Conf. on Acoustics, Speech and Signal Processing, pp. 7304-7308, 2013.
[26]K. T. Fang, D. K. Lin, P. Winker, and Y. Zhang, “Uniform Design: Theory and Application,” Technometrics, Vol. 42, No. 3, pp. 237-248, 2000.
[27]Y. Wang and K. Fang, “A Note on Uniform Distribution and Experimental Design,” Science Bulletin, No. 6, pp. 485-489, 1981.
[28]K. T. Fang and D. K. Lin, “Ch. 4. Uniform Experimental Designs and Their Applications in Industry,” Handbook of Statistics, Vol. 22, pp. 131-170, 2003.
[29]Y. W. Leung and Y. Wang, “Multiobjective Programming Using Uniform Design and Genetic Algorithm,” IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), Vol. 30, No. 3, pp. 293-304, 2000.
[30]G. Taguchi, “Quality Engineering (Taguchi Methods) for The Development of Electronic Circuit Technology,” IEEE Transactions on Reliability, Vol. 44, No. 2, pp. 225-229, 1995.
[31]B. D. Cobb and J. M. CIarkson, “A Simple Procedure for Optimising the Polymerase Chain Reaction (PCR) Using Modified Taguchi Methods,” Nucleic Acids Research, Vol. 22, No. 18, pp. 3801-3805, 1994.
[32]FANUC, Series 30i/31i/32i/35i-Model B, 2018.
[33]Y. Altintas and S. Tulsyan, “Prediction of Part Machining Cycle Times Via Virtual CNC,” CIRP Annals, Vol. 64, No. 1, pp. 361-364, 2015.
[34]S. Tulsyan, Prediction and Reduction of Cycle Time for Five-axis CNC Machine tools, Master Thesis, University of British Columbia, Machanical Engineering, Vancouver, Canada, 2014.
[35]R. Liñán, M. D. Carmen, and W. P. Heath, “Backlash Compensation for Plants with Saturating Actuators” Proceedings of the Institution of Mechanical Engineers, Part I: J. of Systems Control Engineering, Vol. 231, No. 6, pp. 471-480, 2017.
[36]B. A. Hélouvry, P. Dupont, and C. C. De Wit, “A Survey of Models, Analysis Tools and Compensation Methods for the Control of Machines with Friction,” Automatica, Vol. 30, No. 7, pp. 1083-1138, 1994.
[37]İ. Asiltürk, S. Neşeli, and M. A. İnce, “Optimisation of Parameters Affecting Surface Roughness of Co28Cr6Mo Medical Material During CNC Lathe Machining by Using the Taguchi and RSM Methods,” Measurement, Vol. 78, pp. 120-128, 2016.
[38]N. Senthilkumar, J. Sudha, and V. Muthukumar, “A Grey-fuzzy Approach for Optimizing Machining Parameters and the Approach Angle in Turning AISI 1045 Steel,” Advances in Production Engineering and Management, Vol. 10, No. 4, pp. 195-208, 2015.
[39]M. Vishnu Vardhan, G. Sankaraiah, and M. Yohan, “Optimization of Cutting Parameters and Prediction of Ra and MRR for Machining of P20 Steel on CNC Milling Using Artificial Neural Networks,” Materials Today: Proceedings, Vol. 5, No. 13, Part 3, pp. 27058-27064, 2018.
[40]B. Das, S. Roy, R. N. Rai, and S. C. Saha, “Application of Grey Fuzzy Logic for The Optimization of CNC Milling Parameters for Al–4.5% Cu–TiC MMCs with Multi-performance Characteristics,” Engineering Science and Technology, an Int. J., Vol. 19, No. 2, pp. 857-865, 2016.
[41]G. Kant and K. S. Sangwan, “Predictive Modelling and Optimization of Machining Parameters to Minimize Surface Roughness Using Artificial Neural Network Coupled with Genetic Algorithm,” Procedia Cirp, Vol. 31, pp. 453-458, 2015.
[42]P. J. Ross, Taguchi techniques for quality engineering: loss function, orthogonal experiments, parameter and tolerance design (No. TS156 R12), New York: Mc Graw-Hill, 1988.
[43]Q. Yi, C. Li, Y. Tang, and X. Chen, “Multi-objective Parameter Optimization of CNC Machining for Low Carbon Manufacturing,” J. of Cleaner Production, Vol. 95, pp. 256-264, 2015.
[44]M. Nataraj, K. Balasubramanian, and D. Palanisamy, “Optimization of Machining Parameters for CNC Turning of Al/Al2O3 MMC Using RSM Approach,” Materials Today: Proceedings, Vol. 5, No. 6, Part 2, pp. 14265-14272, 2018.
[45]M. Patel, “Optimization of CNC TC Process Parameters Using PCA-based Taguchi Method,” Int. J. of Innovative Research in Science, Engineering and Technology, Vol. 5, No. 4, pp. 4722-4731, 2016.
[46]A. Saravanakumar, S. C. Karthikeyan, B. Dhamotharan, and V. G. kumar, “Optimization of CNC Turning Parameters on Aluminum Alloy 6063 using TaguchiRobust Design,” Materials Today: Proceedings, Vol. 5, No. 2, Part 2, pp. 8290-8298, 2018.
[47]C. Caraveo, F. Valdez, and O. Castillo, “Optimization of Fuzzy Controller Design Using a New Bee Colony Algorithm with Fuzzy Dynamic Parameter Adaptation,” Applied Soft Computing, Vol. 43, pp. 131-142, 2016.
[48]C. T. Kuo and C. H. Lee, “Network-based Type-2 Fuzzy System with Water Flow Like Algorithm for System Identification and Signal Processing,” Smart Science, Vol. 3, No. 1, pp. 21-34, 2015.
[49]S. S. Yeh and J. I. Lee, “Optimal Tuning of Control Gains for Rigid Tapping Processes Using a Learning Automata Methodology,” IEEE Congress on Evolutionary Computation , pp. 3248-3255, 2015.
[50]L. Zuo, L. Shu, S. Dong, C. Zhu, and T. Hara, “A Multi-objective Optimization Scheduling Method Based on The Ant Colony Algorithm in Cloud Computing,” IEEE Access, Vol. 3, pp. 2687-2699, 2015.
[51]Y. S. a. R. Eberhart, “A Modified Particle Swarm Optimizer,” IEEE Int. Conf. on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence, pp. 69-73, 1998.
[52]J. Kennedy and R. Eberhart, “Particle Swarm Optimization,” Proceedings of ICNN''95 - International Conference on Neural Networks, Vol. 4, pp. 1942-1948, 1995.
[53]Y. Shi and R. C. Eberhart, “Empirical Study of Particle Swarm Optimization,” Congress on evolutionary computation-CEC99 (Cat. No. 99TH8406), Vol. 3, pp. 1945-1950, 1999.
[54]A. Ratnaweera, S. K. Halgamuge, and H. C. Watson, “Self-Organizing Hierarchical Particle Swarm Optimizer with Time-Varying Acceleration Coefficients,” IEEE Transactions on Evolutionary Computation, Vol. 8, No. 3, pp. 240-255, 2004
[55]C. N. Ko, Y. P. Chang, and C. J. Wu, “An Orthogonal-Array-Based Particle Swarm Optimizer with Nonlinear Time-Varying Evolution,” Applied Mathematics Computation, Vol. 191, No. 1, pp. 272-279, 2007.
[56]ISO, 286-1 Geometrical Product Specification (GPS) ISO Code System for Tolerances on Linear Sizes Part 1: Basis of Tolerances, Deviations and Fits, 2010.
[57]J. Tsai, K. Lee, and J. Chou, “Robust Evolutionary Optimal Tolerance Design for Machining Variables of Surface Grinding Process,” IEEE Transactions on Industrial Informatics, Vol. 10, No. 1, pp. 301-312, 2014.
[58]A. K. Khan, A. K. Biradar, Y. Y. Dalal, and S. S. Mahboob, “A Review on Optimisation of CNC End Milling Machining Parameters,” Int. J. of Innovative Research in Science, Engineering and Technology, Vol. 6, No. 6, pp11651-11656, 2017.
[59]J. Beck, P. Hellekalek, P. Hickernell, G. Larcher, P. L''Ecuyer, H. Niederreiter, S. Tezuka, C. Xing, Random and Quasi-Random Point Sets, Vol. 138, New York: Springer Science and Business Media, 2012.
[60]K. T. Fang, M. Q. Liu, H. Qin, and Y. D. Zhou, Theory and Application of Uniform Experimental Designs, Vol. 221, Singapore: Springer, 2018.
電子全文 電子全文(網際網路公開日期:20230204)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊