基于小波神经网络的数控机床关键部件故障诊断
|
摘要
数控机床作为典型的机电一体化设备,在现代机械制造行业占据了重要地位,它的拥有量已经成为衡量一个地区制造业能力的标准,并且其应用还在不断地推广,因此数控机床的故障诊断技术也就显得尤为重要。
滚珠丝杠作为数控机床上常用的进给传动部件,对机床的加工性能具有很大的影响,丝杠的微小异常有可能会导致机床的加工零件不合格,甚至影响到产品的加工进度,所以对滚珠丝杠的状态进行监测,及时发现故障是保证数控机床正常工作的一个重要条件。
小波分析凭借其在时域与频域的综合分析能力,成为信号分析领域中非常重要的一种分析技术。它采取变时窗方法克服了傅里叶变换的频域局部分析弱点,将时域与频域结合起来,更加准确地描述了信号的特征。小波包分析是对小波分析的延伸,通过对在小波分析中被忽略掉的高频信号部分进行补充分析来完善小波分析的结果。
本文所研究的小波神经网络将小波分析引入到对信号进行模式识别与故障诊断的人工神经网络中,利用小波函数替换人工神经元中的激励函数,将小波变换的多尺度特性引入神经网络,从而使小波神经网络不但具有小波的多分辨率特性而且保留了神经网络的自学习与模式识别的能力。
本文在BP神经网络的基础上引入morlet小波函数作为隐层神经元的激励函数,从而搭建起小波神经网络。利用正弦函数进行仿真验证后,证实了该小波神经网络的可行性,即本文所建立的小波神经网络可以用来进行模式识别。
本文对采集到的滚珠丝杠的振动信号进行分析,并在时域、频域以及时频域等各个方面从信号中提取出能够体现丝杠状态的有效特征值,将这些有效特征值输入建立的小波神经网络进行训练及模式识别,证实了小波神经网络在数控机床故障诊断中的实用性。通过与BP神经网络的对比,突出了小波神经网络稳定性好、识别率高等特点。
本文的重点在于通过对BP神经网络算法及应用的研究,成功地将小波函数引入其中,从而建立起新型的小波神经网络。并运用此网络成功地对实际工程中的数控机床滚珠丝杠振动数据进行模式识别,正确地诊断滚珠丝杠的故障状态。
As a typical electromechanical integration equipment, CNC machine occupies an important position of modern machinery manufacturing industry, the number of its ownership has become a standard to measure the manufacturing capability of a regional, and its application is continuing to promote, so the fault diagnosis technology of CNC machine is especially important.
As a conventional feed drive components of CNC machine, ball screw has a great impact on the processing performance of the machine. Its tiny abnormality may result in the fail of parts processed, and even affect the overall processing of the product, so it's an important condition of ensuring CNC machine's normal operation to monitor the condition of ball screw and detect its faults timely.
With the comprehensive analysis capability in time domain and frequency domain, wavelet analysis is very important in the area of signal analysis. It overcomes the Fourier transform's weakness of partial analysis in the frequency domain, it combines the time-domain with frequency-domain, so the signal characteristics can be accurate descried. Wavelet packet analysis is an extension of wavelet analysis, it analyzes the high-frequency signal which is ignored in wavelet analysis, so its result is more complete.
The wavelet neural network in this paper introduced wavelet into neural network, it replaced the activation function of artificial neuron with wavelet function to lead the characteristics of multi-scale into neural network. Thereby the wavelet neural network not only has the multi-resolution characteristics of wavelet but also keep the self-learning and pattern recognition capabilities of neural network.
In this paper, the wavelet neural network is based on BP neural network. It introduced morlet wavelet function as the activation function of hidden layer neuron, which erected wavelet neural network. The simulation using sine function has confirmed the feasibility of the wavelet neural network, that is the wavelet neural network established can be used for pattern recognition.
In this paper, the vibration signal of the ball screw is collected and analyzed, and the effective features which can express the condition of the ball screw are extracted from the time domain, frequency domain and time-frequency domain, then put these features into the WNN established to be trained and pattern recognized. The results confirmed the practicability of fault diagnosis of CNC using WNN. And By comparison with the BP neural network, the advantages of high stability and recognition rate are highlighted.
The most important part in this paper is that a new type of wavelet neural network is established by introduce the wavelet function into the BP network successfully based on the study of algorithm and application of BP neural network. And the vibration signal of the ball screw is recognized successfully by the wavelet neural network so that the fault state of the ball screw is diagnosed correctly.
滚珠丝杠作为数控机床上常用的进给传动部件,对机床的加工性能具有很大的影响,丝杠的微小异常有可能会导致机床的加工零件不合格,甚至影响到产品的加工进度,所以对滚珠丝杠的状态进行监测,及时发现故障是保证数控机床正常工作的一个重要条件。
小波分析凭借其在时域与频域的综合分析能力,成为信号分析领域中非常重要的一种分析技术。它采取变时窗方法克服了傅里叶变换的频域局部分析弱点,将时域与频域结合起来,更加准确地描述了信号的特征。小波包分析是对小波分析的延伸,通过对在小波分析中被忽略掉的高频信号部分进行补充分析来完善小波分析的结果。
本文所研究的小波神经网络将小波分析引入到对信号进行模式识别与故障诊断的人工神经网络中,利用小波函数替换人工神经元中的激励函数,将小波变换的多尺度特性引入神经网络,从而使小波神经网络不但具有小波的多分辨率特性而且保留了神经网络的自学习与模式识别的能力。
本文在BP神经网络的基础上引入morlet小波函数作为隐层神经元的激励函数,从而搭建起小波神经网络。利用正弦函数进行仿真验证后,证实了该小波神经网络的可行性,即本文所建立的小波神经网络可以用来进行模式识别。
本文对采集到的滚珠丝杠的振动信号进行分析,并在时域、频域以及时频域等各个方面从信号中提取出能够体现丝杠状态的有效特征值,将这些有效特征值输入建立的小波神经网络进行训练及模式识别,证实了小波神经网络在数控机床故障诊断中的实用性。通过与BP神经网络的对比,突出了小波神经网络稳定性好、识别率高等特点。
本文的重点在于通过对BP神经网络算法及应用的研究,成功地将小波函数引入其中,从而建立起新型的小波神经网络。并运用此网络成功地对实际工程中的数控机床滚珠丝杠振动数据进行模式识别,正确地诊断滚珠丝杠的故障状态。
As a typical electromechanical integration equipment, CNC machine occupies an important position of modern machinery manufacturing industry, the number of its ownership has become a standard to measure the manufacturing capability of a regional, and its application is continuing to promote, so the fault diagnosis technology of CNC machine is especially important.
As a conventional feed drive components of CNC machine, ball screw has a great impact on the processing performance of the machine. Its tiny abnormality may result in the fail of parts processed, and even affect the overall processing of the product, so it's an important condition of ensuring CNC machine's normal operation to monitor the condition of ball screw and detect its faults timely.
With the comprehensive analysis capability in time domain and frequency domain, wavelet analysis is very important in the area of signal analysis. It overcomes the Fourier transform's weakness of partial analysis in the frequency domain, it combines the time-domain with frequency-domain, so the signal characteristics can be accurate descried. Wavelet packet analysis is an extension of wavelet analysis, it analyzes the high-frequency signal which is ignored in wavelet analysis, so its result is more complete.
The wavelet neural network in this paper introduced wavelet into neural network, it replaced the activation function of artificial neuron with wavelet function to lead the characteristics of multi-scale into neural network. Thereby the wavelet neural network not only has the multi-resolution characteristics of wavelet but also keep the self-learning and pattern recognition capabilities of neural network.
In this paper, the wavelet neural network is based on BP neural network. It introduced morlet wavelet function as the activation function of hidden layer neuron, which erected wavelet neural network. The simulation using sine function has confirmed the feasibility of the wavelet neural network, that is the wavelet neural network established can be used for pattern recognition.
In this paper, the vibration signal of the ball screw is collected and analyzed, and the effective features which can express the condition of the ball screw are extracted from the time domain, frequency domain and time-frequency domain, then put these features into the WNN established to be trained and pattern recognized. The results confirmed the practicability of fault diagnosis of CNC using WNN. And By comparison with the BP neural network, the advantages of high stability and recognition rate are highlighted.
The most important part in this paper is that a new type of wavelet neural network is established by introduce the wavelet function into the BP network successfully based on the study of algorithm and application of BP neural network. And the vibration signal of the ball screw is recognized successfully by the wavelet neural network so that the fault state of the ball screw is diagnosed correctly.
引文
1 王贵成.数控机床故障诊断技术.第二版.北京：化学工业出版社,2010.3：1-8.28-60
2 杜国臣,王士军.机床数控技术.第二版.北京：北京大学出版社2010.1：8-9,269-305
3 陈蔚芳,王宏涛.机床数控技术及应用.北京：科学出版社,2005：12,282-322
4 洪宇.高速滚珠丝杠副综合性能测量系统设计.南京：南京理工大学硕士学位论文,2006
5 王兆坦,刘宪银,满海彬,宋现春,于复生.高速精密滚珠丝杠副性能试验简介.世界制造技术与装备市场.2006(6)：75-78
6 肖正义,焦洁.高速滚珠丝杠副的研发和测试技术.制造技术与机床.2004(4)：95-98
7 邓奕.现代数控机床及应用.北京：国防工业出版社,2008.9：8-32
8 盛兆顺,尹琦岭.设备状态监测与故障诊断技术及应用.北京：化学工业出版社,2003.5：38-78
9 薛年喜.MATLAB在数字信号处理中的应用.北京：清华大学出版社,2003：252-338
10 陈桂明,张明照,戚红雨.应用MATLAB语言处理数字信号与数字图像.北京：科学出版社,2000：201-224,273-306
11 孙万麟,山拜·达拉拜.一种基于小波包和双谱的信号分析方法.现代电子技术.2008(5)：149-151
12 金建新,李冬冬,侯汉松.小波包与灰色理论在车床噪声信号分析中的应用.制造技术与机床.2008(9)：62-64
13 王唯,郑正奇,王晓华,夏薇.小波包特征提取算法在信号分析中应用.电子测量技术.2005(5)：27-28
14 陈侃,傅攀,李威霖,曹伟青.钛合金车削加工过程中刀具磨损状态监测的小波包子带能量变换特征提取新方法.组合机床与自动化加工技术.2011(1)：35-38
15 虞和济,陈长征,张省,周建男.基于神经网络的智能诊断.北京：冶金工业出版社,2000.05
16 飞思科技产品研发中心.MATLAB6.5辅助神经网络分析与设计.北京：电子工业出版社,2003.04
17 丛爽.面向MATLAB工具箱的神经网络理论与应用.第三版.合肥：中国科学技术大 学出版社,2009.04
18 (美)萨马拉辛荷(Samarasinghe. s.)著；史晓霞等译.神经网络在应用科学和工程中的应用：从基本原理到复杂的模式识别.北京：机械工业出版社,2009.7
19 杨柄儒.基于内在机理的知识发现理论及其应用.北京：电子工业出版社,2004.04
20 侯媛彬,杜京义,汪梅.神经网络.西安：西安电子科技大学出版社,2007.8
21 阎平凡,张长水.人工神经网络与模拟进化计算.北京：清华大学出版社,2000
22 楼顺天,施阳.基于MATLAB的系统分析与设计—神经网络.西安：西安电子科技大学出版社,1999.4
23 丛玉良,王宏志.数字信号处理原理及其MATLAB实现.第二版.北京：电子工业出版社,2009.7
34 邹鲲,袁俊泉,龚享铱.MATLAB 6.x信号处理.北京：清华大学出版社,2002,.5
35 李勇等.MATLAB辅助现代工程数字信号处理.西安：西安电子科技大学出版社,2002.10
36 钟秉林,黄仁.机械故障诊断学.北京：机械工业出版社,1997.12
37 Zhang, et al. Wavelet Network. IEEE Trans NN,1992.3:889-898
38 Zhang Jun, et al. Wavelet NN for Function Learning. IEEE Trans on Signal Processing,1995..6:185-1500
39 Pati Y E, et al. Analysis and Synthesis of Feedforward Network Using Discrete Affine Wavelet Transfomations. IEEE Trans NN,1993.4:70-90
40 飞思科技产品研发中心.神经网络理论与MATLAB 7实现.北京：电子工业出版社,2005.3：99-108,231-257
41 孙盛宇.基于小波神经网络的往复压缩机故障诊断方法研究.压缩机技术.2009(5)：28-30
42 瞿子易,罗鑫,谢润成,葛善良,牛会玲,杨露.小波神经网络在隔夹层研究中的应用.石油天然气学报.2009(8)：265-268
43 Bakshi B R, et al. Wave-Net:a Multiresolution, Hierarchinal Neural Network with Localized Learing. AIChE Jour,1993.39:55-85
44 Liang Y, et al. Multiresulution Learning Paradigm and Signal Prediction. IEEE Trans Signal Processing,1997.45:2858-2864
45 Zhang Q. Using Wavelet Network in Nonparametic Estimation. IEEE Trans NN, 1997.8:227-236
46 Reyneri L M. Unification of Neural and Wavelet Networks and Fuzzy Systems. IEEE Trans NN,1999.10:810-814
47 Widrow B, et al. Neural Networks Application in Industry, Business and Science. Communcation of the ACM,1994.37:93-105
48 Sorsa T, Heikki N.Koivo. Neural Networks in Process Fault Diagnosis. IEEE Transaction on System, Man,and Cybernetics,1991.21(4):815-825
49 Venkat Venkatasubramanian, et al. Process Fault Detection and Diagnosis Using Neural Networks-I. Steady-State Processes. Computer chem. Engineering, 1990.14(7):699-712
50 Venkat Venkatasubramanian, King Chan. A Neural Network Methodology for Process Fault Diagnosis. Journal of AIChE 1989,35(12):1993-2002
51 秦前清,杨宗凯.使用小波分析.西安：西安电子科技大学出版社,1995
52 张莹.数控机床机械故障诊断方法的研究及应用.大连理工大学硕士学位论文.2005
53 高龙.基于小波分析和集成神经网络的刀具磨损状态识别技术研究.西南交通大学硕士学位论文.2007
54 王嘉梅.基于MATLAB的数字信号处理与实践开发.西安：西安电子科技大学出版社,2007
55 周玉清,梅雪松,邢建辉,宋利强.基于ePS的大型数控机床状态监测及其应用.制造技术与机床.2009(2)：104-107
56 李纪明.基于DSP运动控制器的丝杠误差动态测控系统.淮海工学院学报(自然科学版).2008(17-2)：15-18
57 程德蓉.基于CBR的数控机床故障诊断学习系统.制造技术与机床.2009(2)：135-138
58 夏太武,黄大贵.基于神经网络联想记忆的数控机床故障诊断系统.制造业自动化.2008(30-7)：21-23
59 孙伟,张文有,袁驰,王永.振动在数控机床故障诊断中的应用.机械研究与应用.2004(17-3)：31-32
60 丁明军,宋丹.基于神经网络的数控机床故障诊断专家系统.机电工程.2007(24-5)：92-94
61 葛红,田联房.信息融合技术在模式识别中的应用.计算机应用研究.2009(26-1)：19-24
2 杜国臣,王士军.机床数控技术.第二版.北京：北京大学出版社2010.1：8-9,269-305
3 陈蔚芳,王宏涛.机床数控技术及应用.北京：科学出版社,2005：12,282-322
4 洪宇.高速滚珠丝杠副综合性能测量系统设计.南京：南京理工大学硕士学位论文,2006
5 王兆坦,刘宪银,满海彬,宋现春,于复生.高速精密滚珠丝杠副性能试验简介.世界制造技术与装备市场.2006(6)：75-78
6 肖正义,焦洁.高速滚珠丝杠副的研发和测试技术.制造技术与机床.2004(4)：95-98
7 邓奕.现代数控机床及应用.北京：国防工业出版社,2008.9：8-32
8 盛兆顺,尹琦岭.设备状态监测与故障诊断技术及应用.北京：化学工业出版社,2003.5：38-78
9 薛年喜.MATLAB在数字信号处理中的应用.北京：清华大学出版社,2003：252-338
10 陈桂明,张明照,戚红雨.应用MATLAB语言处理数字信号与数字图像.北京：科学出版社,2000：201-224,273-306
11 孙万麟,山拜·达拉拜.一种基于小波包和双谱的信号分析方法.现代电子技术.2008(5)：149-151
12 金建新,李冬冬,侯汉松.小波包与灰色理论在车床噪声信号分析中的应用.制造技术与机床.2008(9)：62-64
13 王唯,郑正奇,王晓华,夏薇.小波包特征提取算法在信号分析中应用.电子测量技术.2005(5)：27-28
14 陈侃,傅攀,李威霖,曹伟青.钛合金车削加工过程中刀具磨损状态监测的小波包子带能量变换特征提取新方法.组合机床与自动化加工技术.2011(1)：35-38
15 虞和济,陈长征,张省,周建男.基于神经网络的智能诊断.北京：冶金工业出版社,2000.05
16 飞思科技产品研发中心.MATLAB6.5辅助神经网络分析与设计.北京：电子工业出版社,2003.04
17 丛爽.面向MATLAB工具箱的神经网络理论与应用.第三版.合肥：中国科学技术大 学出版社,2009.04
18 (美)萨马拉辛荷(Samarasinghe. s.)著；史晓霞等译.神经网络在应用科学和工程中的应用：从基本原理到复杂的模式识别.北京：机械工业出版社,2009.7
19 杨柄儒.基于内在机理的知识发现理论及其应用.北京：电子工业出版社,2004.04
20 侯媛彬,杜京义,汪梅.神经网络.西安：西安电子科技大学出版社,2007.8
21 阎平凡,张长水.人工神经网络与模拟进化计算.北京：清华大学出版社,2000
22 楼顺天,施阳.基于MATLAB的系统分析与设计—神经网络.西安：西安电子科技大学出版社,1999.4
23 丛玉良,王宏志.数字信号处理原理及其MATLAB实现.第二版.北京：电子工业出版社,2009.7
34 邹鲲,袁俊泉,龚享铱.MATLAB 6.x信号处理.北京：清华大学出版社,2002,.5
35 李勇等.MATLAB辅助现代工程数字信号处理.西安：西安电子科技大学出版社,2002.10
36 钟秉林,黄仁.机械故障诊断学.北京：机械工业出版社,1997.12
37 Zhang, et al. Wavelet Network. IEEE Trans NN,1992.3:889-898
38 Zhang Jun, et al. Wavelet NN for Function Learning. IEEE Trans on Signal Processing,1995..6:185-1500
39 Pati Y E, et al. Analysis and Synthesis of Feedforward Network Using Discrete Affine Wavelet Transfomations. IEEE Trans NN,1993.4:70-90
40 飞思科技产品研发中心.神经网络理论与MATLAB 7实现.北京：电子工业出版社,2005.3：99-108,231-257
41 孙盛宇.基于小波神经网络的往复压缩机故障诊断方法研究.压缩机技术.2009(5)：28-30
42 瞿子易,罗鑫,谢润成,葛善良,牛会玲,杨露.小波神经网络在隔夹层研究中的应用.石油天然气学报.2009(8)：265-268
43 Bakshi B R, et al. Wave-Net:a Multiresolution, Hierarchinal Neural Network with Localized Learing. AIChE Jour,1993.39:55-85
44 Liang Y, et al. Multiresulution Learning Paradigm and Signal Prediction. IEEE Trans Signal Processing,1997.45:2858-2864
45 Zhang Q. Using Wavelet Network in Nonparametic Estimation. IEEE Trans NN, 1997.8:227-236
46 Reyneri L M. Unification of Neural and Wavelet Networks and Fuzzy Systems. IEEE Trans NN,1999.10:810-814
47 Widrow B, et al. Neural Networks Application in Industry, Business and Science. Communcation of the ACM,1994.37:93-105
48 Sorsa T, Heikki N.Koivo. Neural Networks in Process Fault Diagnosis. IEEE Transaction on System, Man,and Cybernetics,1991.21(4):815-825
49 Venkat Venkatasubramanian, et al. Process Fault Detection and Diagnosis Using Neural Networks-I. Steady-State Processes. Computer chem. Engineering, 1990.14(7):699-712
50 Venkat Venkatasubramanian, King Chan. A Neural Network Methodology for Process Fault Diagnosis. Journal of AIChE 1989,35(12):1993-2002
51 秦前清,杨宗凯.使用小波分析.西安：西安电子科技大学出版社,1995
52 张莹.数控机床机械故障诊断方法的研究及应用.大连理工大学硕士学位论文.2005
53 高龙.基于小波分析和集成神经网络的刀具磨损状态识别技术研究.西南交通大学硕士学位论文.2007
54 王嘉梅.基于MATLAB的数字信号处理与实践开发.西安：西安电子科技大学出版社,2007
55 周玉清,梅雪松,邢建辉,宋利强.基于ePS的大型数控机床状态监测及其应用.制造技术与机床.2009(2)：104-107
56 李纪明.基于DSP运动控制器的丝杠误差动态测控系统.淮海工学院学报(自然科学版).2008(17-2)：15-18
57 程德蓉.基于CBR的数控机床故障诊断学习系统.制造技术与机床.2009(2)：135-138
58 夏太武,黄大贵.基于神经网络联想记忆的数控机床故障诊断系统.制造业自动化.2008(30-7)：21-23
59 孙伟,张文有,袁驰,王永.振动在数控机床故障诊断中的应用.机械研究与应用.2004(17-3)：31-32
60 丁明军,宋丹.基于神经网络的数控机床故障诊断专家系统.机电工程.2007(24-5)：92-94
61 葛红,田联房.信息融合技术在模式识别中的应用.计算机应用研究.2009(26-1)：19-24