基于EEMD和支持向量机的刀具状态监测方法研究
|
摘要
本文针对机械加工中大量用到的切削刀具的磨损状态进行了监测方法的研究,主要做了以下一系列工作：
首先,在分析刀具损坏机理和刀具磨损过程以及刀具磨钝标准的基础上,搭建了融合多传感器的刀具磨损状态监测实验平台,并且采集车削时不同切削条件下的振动和切削力数据。
其次,详细分析经验模态分解方法的原理和分解过程,针对其存在的模态混叠不足采用改进的总体经验模态分解方法。尝试性的将该方法运用于刀具磨损振动数据的分析处理上,抽取经过分解后的各IMF分量的能量百分比值作为表征刀具磨损量的特征值,并且详细分析证明了所提取特征值具有很好的重复性和差异性。
此外,介绍了统计知识基础和基于结构风险最小化原理的支持向量机的基本思想、理论特点。将运用EEMD分解法提取的振动数据能量百分比值和切削力均值作为输入支持向量机的训练样本和测试样本,建立支持向量机分类器模型,经过测试样本的验证发现支持向量机能够对EEMD能量百分比特征值进行正确的分类识别。
最后,经过对比BP和RBF神经网络与支持向量机分类器对刀具磨损状态的识别,发现支持向量机在识别精度、训练时间和对模型结构的依赖程度等方面表现出很好的优越性。
本文将EEMD分解方法与支持向量机结合起来运用到刀具磨损状态监测中,得到预想的结果,丰富了刀具磨损状态监测的研究方法,也为进一步实现在线监测提供一种理论依据。此外还对比分析了神经网络和支持向量机在分类识别应用中的特点,为后续的识别模型选取提供一定的理论参考。
In this paper, we have a series of work for the method research for the wear state of cutting tool, which is been used in machining largely.
Firstly, the mechanism of tool damage、the process of tool wearing and the tool blunt standard are been analyzed. Then setting up the experimental platform of multi-sensor for the monitoring of tool wear condition, and collecting turning vibration and cutting force data under different conditions.
Secondly, author analysis the principle of the method of empirical mode decomposition and the decomposition process. Towards its shortage of modal aliasing, it used the improved overall empirical mode decomposition method. Then trying to use the method for the analysis of the vibration data of tool wear. It extracted the percentage value of the energy of each IMF component after decomposition as the feature, and discussed the characteristic's repeatability and differences in detail.
In addition, it introduced the basic idea of the statistical knowledge and the theoretical characteristics of support vector machine. Support vector machine is based on structural risk minimization principle. Then, it makes the energy percentage values of vibration data extracted from ensemble empirical mode decomposition and the mean of cutting force as training samples and testing samples of support vector machine model, In this way, it established a support vector machine classifier model. The test samples tell the correct of this model for classification and identification of feature value that the energy percentage values of vibration data extracted from ensemble empirical mode decomposition and the mean of cutting force.
Finally, though comparing of BP and RBF neural network with support vector machine classifier in tool wear identification found that support vector machine showed good superiority in recognition accuracy, training time and reliance on the model structure. This paper combined EEMD decomposition method and support vector machine for tool wear monitoring, and achieved the anticipated results. Enriched the research methods of the tool wear condition monitoring, and also provided a theoretical basis for the further realization of online monitoring, In addition, it compared the characteristics of neural network and support vector machine in classification and recognition applications for providing a theoretical reference for the subsequent selecting of recognition model.
首先,在分析刀具损坏机理和刀具磨损过程以及刀具磨钝标准的基础上,搭建了融合多传感器的刀具磨损状态监测实验平台,并且采集车削时不同切削条件下的振动和切削力数据。
其次,详细分析经验模态分解方法的原理和分解过程,针对其存在的模态混叠不足采用改进的总体经验模态分解方法。尝试性的将该方法运用于刀具磨损振动数据的分析处理上,抽取经过分解后的各IMF分量的能量百分比值作为表征刀具磨损量的特征值,并且详细分析证明了所提取特征值具有很好的重复性和差异性。
此外,介绍了统计知识基础和基于结构风险最小化原理的支持向量机的基本思想、理论特点。将运用EEMD分解法提取的振动数据能量百分比值和切削力均值作为输入支持向量机的训练样本和测试样本,建立支持向量机分类器模型,经过测试样本的验证发现支持向量机能够对EEMD能量百分比特征值进行正确的分类识别。
最后,经过对比BP和RBF神经网络与支持向量机分类器对刀具磨损状态的识别,发现支持向量机在识别精度、训练时间和对模型结构的依赖程度等方面表现出很好的优越性。
本文将EEMD分解方法与支持向量机结合起来运用到刀具磨损状态监测中,得到预想的结果,丰富了刀具磨损状态监测的研究方法,也为进一步实现在线监测提供一种理论依据。此外还对比分析了神经网络和支持向量机在分类识别应用中的特点,为后续的识别模型选取提供一定的理论参考。
In this paper, we have a series of work for the method research for the wear state of cutting tool, which is been used in machining largely.
Firstly, the mechanism of tool damage、the process of tool wearing and the tool blunt standard are been analyzed. Then setting up the experimental platform of multi-sensor for the monitoring of tool wear condition, and collecting turning vibration and cutting force data under different conditions.
Secondly, author analysis the principle of the method of empirical mode decomposition and the decomposition process. Towards its shortage of modal aliasing, it used the improved overall empirical mode decomposition method. Then trying to use the method for the analysis of the vibration data of tool wear. It extracted the percentage value of the energy of each IMF component after decomposition as the feature, and discussed the characteristic's repeatability and differences in detail.
In addition, it introduced the basic idea of the statistical knowledge and the theoretical characteristics of support vector machine. Support vector machine is based on structural risk minimization principle. Then, it makes the energy percentage values of vibration data extracted from ensemble empirical mode decomposition and the mean of cutting force as training samples and testing samples of support vector machine model, In this way, it established a support vector machine classifier model. The test samples tell the correct of this model for classification and identification of feature value that the energy percentage values of vibration data extracted from ensemble empirical mode decomposition and the mean of cutting force.
Finally, though comparing of BP and RBF neural network with support vector machine classifier in tool wear identification found that support vector machine showed good superiority in recognition accuracy, training time and reliance on the model structure. This paper combined EEMD decomposition method and support vector machine for tool wear monitoring, and achieved the anticipated results. Enriched the research methods of the tool wear condition monitoring, and also provided a theoretical basis for the further realization of online monitoring, In addition, it compared the characteristics of neural network and support vector machine in classification and recognition applications for providing a theoretical reference for the subsequent selecting of recognition model.
引文
[1]Yu Teng Liang, Yih Chih Chiou. An Automated System Based on Multiple Cutting Force Parameters and Machine Vision Technique [J]. Materials Science Forum 2009 (626-627):5-10.
[2]吕俊杰,王杰,王玫,吴越.基于SOM和HMM结合的刀具磨损状态监测研究[J].中国机械工程,2010.21(13)：1531-1535.
[3]王玫,吕俊杰,王杰.基于连续高斯密度混合HMM的刀具磨损状态监测[J].四川大学学报,2010.42(3)：240-244.
[4]白莉,李言,郑建明,李淑娟.基于改进Hough变换的刀具磨损状态监测[J].西安理工大学学报,2010.26(1)：101-105.
[5]肖毅,王希.基于温度信号的高速干铣削试验研究[J].航空制造技术,2009.5：93-95.
[6]聂鹏,王东磊,王哲峰,徐涛.刀具磨损声发射信号处理中小波基选取的研究[J].工具技术,2009.43(1)：94-97.
[7]雷萍.基于PSO优化的小波神经网络在刀具磨损识别中的应用[J].工具技术,2007.41(6)：91-94.
[8]郑金兴,张铭钧,孟庆鑫.多传感器数据融合技术在刀具状态监测中的应用[J].传感器与微系统,2007.26(4)：90-93.
[9]刘建萍,叶邦彦.模糊数据融合的刀具磨损状态智能识别[J].机械与电子,2010.4：49-53.
[10]汤为,王海丽,庄子杰,胡德金.基于小波多分辨率分析和RBF神经网络的刀具磨损状态识别[J].工具技术,2009.43(2)：15-18.
[11]张锴锋,聂鹏,王东磊,林士龙,谌鑫.小波分析在数控刀具磨损状态监测中的应用[J].测控技术,2009.28(12)：13-16.
[12]关山,王龙山,聂鹏.基于EMD与LS-SVM的刀具磨损识别方法[J].北京航天航空大学学报,2011.37(2)：144-148.
[13]曹伟青.B样条模糊神经网络在刀具故障诊断中的应用[D].四川：成都,2005.
[14]王姣,祁美玲.RBF云神经网络在数控机床刀具磨损状态识别中的应用[J].机床与液压,2011.39(15)：146-149.
[15]李勇,王细洋,王学超.基于AR模型的铣刀磨损诊断[J].失效分析与预防,2009.4(1)：24-29.
[16]王计生,喻俊馨,黄惟公.小波包分析和支持向量机在刀具故障诊断中的应用[J].振动、测试与诊断,2008.28(3)：273-276.
[17]陈日曜.金属切削原理[M].版本.湖北：机械工业出版社.2009.1：92-117
[18]Huang, N. E., and Z. Wu,2008:A review on Hilbert-Huang transform:Method and its applications to geophysical studies. Rev. Geophysics.,46, RG2006, doi:10.1029/2007RG000228.
[19]张佳芳.基于EEMD的车内语音增强研究[D].浙江：浙江大学,2007.
[20]张晨罡.基于经验模态分解的滚动轴承故障诊断方法研究[D].郑州：郑州大学,2007.
[21]Li, Rouyn, He, David. APR 2012:Rotational Machine Health Monitoring and Fault Detection Using EMD-Based Acoustic Emission Feature Quantification. IEEE Transactions on Industrial Electronics.doi:10.1109/TIM.2011.2179819.:990-1001.
[22]张进林.抑制经验模态分解端点效应的常用方法性能比较研究[D].昆明：云南大学,2010.
[23]Wu, Z., E. K. Schneider, B. P. Karman, E. S. Karachi, N. E. Huang, and C. J. Tucker, 2008:The modulated annual cycle:an alternative reference frame for climate anomalies. Climate Dyne.(31)823-841.
[24]Qian, C, C. Fu, Z. Wu, and Z. Yan,2009:On the secular change of spring onset at Stockholm. Geophys. Res. Lett.36, L12706, doi:10.1029/2009GL038617,2009.
[25]Breaker, L. C., and A. Ruzmaikin,2010:The 154-year record of sea level at San Francisco:extracting the long-term trend, recent changes, and other tidbits. Climate Dynamics, doi:10.1007/s00382-010-0865-4.
[26]李海涛,王成国,许跃生,吴朝华.基于EEMD的轨道—车辆系统垂向动力学的时频分析[J].中国铁道科学,2007.28(5)：24-30.
[27]张杨,刘志刚EEMD在电能质量扰动检测中的应用[J].电力自动化设备,2011.31(12)：86-90.
[28]Lei, Y., Z. He, Y. Zi,2009:Application of the EEMD method to rotor fault diagnosis of rotating machinery. Mechanical Systems and Signal Processing,23 (4),1327-1338.
[29]董文智,张超.基于EEMD能量百分比和支持向量机的轴承故障诊断[J].机械设计与研究,2011.27(5)：53-56.
[30]张玲玲,廖红云,曹亚娟,骆诗定,赵懿冠.基于EEMD和模糊C均值聚类算法诊断发动机曲轴轴承故障[J].内燃机学报,2011.29(4)：332-336.
[31]郑旭,郝志勇,金阳,卢兆刚.基于EEMD与广义S变换的内燃机噪声源识别研究[J].内燃机工程,2011.32(5)：68-73.
[32]高清清,贾民平.基于EEMD的奇异谱百分比在旋转机械故障诊断中的应用[J].东南大学学报,2011.41(5)：998-1001.
[33]高昌鑫,荆双喜.基于EEMD的齿轮箱故障诊断[J].煤炭技术,2010.29(6)：20-22.
[34]张超,陈建军,杨立东,徐亚兰.奇异值百分比和支持向量机的齿轮故障诊断[J].振动、测试与诊断,2011.31(5)：600-604.
[35]张玲玲,骆诗定,肖云魁,赵懿冠,廖红云.集合经验模式分解在柴油机机械故障诊断中的应用[J].科学技术与工程,2010.10(27)：6745-674.
[36]陈可,李野,陈澜EEMD分解在电力系统故障信号检测中的应用[J].计算机仿真,2010.27(3)：263-266.
[37]王胜涛.基于EEMD的冠脉狭窄舒张期心音分析算法研究[D].杭州：杭州电子科技大学,2011.
[38]邵骏,吕孙云,钱晓燕,袁鹏.基于总体经验模态分解的水文序列多尺度分析[J].华中科技大学学报,2011.39(11)：105-108.
[39]Wu, Z., and N. E. Huang,2009:Ensemble Empirical Mode Decomposition: a noise-assisted data analysis method. Advances in Adaptive Data Analysis,1,1-41.
[40]Huang, N. E., Z. Shen, S. R. Long, M. C. Wu, E. H. Shih, Q. Zheng, C. C. Tung, and H. H. Liu,1998:The empirical mode decomposition and the Hilbert spectrum for nonlinear and nonstationary time series analysis. Proceedings of the Royal Society A, London, 454, 903-995.
[41]Chia-Feng Juang; Guo-Cyuan Chen,2012:A TS Fuzzy System Learned Through a Support Vector Machine in Principal Component Space for Real-Time Object Detection. IEEE Transactions on Industrial Electronics.doi:10.1109/TIE.2011.2159949:3309-20.
[42]杨宇.基于EMD和支持向量机的旋转机械故障诊断方法研究[D].湖南：湖南大学,2005.
[43]彭兵.基于改进支持向量机和特征信息融合的水电机组故障诊断[D].武汉：华中科技大学,2008.
[44]吕冬梅.支持向量机在刀具故障诊断中的应用[D].成都：西华大学,2008.
[45]李娜.基于模糊C均值及粒子群参数优化的支持向量机故障诊断方法研究[D].成都：电子科技大学,2011.
[46]刘晓娟基于希尔伯特_黄变换和支持向量机的齿轮箱故障诊断研究[D].太原：中北大学,2011.
[47]翟永杰基于支持向量机的故障智能诊断方法研究[D].河北：华北电力大学,2004.
[48]吴小季基于SVM图像分类方法的研究[D].南京：南京信息工程大学,2011.
[2]吕俊杰,王杰,王玫,吴越.基于SOM和HMM结合的刀具磨损状态监测研究[J].中国机械工程,2010.21(13)：1531-1535.
[3]王玫,吕俊杰,王杰.基于连续高斯密度混合HMM的刀具磨损状态监测[J].四川大学学报,2010.42(3)：240-244.
[4]白莉,李言,郑建明,李淑娟.基于改进Hough变换的刀具磨损状态监测[J].西安理工大学学报,2010.26(1)：101-105.
[5]肖毅,王希.基于温度信号的高速干铣削试验研究[J].航空制造技术,2009.5：93-95.
[6]聂鹏,王东磊,王哲峰,徐涛.刀具磨损声发射信号处理中小波基选取的研究[J].工具技术,2009.43(1)：94-97.
[7]雷萍.基于PSO优化的小波神经网络在刀具磨损识别中的应用[J].工具技术,2007.41(6)：91-94.
[8]郑金兴,张铭钧,孟庆鑫.多传感器数据融合技术在刀具状态监测中的应用[J].传感器与微系统,2007.26(4)：90-93.
[9]刘建萍,叶邦彦.模糊数据融合的刀具磨损状态智能识别[J].机械与电子,2010.4：49-53.
[10]汤为,王海丽,庄子杰,胡德金.基于小波多分辨率分析和RBF神经网络的刀具磨损状态识别[J].工具技术,2009.43(2)：15-18.
[11]张锴锋,聂鹏,王东磊,林士龙,谌鑫.小波分析在数控刀具磨损状态监测中的应用[J].测控技术,2009.28(12)：13-16.
[12]关山,王龙山,聂鹏.基于EMD与LS-SVM的刀具磨损识别方法[J].北京航天航空大学学报,2011.37(2)：144-148.
[13]曹伟青.B样条模糊神经网络在刀具故障诊断中的应用[D].四川：成都,2005.
[14]王姣,祁美玲.RBF云神经网络在数控机床刀具磨损状态识别中的应用[J].机床与液压,2011.39(15)：146-149.
[15]李勇,王细洋,王学超.基于AR模型的铣刀磨损诊断[J].失效分析与预防,2009.4(1)：24-29.
[16]王计生,喻俊馨,黄惟公.小波包分析和支持向量机在刀具故障诊断中的应用[J].振动、测试与诊断,2008.28(3)：273-276.
[17]陈日曜.金属切削原理[M].版本.湖北：机械工业出版社.2009.1：92-117
[18]Huang, N. E., and Z. Wu,2008:A review on Hilbert-Huang transform:Method and its applications to geophysical studies. Rev. Geophysics.,46, RG2006, doi:10.1029/2007RG000228.
[19]张佳芳.基于EEMD的车内语音增强研究[D].浙江：浙江大学,2007.
[20]张晨罡.基于经验模态分解的滚动轴承故障诊断方法研究[D].郑州：郑州大学,2007.
[21]Li, Rouyn, He, David. APR 2012:Rotational Machine Health Monitoring and Fault Detection Using EMD-Based Acoustic Emission Feature Quantification. IEEE Transactions on Industrial Electronics.doi:10.1109/TIM.2011.2179819.:990-1001.
[22]张进林.抑制经验模态分解端点效应的常用方法性能比较研究[D].昆明：云南大学,2010.
[23]Wu, Z., E. K. Schneider, B. P. Karman, E. S. Karachi, N. E. Huang, and C. J. Tucker, 2008:The modulated annual cycle:an alternative reference frame for climate anomalies. Climate Dyne.(31)823-841.
[24]Qian, C, C. Fu, Z. Wu, and Z. Yan,2009:On the secular change of spring onset at Stockholm. Geophys. Res. Lett.36, L12706, doi:10.1029/2009GL038617,2009.
[25]Breaker, L. C., and A. Ruzmaikin,2010:The 154-year record of sea level at San Francisco:extracting the long-term trend, recent changes, and other tidbits. Climate Dynamics, doi:10.1007/s00382-010-0865-4.
[26]李海涛,王成国,许跃生,吴朝华.基于EEMD的轨道—车辆系统垂向动力学的时频分析[J].中国铁道科学,2007.28(5)：24-30.
[27]张杨,刘志刚EEMD在电能质量扰动检测中的应用[J].电力自动化设备,2011.31(12)：86-90.
[28]Lei, Y., Z. He, Y. Zi,2009:Application of the EEMD method to rotor fault diagnosis of rotating machinery. Mechanical Systems and Signal Processing,23 (4),1327-1338.
[29]董文智,张超.基于EEMD能量百分比和支持向量机的轴承故障诊断[J].机械设计与研究,2011.27(5)：53-56.
[30]张玲玲,廖红云,曹亚娟,骆诗定,赵懿冠.基于EEMD和模糊C均值聚类算法诊断发动机曲轴轴承故障[J].内燃机学报,2011.29(4)：332-336.
[31]郑旭,郝志勇,金阳,卢兆刚.基于EEMD与广义S变换的内燃机噪声源识别研究[J].内燃机工程,2011.32(5)：68-73.
[32]高清清,贾民平.基于EEMD的奇异谱百分比在旋转机械故障诊断中的应用[J].东南大学学报,2011.41(5)：998-1001.
[33]高昌鑫,荆双喜.基于EEMD的齿轮箱故障诊断[J].煤炭技术,2010.29(6)：20-22.
[34]张超,陈建军,杨立东,徐亚兰.奇异值百分比和支持向量机的齿轮故障诊断[J].振动、测试与诊断,2011.31(5)：600-604.
[35]张玲玲,骆诗定,肖云魁,赵懿冠,廖红云.集合经验模式分解在柴油机机械故障诊断中的应用[J].科学技术与工程,2010.10(27)：6745-674.
[36]陈可,李野,陈澜EEMD分解在电力系统故障信号检测中的应用[J].计算机仿真,2010.27(3)：263-266.
[37]王胜涛.基于EEMD的冠脉狭窄舒张期心音分析算法研究[D].杭州：杭州电子科技大学,2011.
[38]邵骏,吕孙云,钱晓燕,袁鹏.基于总体经验模态分解的水文序列多尺度分析[J].华中科技大学学报,2011.39(11)：105-108.
[39]Wu, Z., and N. E. Huang,2009:Ensemble Empirical Mode Decomposition: a noise-assisted data analysis method. Advances in Adaptive Data Analysis,1,1-41.
[40]Huang, N. E., Z. Shen, S. R. Long, M. C. Wu, E. H. Shih, Q. Zheng, C. C. Tung, and H. H. Liu,1998:The empirical mode decomposition and the Hilbert spectrum for nonlinear and nonstationary time series analysis. Proceedings of the Royal Society A, London, 454, 903-995.
[41]Chia-Feng Juang; Guo-Cyuan Chen,2012:A TS Fuzzy System Learned Through a Support Vector Machine in Principal Component Space for Real-Time Object Detection. IEEE Transactions on Industrial Electronics.doi:10.1109/TIE.2011.2159949:3309-20.
[42]杨宇.基于EMD和支持向量机的旋转机械故障诊断方法研究[D].湖南：湖南大学,2005.
[43]彭兵.基于改进支持向量机和特征信息融合的水电机组故障诊断[D].武汉：华中科技大学,2008.
[44]吕冬梅.支持向量机在刀具故障诊断中的应用[D].成都：西华大学,2008.
[45]李娜.基于模糊C均值及粒子群参数优化的支持向量机故障诊断方法研究[D].成都：电子科技大学,2011.
[46]刘晓娟基于希尔伯特_黄变换和支持向量机的齿轮箱故障诊断研究[D].太原：中北大学,2011.
[47]翟永杰基于支持向量机的故障智能诊断方法研究[D].河北：华北电力大学,2004.
[48]吴小季基于SVM图像分类方法的研究[D].南京：南京信息工程大学,2011.