成形铣刀状态分析神经网络模型的研究与仿真
|
摘要
随着制造业自动化程度的不断提高，带来许多制造中存在的需解决的新问题，其中包括刀具磨损、破损。在早期的机械加工中，全凭操作人员观察刀具，更换刀具，但在现代化、连续自动化生产系统中，刀具的破损不仅会导致机床的功能失效，还会构成整个系统的故障。因此，预测刀具的磨损和破损的产生，显得十分紧迫。
本文建立了成形铣刀状态分析的神经网络模型。首先对铣刀状态进行了分类，描述了各种状态的特征，并对影响因素进行了详细的分析。其次，针对成形铣刀常见的典型的四类状态，选取了与刀具状态密切相关的特征物理量作为神经网络的学习样本，即声发射信号、切削力信号、功率信号等。
神经网络良好的非线性逼近能力、泛化功能可对铣刀磨损状态进行分析。神经网络通过一系列学习样本的训练来使其具有诊断功能。本文建立了神经网络模型，并对模型的建立进行了充分的分析。由于神经网络结构的可拓展性，此模型可用于其它铣刀状态的分析。借助于MATLAB神经网络工具箱对训练好的网络进行仿真，得出各种敏感特征参数对成形铣刀状态影响的仿真曲线。
通过该项目的研究，提供用于成形铣刀状态分析的模型，证明利用神经网络模型对成形铣刀状态的诊断是完全可行的。由于神经网络结构的可拓展性，对其它刀具状态的诊断也成为可能，研究证明该模型能有效地提高加工质量及效率。
Along with automation in manufacturing industry, many industry problems have been generated and include tool wear and failure. The operate-person observed tool and replaced it in the early period of machining. However, in automatic manufacturing system, the tool-failure causes invalid of machine function and the whole system's failure. Therefore, the prediction of tool wear and failure is very urgent.
In this paper, the condition analysis of shape-milling tool is set up based on artificial neural network. First of all, the conditions are classed and kinds of features are described and influence factors are detailed analyzed. Moreover, the feature physical parameters are selected in view of four typical conditions of shape-milling tool, namely acoustic emission signal, cutting force signal and power signal.
The neural network can analyze shape-milling tool condition because of better nonlinear approachable and generalization ability. It diagnoses function through serious training of learning samples. The neural network model is set up and analyzed. The model can use to analyze other milling tool condition due to expand. The simulation graphs are drawn by means of MATLAB neural network toolbox.
The research provide neural network model of shape-milling tool condition. The model is completely possible to analyze shape-milling tool condition, Because neural network construction's expand, it can be used in other tool condition. The model improves machining quality and efficiency.
本文建立了成形铣刀状态分析的神经网络模型。首先对铣刀状态进行了分类，描述了各种状态的特征，并对影响因素进行了详细的分析。其次，针对成形铣刀常见的典型的四类状态，选取了与刀具状态密切相关的特征物理量作为神经网络的学习样本，即声发射信号、切削力信号、功率信号等。
神经网络良好的非线性逼近能力、泛化功能可对铣刀磨损状态进行分析。神经网络通过一系列学习样本的训练来使其具有诊断功能。本文建立了神经网络模型，并对模型的建立进行了充分的分析。由于神经网络结构的可拓展性，此模型可用于其它铣刀状态的分析。借助于MATLAB神经网络工具箱对训练好的网络进行仿真，得出各种敏感特征参数对成形铣刀状态影响的仿真曲线。
通过该项目的研究，提供用于成形铣刀状态分析的模型，证明利用神经网络模型对成形铣刀状态的诊断是完全可行的。由于神经网络结构的可拓展性，对其它刀具状态的诊断也成为可能，研究证明该模型能有效地提高加工质量及效率。
Along with automation in manufacturing industry, many industry problems have been generated and include tool wear and failure. The operate-person observed tool and replaced it in the early period of machining. However, in automatic manufacturing system, the tool-failure causes invalid of machine function and the whole system's failure. Therefore, the prediction of tool wear and failure is very urgent.
In this paper, the condition analysis of shape-milling tool is set up based on artificial neural network. First of all, the conditions are classed and kinds of features are described and influence factors are detailed analyzed. Moreover, the feature physical parameters are selected in view of four typical conditions of shape-milling tool, namely acoustic emission signal, cutting force signal and power signal.
The neural network can analyze shape-milling tool condition because of better nonlinear approachable and generalization ability. It diagnoses function through serious training of learning samples. The neural network model is set up and analyzed. The model can use to analyze other milling tool condition due to expand. The simulation graphs are drawn by means of MATLAB neural network toolbox.
The research provide neural network model of shape-milling tool condition. The model is completely possible to analyze shape-milling tool condition, Because neural network construction's expand, it can be used in other tool condition. The model improves machining quality and efficiency.
引文
[1] James.W. Psychology.Holt.New York,1890.
[2] Mclulloch W.W.&Pitts W..A logic calculus of the ideas imminent in neurons activity. Balletin of Math.Bio. 1943No.5.115-133.
[3] Hebb.D.O. The Organization of Behavior. Wiley,New York,1949.
[4] Rosenblatt.F. Principles of Neurodynamics, New York, Spartan Book,1962.
[5] Widro B. & Hoff.M.E. Adaptive Switching Circuits,1960 IRE WESCON Convention Record: Part 4,Computers:Man-Machine System, Los Angeles, 1960.
[6] Minsky M.L. & Papert S.A., Percepetion. The MIT Press,Cambridge,MA,1969.
[7] Grossberg,S. Some network that can leam, remember and reproduce any number of complicated space-time pattern. Journal of Math. and Math. 1969,Vol 19,53-91.
[8] Kohonen T., Associative Memory, A system Theory Approach. Springer, New York, 1977
[9] Kohonen T., Self-Organization and associative Memory.Springer, Berlin,1984
[10] Anderson J. & Rosenfeld,E. Nearcomputing,MTT-Press, 1988
[11] Kohonen,T. Correlation Matrix Memories, IEEE Tran. on Computers Holland, 1982
[12] Fukushima.K. Recognization:a self-organizing neural network model for a mechanism of pattern recognization unaffected by shift position. Biol.Cyber, 1980, Vol 36,No.4,193-220.
[13] Fukushima K. & miyake S.. Recognization:a new algorithm for pattern recognization tolerant of deformation and shifts in position. Pattern Recognition, 1982,Vol. 15,No.6,455-469.
[14] Fukshima K.,Mecognitron:A hierarchical neural network model of visual pattern recognization, Neural Networks, 1988,Vol.1,No.2,
[15] Amari S. et al,Mathematical theory on formation of category detecting nerve cell' s.Biol.Cybern, 1978,Vol.29,127-136.
[16] Hopfield J.J., Neural networks and physical systems with emergent collective computational abilities.Proc.Acad.Sci,USA, 1982.Vol.79,2554-2558.
[17] Hopfield,J.J. Neurons with graded response have collective computional properties like those of two-state neuron.. Proc. Natl.Acad.Sci, 1984Vol.81,3088-3092.
[18] Hopfield J.J. & Tank D.W.,Neural computation of decisions optimization problem.Biol.Cybem, 1985,Vol. 52,141-152.
[19] HopfieldJ.J&Tank D.W.,Computing with neural circuits: A model.Sci. 1986,Vol. 233,625-633,
[20] Hiton G.E.,T.J.Sejowskii and D.H.Ackley, Boltzmann machine: constraint satisfaction networks that leam.CMV-CS-84-119,Cameie-Mellon Uni., 1984.
[21] Ackley D.H., Hiton G.E.&Sejnowskii,T.J. Learning algorithm for boltzmann machine.Cognitive Sciences, 1988Vol.9,147-169.
[22] Rumelhart D.E. & Mcclelland J.L.,Parallel Distributed Processing,MIT press, 1986.
[23] Chun L.O. and Lin Yang, Cellular Neural Network Theory, IEEE Trans,on CAS 1988,Vol.35,No. 10,1257-1271.
[24] Pham D.Y.,Liu xing,Neural Networks for Identification,Predicition and Control,Springer, Berlin, 1995
[25] Omatu,khaalid M. and Yusof R., Neuro-Control and Its Applications, Springer, Berlin, 1995
[26] 丁国锋，高阶神经网络控制理论机器在机电系统中的应用研究，西安交通大学博士学位论文，1997。
[27] Etxebarria V., Adaptive Control of Discrete Systems Using Neural Networks, IEEE Proc.-Control Theory Appl, 1994, Vol. 141,No.4,209-215.
[28] 吴耀军、陶宝祺、B样条小波神经网络，模式识别与人工智能，1996，Vol(9)，228-233。
[29] Liang Jin,EN.nikiforuk & Gupta M.M., Adaptive Control of Discrete-time Nonlinear systems Using Recurrent Neural Networks, IEE Proc., Control Theory Appl. 1994,Vol141,169-176。
[30] Venugopal K.P., Pandya A.S. & Sudhakar,R. A Recurrent Neural Network Controller and learning algorithm for The On-Line Learning Control of Autonomous Underwater Vehicles ,Neural Networks, 1994, Vol7883-846.
[31] Liang Jin. Nikiforuk P.N., Gupta,M.M. Dynamic Recurrent Neural Networks for Unknown Nonlinear Systems,ASME Journal of Dynamic Systems, Measurement and Control, 1994,Vol116,567-567.
[32] Zhu,C. Paul F.U..A Fourier Series Neural Network and Its Application and Control, 1995,Vol. 117,253-261.
[33] 焦本成编著，神经网络计算。西安电子科技大学出版社，1993。
[34] 胡守仁主编，神经网络应用技术。国防科技大学出版社，1993。
[35] Zadeh L A. Fuzzy Logic, Neural Networks and Soft Computing. Communications of the ACM, 1994.Vo137(3)77-86.
[36] Laura I.Burke. Competitive Learning Based Approaches to Tool-wear Identification. IEEE Transactions on systems, Man and Cyberetics.Vol22(3)559-564
[37] 章伟、罗干英、李步青，神经网络在线切割加工中的应用，机械工业自动化，Vol16(4))．33-36，1994。
[38] 李旭东，神经网络技术在切削用量选择中的应用(硕士论文)，山东工业大学，1998。
[39] 刘艳明，黄一夫，杨叔子，机械加工过程中的神经网络最优化自适应控制，机械工业自动化，1994，Vol 16(2)。
[40] 朱名铨，党志斌，智能制造系统质量控制的神经网络方法研究，航空学报，1997，Vol18(5)603-606。
[41] 张连洪，朱克珊，吴华杰等，分层实体制造快速成型工艺参数的人工神经网络预测，中国机械工程，1999，Vol(12)．1347-1348。
[42] 傅志红，王洪，彭玉成，人工神经网络在智能机械设计中的应用，机械设计，2000，Vol(11)10-12。
[43] 钟秉林，黄仁主编，机械状态诊断学，北京：机械工业出版社．1997。
[44] Altintas Y., I. Yellowley and J. Tlusty. The Detection of tool
breakage in milling operations. Trans. ASME 110(1988):271-277
[45] Tansel I.N. and Mclaughlin C. Identification of tool breakage with time series analysis in milling operations. In Control of Manufacturing process, ASME, 1991, Vol52:59-65
[46] 王忠民，王信义，杨大勇等，刀具磨损状态在线监测技术，制造技术与机床，2000，(6)40-41。
[47] 陈爱弟，王信义，王忠民等，用于监测刀具磨损的声发射(AE)特征优选方法，北京理工大学学报，2000，Vol20(3)270-275。
[48] 陈爱弟，王信义，王忠民等，基于模糊聚类的刀具磨损量在线监测方法，北京理工大学学报．2000，Vol30(3)276-280。
[49] 张昆，宋千，郝晓红，金属切削刀具磨损的监控和预报研究，中国机械工程，1994 Vol5(6)61-62。
[50] 胡建军，王叔淳，现代智能制造中的关键技术研究综述，中国机械工程，2000，Vol11(7)：828-835
[51] 董选明，裘丽华，王占林等，机电控制系统状态诊断的回顾与展望，中国机械工程，1998，Vol9(10)63-66。
[52] Rangwal S. and Dornfeld D.. Sensor Integration Using Neural Network for Intelligent Tool Condition Monitoring. ASME, August. Journal of Engineering for Industry, 1990,112(2):219-228。
[53] Chryssonris J. and Gomrose M..Sensor Integration for Tool Wear Estimation in Maching. Proc. Symosium Sensors and Controls for Manufacturing. New York: ASME, 1988.123。
[54] Dornfeld D.. Neural Network Sensor fusion for Tool Condition Monitoring. Annals of the CIRP, 1990,39(1):101-105。
[55] Purushothaman S. and Srinivasa Y.G.. A Back-propagation Algorithm Applied to Tool Wear Monitoring. Int. j. Mach. Tools Manufact, 1994,34(5): 625-631。
[56] TarngY. S. andHseihY. W.. Sensing Tool Breakage in Face Milling with a Neural Network. Int. J. Mach. Tools Manufact, 1994,34(3)。
[57] Tansel I.N. and Mclaughlin C.. On-line monitoring of tool breakage with unsupervised control network. Trans. North American Manufacturing Research Institute of SME, May 1991:364-370。
[58] Tansel I.N. and Mclaughlin C.. monitoring of tool breakage with restricted coulomb energy type neural network. Sensors, Control and Quality Issues in Manufacturing, ASME, (1991),Vol. 55:59-65。
[59] Tansel I.N. and Mclaughlin C.. Detection of tool failure in end milling with wavelet transformations and neural network. Int. J. Mach. Tools Manufact, 1994,35(8): 1137-1147。
[60] 牟建强，艾兴，李兆前等，刀具耐用度变动系数的BP神经网络预报技术，山东工业大学学报，1996，Vol26(3)201-205。
[61] 叶伟昌，刀具切削性能可靠性指标的评定方法，组合机床与自动化加工技术，1991，Vol(2)34-38。
[62] 唐英，孙荣平，陈克兴等，刀具切削状态智能监测系统研究，组合机床与自动化加工技术，1995，Vol(8)23-27。
[63] 游淳，翁世修，基于神经网络的刀具状态实时监控系统，组合机床与自动化加工技术，1995，Vol29(9)32-37。
[64] 杨青，姚英学，袁哲俊等，模糊神经技术在刀具状态检测中的应用，哈尔滨工业大学学报，1997，Vol(6)34-37。
[65] Y. Altinas and I. Yellowlay. In-process detection of tool failture in milling using cutting force models. Journal of Engineering for Industry, May, 1989,111(5):149-157.
[66] 刘晓东，基于切削力的铣刀磨损在线监测研究，机械制造，1998，Vol 10(37)28-31。
[67] 邵华，林益耀，铣削功率信号试验分析，组合机床与自动化加工技术，1998(8)。
[68] 刘晓东，自回归算法在铣刀破损监测中的应用，组合机床与自动化加工技术，1999，3，27-32。
[69] 程光，万军，铣刀破损监测方法的研究，机械工艺师，1998，4，32-34。
[70] 郭兴，杜润生，杨叔子，基于人工神经网络的铣刀破损功率监测，1996，Vol6(24)47-49。
[71] 汪朝军，刘艳明，杨叔子，铣削加工过程的自适应最优控制，华中理工大学学报，1997 Vol25(10)7-9。
[72] SaLje，E，精密磨削中的一些重要关系，磨削过程的适应控制及磨削机理，上海机床厂磨床研究所印，1976，12。
[73] 杨荣福，董申，金属切削原理，机械工业出版社，1988。
[74] Tonshoff HK，砂带磨削过程中接触轮产生的噪声与振动机床译丛，1983，2。Malkin S.and Cook.N.H.The Wear Grinding Wheels, Part Ⅰ. Attritious Wear Trans of ASME 93B 1971.p. 1120-1128。
[75] 郭兴，杜润生，杨叔子，基于人工神经网络的铣刀破损功率监测，华中科技大学学报，1996，6，Vol24(6)6，47-49。
[76] 程光，万军，铣刀破损监控方法的研究，机械工艺师，1998，4，32-34。
[77] 刘晓东，基于切削力的铣刀磨损在线检测研究，
[78] 刘晓东，自回归算法在铣刀破损检测中的应用，组合机床与自动化加工技术，1999，3，27-32。
[79] 乐总谦，金属切削刀具，机械工业出版社，2001。
[80] 李造鼎，李锡润，虞和济，故障诊断的声学方法，冶金工业出版社，1989。
[81] Rangwala S, Domfeld DA. Sensor integration using neural network for intelligent tool condition monitoring. Trans of ASME Journal of Engineering for Industry, 1990,Vol112(8);219-228.
[82] Waschkies E, Sklarczyk C,Hepp K, Tool wear monitoring at trtning .Trans of ASME, Journal of Engineering for Industry, 1994, Vol 116(9);512-524.
[83] 赵彦玲，董丽华，严复钢，刀具磨损的声发射特性，机械工程师，1996，6，8-9。
[84] 王忠民，王信义，杨大勇等，刀具磨损状态在监测技术，制造技术与车床，2000，6，40-42。
[85] 王信义，徐春广等，自动化加工中刀具破损实时监测方法研究，北京理工大学学报，1995，Vol 15(3)。
[86] 陈超，徐建林，黄建龙，基于人工神经网络的刀具状态监测系统，机械工
程学报，2002，Vol 8(38)135—138。
[87] 史洪志，金属切削理论与实践，北京出版社，1980。
[88] .Noori-Khajavi A.Frequency and time domain analyses of sensor signals in drilling (part one:corretation with drill wear).International Journal of Machine Tools and Manufacture, 1995,35(b):775～794。
[89] Andreasen JL,Chiffer D Automatic chip-breakage detection in turning by frequency analysis of cutting force .Annals of the CIRP, 1993,42(1):45～48。
[90] 李锡文，杜润生、杨叔子，铣刀磨损过程中铣削力与磨损面积分析，华中理工大学学报，1998，2(26)，45～48。
[91] 张立明，人工神经网络的模型及其应用，复旦大学出版，1994。
[92] D.E.Rumelhart&J.L.Mcclelland,Parallel Distributed Processing,MIT Press, 1986.
[93] R.Hecht-Nielsen. Theory of The Back Propagation Neural Network.Proc.of IJCNN. 1989,Vol(1):593～603。
[94] R.CEberhart and R.W.Dobbins,Neural Network Pc tools,Academic Press, 1990.
[95] 李士勇，模糊控制，神经网络和智能控制论，哈尔滨工业大学出版社，1996。
[96] 孙增析，张再兴，邓志东，智能控制理论与技术，清华大学出版社，广西科学技术出版社，1997。
[97] 何振亚，神经智能，湖南科学技术出版社，1997。
[98] 王永骥，涂健，神经网络控制，机械工业出版社，1998。
[99] A.Cichocki,R.Vnbehauen. Neural Networks for Optimization and SignalProcessing. England: John wilcy&Sons Ltd. 1993.
[2] Mclulloch W.W.&Pitts W..A logic calculus of the ideas imminent in neurons activity. Balletin of Math.Bio. 1943No.5.115-133.
[3] Hebb.D.O. The Organization of Behavior. Wiley,New York,1949.
[4] Rosenblatt.F. Principles of Neurodynamics, New York, Spartan Book,1962.
[5] Widro B. & Hoff.M.E. Adaptive Switching Circuits,1960 IRE WESCON Convention Record: Part 4,Computers:Man-Machine System, Los Angeles, 1960.
[6] Minsky M.L. & Papert S.A., Percepetion. The MIT Press,Cambridge,MA,1969.
[7] Grossberg,S. Some network that can leam, remember and reproduce any number of complicated space-time pattern. Journal of Math. and Math. 1969,Vol 19,53-91.
[8] Kohonen T., Associative Memory, A system Theory Approach. Springer, New York, 1977
[9] Kohonen T., Self-Organization and associative Memory.Springer, Berlin,1984
[10] Anderson J. & Rosenfeld,E. Nearcomputing,MTT-Press, 1988
[11] Kohonen,T. Correlation Matrix Memories, IEEE Tran. on Computers Holland, 1982
[12] Fukushima.K. Recognization:a self-organizing neural network model for a mechanism of pattern recognization unaffected by shift position. Biol.Cyber, 1980, Vol 36,No.4,193-220.
[13] Fukushima K. & miyake S.. Recognization:a new algorithm for pattern recognization tolerant of deformation and shifts in position. Pattern Recognition, 1982,Vol. 15,No.6,455-469.
[14] Fukshima K.,Mecognitron:A hierarchical neural network model of visual pattern recognization, Neural Networks, 1988,Vol.1,No.2,
[15] Amari S. et al,Mathematical theory on formation of category detecting nerve cell' s.Biol.Cybern, 1978,Vol.29,127-136.
[16] Hopfield J.J., Neural networks and physical systems with emergent collective computational abilities.Proc.Acad.Sci,USA, 1982.Vol.79,2554-2558.
[17] Hopfield,J.J. Neurons with graded response have collective computional properties like those of two-state neuron.. Proc. Natl.Acad.Sci, 1984Vol.81,3088-3092.
[18] Hopfield J.J. & Tank D.W.,Neural computation of decisions optimization problem.Biol.Cybem, 1985,Vol. 52,141-152.
[19] HopfieldJ.J&Tank D.W.,Computing with neural circuits: A model.Sci. 1986,Vol. 233,625-633,
[20] Hiton G.E.,T.J.Sejowskii and D.H.Ackley, Boltzmann machine: constraint satisfaction networks that leam.CMV-CS-84-119,Cameie-Mellon Uni., 1984.
[21] Ackley D.H., Hiton G.E.&Sejnowskii,T.J. Learning algorithm for boltzmann machine.Cognitive Sciences, 1988Vol.9,147-169.
[22] Rumelhart D.E. & Mcclelland J.L.,Parallel Distributed Processing,MIT press, 1986.
[23] Chun L.O. and Lin Yang, Cellular Neural Network Theory, IEEE Trans,on CAS 1988,Vol.35,No. 10,1257-1271.
[24] Pham D.Y.,Liu xing,Neural Networks for Identification,Predicition and Control,Springer, Berlin, 1995
[25] Omatu,khaalid M. and Yusof R., Neuro-Control and Its Applications, Springer, Berlin, 1995
[26] 丁国锋，高阶神经网络控制理论机器在机电系统中的应用研究，西安交通大学博士学位论文，1997。
[27] Etxebarria V., Adaptive Control of Discrete Systems Using Neural Networks, IEEE Proc.-Control Theory Appl, 1994, Vol. 141,No.4,209-215.
[28] 吴耀军、陶宝祺、B样条小波神经网络，模式识别与人工智能，1996，Vol(9)，228-233。
[29] Liang Jin,EN.nikiforuk & Gupta M.M., Adaptive Control of Discrete-time Nonlinear systems Using Recurrent Neural Networks, IEE Proc., Control Theory Appl. 1994,Vol141,169-176。
[30] Venugopal K.P., Pandya A.S. & Sudhakar,R. A Recurrent Neural Network Controller and learning algorithm for The On-Line Learning Control of Autonomous Underwater Vehicles ,Neural Networks, 1994, Vol7883-846.
[31] Liang Jin. Nikiforuk P.N., Gupta,M.M. Dynamic Recurrent Neural Networks for Unknown Nonlinear Systems,ASME Journal of Dynamic Systems, Measurement and Control, 1994,Vol116,567-567.
[32] Zhu,C. Paul F.U..A Fourier Series Neural Network and Its Application and Control, 1995,Vol. 117,253-261.
[33] 焦本成编著，神经网络计算。西安电子科技大学出版社，1993。
[34] 胡守仁主编，神经网络应用技术。国防科技大学出版社，1993。
[35] Zadeh L A. Fuzzy Logic, Neural Networks and Soft Computing. Communications of the ACM, 1994.Vo137(3)77-86.
[36] Laura I.Burke. Competitive Learning Based Approaches to Tool-wear Identification. IEEE Transactions on systems, Man and Cyberetics.Vol22(3)559-564
[37] 章伟、罗干英、李步青，神经网络在线切割加工中的应用，机械工业自动化，Vol16(4))．33-36，1994。
[38] 李旭东，神经网络技术在切削用量选择中的应用(硕士论文)，山东工业大学，1998。
[39] 刘艳明，黄一夫，杨叔子，机械加工过程中的神经网络最优化自适应控制，机械工业自动化，1994，Vol 16(2)。
[40] 朱名铨，党志斌，智能制造系统质量控制的神经网络方法研究，航空学报，1997，Vol18(5)603-606。
[41] 张连洪，朱克珊，吴华杰等，分层实体制造快速成型工艺参数的人工神经网络预测，中国机械工程，1999，Vol(12)．1347-1348。
[42] 傅志红，王洪，彭玉成，人工神经网络在智能机械设计中的应用，机械设计，2000，Vol(11)10-12。
[43] 钟秉林，黄仁主编，机械状态诊断学，北京：机械工业出版社．1997。
[44] Altintas Y., I. Yellowley and J. Tlusty. The Detection of tool
breakage in milling operations. Trans. ASME 110(1988):271-277
[45] Tansel I.N. and Mclaughlin C. Identification of tool breakage with time series analysis in milling operations. In Control of Manufacturing process, ASME, 1991, Vol52:59-65
[46] 王忠民，王信义，杨大勇等，刀具磨损状态在线监测技术，制造技术与机床，2000，(6)40-41。
[47] 陈爱弟，王信义，王忠民等，用于监测刀具磨损的声发射(AE)特征优选方法，北京理工大学学报，2000，Vol20(3)270-275。
[48] 陈爱弟，王信义，王忠民等，基于模糊聚类的刀具磨损量在线监测方法，北京理工大学学报．2000，Vol30(3)276-280。
[49] 张昆，宋千，郝晓红，金属切削刀具磨损的监控和预报研究，中国机械工程，1994 Vol5(6)61-62。
[50] 胡建军，王叔淳，现代智能制造中的关键技术研究综述，中国机械工程，2000，Vol11(7)：828-835
[51] 董选明，裘丽华，王占林等，机电控制系统状态诊断的回顾与展望，中国机械工程，1998，Vol9(10)63-66。
[52] Rangwal S. and Dornfeld D.. Sensor Integration Using Neural Network for Intelligent Tool Condition Monitoring. ASME, August. Journal of Engineering for Industry, 1990,112(2):219-228。
[53] Chryssonris J. and Gomrose M..Sensor Integration for Tool Wear Estimation in Maching. Proc. Symosium Sensors and Controls for Manufacturing. New York: ASME, 1988.123。
[54] Dornfeld D.. Neural Network Sensor fusion for Tool Condition Monitoring. Annals of the CIRP, 1990,39(1):101-105。
[55] Purushothaman S. and Srinivasa Y.G.. A Back-propagation Algorithm Applied to Tool Wear Monitoring. Int. j. Mach. Tools Manufact, 1994,34(5): 625-631。
[56] TarngY. S. andHseihY. W.. Sensing Tool Breakage in Face Milling with a Neural Network. Int. J. Mach. Tools Manufact, 1994,34(3)。
[57] Tansel I.N. and Mclaughlin C.. On-line monitoring of tool breakage with unsupervised control network. Trans. North American Manufacturing Research Institute of SME, May 1991:364-370。
[58] Tansel I.N. and Mclaughlin C.. monitoring of tool breakage with restricted coulomb energy type neural network. Sensors, Control and Quality Issues in Manufacturing, ASME, (1991),Vol. 55:59-65。
[59] Tansel I.N. and Mclaughlin C.. Detection of tool failure in end milling with wavelet transformations and neural network. Int. J. Mach. Tools Manufact, 1994,35(8): 1137-1147。
[60] 牟建强，艾兴，李兆前等，刀具耐用度变动系数的BP神经网络预报技术，山东工业大学学报，1996，Vol26(3)201-205。
[61] 叶伟昌，刀具切削性能可靠性指标的评定方法，组合机床与自动化加工技术，1991，Vol(2)34-38。
[62] 唐英，孙荣平，陈克兴等，刀具切削状态智能监测系统研究，组合机床与自动化加工技术，1995，Vol(8)23-27。
[63] 游淳，翁世修，基于神经网络的刀具状态实时监控系统，组合机床与自动化加工技术，1995，Vol29(9)32-37。
[64] 杨青，姚英学，袁哲俊等，模糊神经技术在刀具状态检测中的应用，哈尔滨工业大学学报，1997，Vol(6)34-37。
[65] Y. Altinas and I. Yellowlay. In-process detection of tool failture in milling using cutting force models. Journal of Engineering for Industry, May, 1989,111(5):149-157.
[66] 刘晓东，基于切削力的铣刀磨损在线监测研究，机械制造，1998，Vol 10(37)28-31。
[67] 邵华，林益耀，铣削功率信号试验分析，组合机床与自动化加工技术，1998(8)。
[68] 刘晓东，自回归算法在铣刀破损监测中的应用，组合机床与自动化加工技术，1999，3，27-32。
[69] 程光，万军，铣刀破损监测方法的研究，机械工艺师，1998，4，32-34。
[70] 郭兴，杜润生，杨叔子，基于人工神经网络的铣刀破损功率监测，1996，Vol6(24)47-49。
[71] 汪朝军，刘艳明，杨叔子，铣削加工过程的自适应最优控制，华中理工大学学报，1997 Vol25(10)7-9。
[72] SaLje，E，精密磨削中的一些重要关系，磨削过程的适应控制及磨削机理，上海机床厂磨床研究所印，1976，12。
[73] 杨荣福，董申，金属切削原理，机械工业出版社，1988。
[74] Tonshoff HK，砂带磨削过程中接触轮产生的噪声与振动机床译丛，1983，2。Malkin S.and Cook.N.H.The Wear Grinding Wheels, Part Ⅰ. Attritious Wear Trans of ASME 93B 1971.p. 1120-1128。
[75] 郭兴，杜润生，杨叔子，基于人工神经网络的铣刀破损功率监测，华中科技大学学报，1996，6，Vol24(6)6，47-49。
[76] 程光，万军，铣刀破损监控方法的研究，机械工艺师，1998，4，32-34。
[77] 刘晓东，基于切削力的铣刀磨损在线检测研究，
[78] 刘晓东，自回归算法在铣刀破损检测中的应用，组合机床与自动化加工技术，1999，3，27-32。
[79] 乐总谦，金属切削刀具，机械工业出版社，2001。
[80] 李造鼎，李锡润，虞和济，故障诊断的声学方法，冶金工业出版社，1989。
[81] Rangwala S, Domfeld DA. Sensor integration using neural network for intelligent tool condition monitoring. Trans of ASME Journal of Engineering for Industry, 1990,Vol112(8);219-228.
[82] Waschkies E, Sklarczyk C,Hepp K, Tool wear monitoring at trtning .Trans of ASME, Journal of Engineering for Industry, 1994, Vol 116(9);512-524.
[83] 赵彦玲，董丽华，严复钢，刀具磨损的声发射特性，机械工程师，1996，6，8-9。
[84] 王忠民，王信义，杨大勇等，刀具磨损状态在监测技术，制造技术与车床，2000，6，40-42。
[85] 王信义，徐春广等，自动化加工中刀具破损实时监测方法研究，北京理工大学学报，1995，Vol 15(3)。
[86] 陈超，徐建林，黄建龙，基于人工神经网络的刀具状态监测系统，机械工
程学报，2002，Vol 8(38)135—138。
[87] 史洪志，金属切削理论与实践，北京出版社，1980。
[88] .Noori-Khajavi A.Frequency and time domain analyses of sensor signals in drilling (part one:corretation with drill wear).International Journal of Machine Tools and Manufacture, 1995,35(b):775～794。
[89] Andreasen JL,Chiffer D Automatic chip-breakage detection in turning by frequency analysis of cutting force .Annals of the CIRP, 1993,42(1):45～48。
[90] 李锡文，杜润生、杨叔子，铣刀磨损过程中铣削力与磨损面积分析，华中理工大学学报，1998，2(26)，45～48。
[91] 张立明，人工神经网络的模型及其应用，复旦大学出版，1994。
[92] D.E.Rumelhart&J.L.Mcclelland,Parallel Distributed Processing,MIT Press, 1986.
[93] R.Hecht-Nielsen. Theory of The Back Propagation Neural Network.Proc.of IJCNN. 1989,Vol(1):593～603。
[94] R.CEberhart and R.W.Dobbins,Neural Network Pc tools,Academic Press, 1990.
[95] 李士勇，模糊控制，神经网络和智能控制论，哈尔滨工业大学出版社，1996。
[96] 孙增析，张再兴，邓志东，智能控制理论与技术，清华大学出版社，广西科学技术出版社，1997。
[97] 何振亚，神经智能，湖南科学技术出版社，1997。
[98] 王永骥，涂健，神经网络控制，机械工业出版社，1998。
[99] A.Cichocki,R.Vnbehauen. Neural Networks for Optimization and SignalProcessing. England: John wilcy&Sons Ltd. 1993.