基于时序深度学习的数控机床运动精度预测方法
|
摘要
由于数控机床精度演化规律难以通过数学建模分析,提出了一种基于时序深度学习网络的数控机床运动精度建模与预测方法。基于长短时记忆网络建立时序深度学习预测模型,利用相空间重构原理构建模型时序输入向量,采用多层网格搜索方法选择最优隐含层层数、隐含层节点数等模型参数,以BPTT方法训练模型;模型自动提取运动精度时间序列的时空特征,挖掘精度时间序列前后关联信息,对运动精度变化趋势进行预测。实验结果表明,基于时序深度学习网络的预测模型能够准确预测数控机床精度的衰退趋势,预测的最大相对误差不大于7. 96%,优于传统方法。
Because of the difficult to analyze the evolution law of CNC machine tools accuracy through mathematical modeling,a method of motion accuracy modeling and prediction based on sequential deep learning network was proposed. A deep learning network was presented based on the long short-term memory( LSTM). Using the principle of phase space reconstruction,the sequence input vector of the model was constructed. The optimal parameters of the model,such as number of hidden layer and number of hidden layer node were determined based on multi-layer grid search algorithm. The model was trained with BPTT method. The mutual information before and after the precision time series was mined with data driven. The temporal and spatial characteristics of the motion accuracy series were automatically extracted through the deep learning network. Finally,the declining trend of motion accuracy was predicted by the model. The experiments results showed that the prediction model based on the sequential deep learning network could predict properly the evolutionary trends and regularity of the precision. The maximum relative error of prediction was not more than 7. 96%. The prediction accuracy of the method was better than that of the traditional methods. The method was helpful for evaluating the reliability of NC machine tools and ensuring the machining accuracy.
Because of the difficult to analyze the evolution law of CNC machine tools accuracy through mathematical modeling,a method of motion accuracy modeling and prediction based on sequential deep learning network was proposed. A deep learning network was presented based on the long short-term memory( LSTM). Using the principle of phase space reconstruction,the sequence input vector of the model was constructed. The optimal parameters of the model,such as number of hidden layer and number of hidden layer node were determined based on multi-layer grid search algorithm. The model was trained with BPTT method. The mutual information before and after the precision time series was mined with data driven. The temporal and spatial characteristics of the motion accuracy series were automatically extracted through the deep learning network. Finally,the declining trend of motion accuracy was predicted by the model. The experiments results showed that the prediction model based on the sequential deep learning network could predict properly the evolutionary trends and regularity of the precision. The maximum relative error of prediction was not more than 7. 96%. The prediction accuracy of the method was better than that of the traditional methods. The method was helpful for evaluating the reliability of NC machine tools and ensuring the machining accuracy.
引文
[1]马军旭,赵万华,张根保.国产数控机床精度保持性分析及研究现状[J].中国机械工程,2015,26(22):3108-3115.MA Junxu,ZHAO Wanhua,ZHANG Genbao. Research status and analyes on accuracy retentivity of domestic CNC machine tools[J]. China Mechanical Engineering,2015,26(22):3108-3115.(in Chinese)
[2]韩飞飞,赵继,张雷,等.数控机床几何精度综合解析与试验研究[J].机械工程学报,2012,48(21):141-148.HAN Feifei,ZHAO Ji,ZHANG Lei,et al. Synthetical analysis and experimental study of the geometric accuracy of CNC machine tools[J]. Journal of Mechanical Engineering,2012,48(21):141-148.(in Chinese)
[3] FUJIMORI T,TANIGUCHI K,ELLIS C,et al. A study on error compensation on high precision machine tool system using a 2D laser holographic scale system[J]. Journal of Advanced Mechanical Design,Systems and Manufacturing,2012,6(6):999-1114.
[4] IBARAKI S,OYAMA C,OTSUBO H. Construction of an error map of rotary axes on a 5-axis machining center by static R-test[J]. International Journal of Machine Tools and Manufacture,2011,51(3):190-200.
[5] MANN S,BEDI S,ISRAELI G,et al. Machine models and tool motions for simulating five-axis machining[J]. Computer-Aided Design,2010,42(3):23l-237.
[6]萨日娜,张树有,刘晓健.面向零件切削性评价的数控机床精度特性重要度耦合识别技术[J].机械工程学报,2013,49(9):113-120.SARINA,ZHANG Shuyou,LIU Xiaojian. Identification of accuracy characteristics importance of machine tool for parts machinability evaluation[J]. Journal of Mechanical Engineering,2013,49(9):113-120.(in Chinese)
[7]粟时平,李圣怡.多体系统理论在数控加工精度软件预测中的应用[J].组合机床与自动化加工技术,2004(4):26-30.SU Shiping,LI Shengyi. Study about the application of multi-body system theory in machining precision of CNC machine tools[J]. Modular Machine Tool&Automatic Manufacturing Technique,2004(4):26-30.(in Chinese)
[8]胡占齐,刘金超,解亚非,等.基于多体运动学的超重型数控机床维护周期预测[J].燕山大学学报,2012,36(3):201-214.HU Zhanqi,LIU Jinchao,XIE Yafei,et al. Prediction of super-heavy CNC machine maintenance cycle based on multibody kinematics[J]. Journal of Yanshan University,2012,36(3):201-214.(in Chinese)
[9]王民,胡建忠,昝涛,等.基于斜置锥台的五轴数控机床加工精度预测技术[J].高技术通讯,2011,21(12):1299-1304.WANG Min,HU Jianzhong,ZAN Tao,et al. Prediction of the machining precision of five-axis NC machine tools based on cone frustum[J]. High Technology Letters,2011,21(12):1299-1304.(in Chinese)
[10]余永维,殷国富,殷鹰,等.基于深度学习网络的射线图像缺陷识别方法[J].仪器仪表学报,2014,35(9):2012-2019.YU Yongwei,YIN Guofu,YIN Ying,et al. Defect recognition for radiographic image based on deep learning network[J].Chinese Journal of Scientific Instrument,2014,35(9):2012-2019.(in Chinese)
[11]余永维,杜柳青.基于深度学习特征匹配的铸件微小缺陷自动定位方法[J].仪器仪表学报,2016,37(6):1364-1370.YU Yongwei,DU Liuqing. Automatic location of casting small defect based on deep learning feature[J]. Chinese Journal of Scientific Instrument,2016,37(6):1364-1370.(in Chinese)
[12]谭文学,赵春江,吴华瑞,等.基于弹性动量深度学习神经网络的果体病理图像识别[J/OL].农业机械学报,2015,46(1):20-25. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20150104&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2015. 01. 004.TAN Wenxue,ZHAO Chunjiang,WU Huarui,et al. A deep learning network for recognizing fruit pathologic images based on flexible momentum[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2015,46(1):20-25.(in Chinese)
[13]高震宇,王安,刘勇,等.基于卷积神经网络的鲜茶叶智能分选系统研究[J/OL].农业机械学报,2017,48(7):53-58.http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20170707&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2017. 07. 007.GAO Zhenyu,WANG An,LIU Yong,et al. Intelligent fresh-tea-leaves sorting system research based on convolution neural network[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2017,48(7):53-58.(in Chinese)
[14]孙钰,韩京冶,陈志泊,等.基于深度学习的大棚及地膜农田无人机航拍监测方法[J/OL].农业机械学报,2018,49(2):133-140. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20180218&journal_id=jcsam.DOI:10. 6041/j. issn. 1000-1298. 2018. 02. 018.SUN Yu,HAN Jingye,CHEN Zhibo,et al. Monitoring method for UAV image of greenhouse and plastic-mulched landcover based on deep learning[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2018,49(2):133-140.(in Chinese)
[15]余永维,杜柳青,闫哲,等.基于深度学习特征的铸件缺陷射线图像动态检测方法[J/OL].农业机械学报,2016,47(7):407-412. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=201160755&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2016. 07. 055.YU Yongwei,DU Liuqing,YAN Zhe,et al. Dynamic detection of casting defects radiographic image based on deep learning feature[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2016,47(7):407-412.(in Chinese)
[16] BENGIO Y. Learning deep architectures for AI[J]. Foundations and Trends in Machine Learning,2009,2(1):1-127.
[17] HINTON G E,SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science,2006,313(5786):504-507.
[18] GERS F A,SCHMIDHUBER J. Learning to forget:continual prediction with LSTM[J]. Neural Computation,2000,12(10):2451-2471.
[19] HOCHREITER S,SCHMIDHUBER J. Long short-term memory[J]. Neural Computation,1997,9(8):1735-1780.
[20] TAKENS F. Detecting strange attractor in turbulence[C]∥Lecture Notes in Mathematics,1981,898:366-381.
[2]韩飞飞,赵继,张雷,等.数控机床几何精度综合解析与试验研究[J].机械工程学报,2012,48(21):141-148.HAN Feifei,ZHAO Ji,ZHANG Lei,et al. Synthetical analysis and experimental study of the geometric accuracy of CNC machine tools[J]. Journal of Mechanical Engineering,2012,48(21):141-148.(in Chinese)
[3] FUJIMORI T,TANIGUCHI K,ELLIS C,et al. A study on error compensation on high precision machine tool system using a 2D laser holographic scale system[J]. Journal of Advanced Mechanical Design,Systems and Manufacturing,2012,6(6):999-1114.
[4] IBARAKI S,OYAMA C,OTSUBO H. Construction of an error map of rotary axes on a 5-axis machining center by static R-test[J]. International Journal of Machine Tools and Manufacture,2011,51(3):190-200.
[5] MANN S,BEDI S,ISRAELI G,et al. Machine models and tool motions for simulating five-axis machining[J]. Computer-Aided Design,2010,42(3):23l-237.
[6]萨日娜,张树有,刘晓健.面向零件切削性评价的数控机床精度特性重要度耦合识别技术[J].机械工程学报,2013,49(9):113-120.SARINA,ZHANG Shuyou,LIU Xiaojian. Identification of accuracy characteristics importance of machine tool for parts machinability evaluation[J]. Journal of Mechanical Engineering,2013,49(9):113-120.(in Chinese)
[7]粟时平,李圣怡.多体系统理论在数控加工精度软件预测中的应用[J].组合机床与自动化加工技术,2004(4):26-30.SU Shiping,LI Shengyi. Study about the application of multi-body system theory in machining precision of CNC machine tools[J]. Modular Machine Tool&Automatic Manufacturing Technique,2004(4):26-30.(in Chinese)
[8]胡占齐,刘金超,解亚非,等.基于多体运动学的超重型数控机床维护周期预测[J].燕山大学学报,2012,36(3):201-214.HU Zhanqi,LIU Jinchao,XIE Yafei,et al. Prediction of super-heavy CNC machine maintenance cycle based on multibody kinematics[J]. Journal of Yanshan University,2012,36(3):201-214.(in Chinese)
[9]王民,胡建忠,昝涛,等.基于斜置锥台的五轴数控机床加工精度预测技术[J].高技术通讯,2011,21(12):1299-1304.WANG Min,HU Jianzhong,ZAN Tao,et al. Prediction of the machining precision of five-axis NC machine tools based on cone frustum[J]. High Technology Letters,2011,21(12):1299-1304.(in Chinese)
[10]余永维,殷国富,殷鹰,等.基于深度学习网络的射线图像缺陷识别方法[J].仪器仪表学报,2014,35(9):2012-2019.YU Yongwei,YIN Guofu,YIN Ying,et al. Defect recognition for radiographic image based on deep learning network[J].Chinese Journal of Scientific Instrument,2014,35(9):2012-2019.(in Chinese)
[11]余永维,杜柳青.基于深度学习特征匹配的铸件微小缺陷自动定位方法[J].仪器仪表学报,2016,37(6):1364-1370.YU Yongwei,DU Liuqing. Automatic location of casting small defect based on deep learning feature[J]. Chinese Journal of Scientific Instrument,2016,37(6):1364-1370.(in Chinese)
[12]谭文学,赵春江,吴华瑞,等.基于弹性动量深度学习神经网络的果体病理图像识别[J/OL].农业机械学报,2015,46(1):20-25. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20150104&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2015. 01. 004.TAN Wenxue,ZHAO Chunjiang,WU Huarui,et al. A deep learning network for recognizing fruit pathologic images based on flexible momentum[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2015,46(1):20-25.(in Chinese)
[13]高震宇,王安,刘勇,等.基于卷积神经网络的鲜茶叶智能分选系统研究[J/OL].农业机械学报,2017,48(7):53-58.http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20170707&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2017. 07. 007.GAO Zhenyu,WANG An,LIU Yong,et al. Intelligent fresh-tea-leaves sorting system research based on convolution neural network[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2017,48(7):53-58.(in Chinese)
[14]孙钰,韩京冶,陈志泊,等.基于深度学习的大棚及地膜农田无人机航拍监测方法[J/OL].农业机械学报,2018,49(2):133-140. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20180218&journal_id=jcsam.DOI:10. 6041/j. issn. 1000-1298. 2018. 02. 018.SUN Yu,HAN Jingye,CHEN Zhibo,et al. Monitoring method for UAV image of greenhouse and plastic-mulched landcover based on deep learning[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2018,49(2):133-140.(in Chinese)
[15]余永维,杜柳青,闫哲,等.基于深度学习特征的铸件缺陷射线图像动态检测方法[J/OL].农业机械学报,2016,47(7):407-412. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=201160755&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2016. 07. 055.YU Yongwei,DU Liuqing,YAN Zhe,et al. Dynamic detection of casting defects radiographic image based on deep learning feature[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2016,47(7):407-412.(in Chinese)
[16] BENGIO Y. Learning deep architectures for AI[J]. Foundations and Trends in Machine Learning,2009,2(1):1-127.
[17] HINTON G E,SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science,2006,313(5786):504-507.
[18] GERS F A,SCHMIDHUBER J. Learning to forget:continual prediction with LSTM[J]. Neural Computation,2000,12(10):2451-2471.
[19] HOCHREITER S,SCHMIDHUBER J. Long short-term memory[J]. Neural Computation,1997,9(8):1735-1780.
[20] TAKENS F. Detecting strange attractor in turbulence[C]∥Lecture Notes in Mathematics,1981,898:366-381.