基于小波神经网络的齿轮箱故障诊断研究
|
摘要
随着连轧技术的出现,轧机越来越朝着大型化、连续化、自动化的方向发展。轧机的传动系统一旦出现故障,就会造成整台轧机甚至整条生产线的停产,由此将造成巨大的经济损失。在轧机传动系统出现的故障中,齿轮箱的故障占有很大的比例。
齿轮箱的故障诊断方法很多,有振动诊断、声学诊断、油样分析等。其中,振动信号分析是对齿轮箱进行状态监测与故障诊断的重要手段,也是最有效的诊断方法。本文主要对齿轮箱中的齿轮和轴承的振动信号进行分析。
本文对齿轮和轴承进行振动机理研究,找出故障发生的原因。并根据小波去噪理论对测得的信号进行去噪处理,从而有效地去除了混杂在其中的高频噪声信号,提取了故障特征信号频带内的信号成分。
小波神经网络是建立在小波分析基础上的一种新型神经网络,它综合了小波分析的时频分析特性和神经网络的自学习特性。本文将小波神经网络应用到齿轮箱故障诊断当中。通过试验验证,小波神经网络应用到齿轮箱的故障诊断当中,有利于提高故障的确诊率,有着良好的发展前景。
利用MATLAB和Visual C++进行混合编程,并结合nnToolKit神经网络工具包设计出基于小波神经网络的智能诊断程序,该程序界面友好、易于操作、占用空间小、安装方便,并且脱离了MATLAB与VC环境。
With the appearance of tandem rolling, the rolling mills become more and more large-sized、sequential and roboticized. Once the gearing of rolling mill breaks down, the whole rolling mill will be unable to work normally, and the economic losses will be enormous. In the fault of rolling mill’s gearing system, gear-box’s fault holds a large proportion.
There are many methods about fault diagnosis, such as vibration diagnosis、acoustics diagnosis、oil sample analysis and so on. Viabration analysis is widely used in the condition monitoring and fault diagnosis of the gear-box system, and also is the most effective method. Analysing the viabration signal of gear and bearing is the main work of the dissertation.
In the dissertation, the mechanism of gear-box’s vibration is studied, and the reason of fault is found out. And through the theory of de-noise, the high frequency noise is excluded and the characteristic signal frequency band is abstracted.
Wavelet neural network which is based on wavelet analysis rationale is a sort of new neural network. It incorporates the time-frequency character of the wavelet analysis and the self-study function of the neural network. In the paper, the wavelet neural network is applied in fault diagnosis of the gear-box. The results of the experimentation show that the wavelet neural network which is applied in fault diagnosis will increase the accuracy and will have a good develop tendency.
The intelligentized diagnosis program is designed which combines nnToolKit neural network toolbox with MATLAB and Visual C++. The program , which gets rid of MATLAB and VC environment, has humanization interface , is easy to work and install.
齿轮箱的故障诊断方法很多,有振动诊断、声学诊断、油样分析等。其中,振动信号分析是对齿轮箱进行状态监测与故障诊断的重要手段,也是最有效的诊断方法。本文主要对齿轮箱中的齿轮和轴承的振动信号进行分析。
本文对齿轮和轴承进行振动机理研究,找出故障发生的原因。并根据小波去噪理论对测得的信号进行去噪处理,从而有效地去除了混杂在其中的高频噪声信号,提取了故障特征信号频带内的信号成分。
小波神经网络是建立在小波分析基础上的一种新型神经网络,它综合了小波分析的时频分析特性和神经网络的自学习特性。本文将小波神经网络应用到齿轮箱故障诊断当中。通过试验验证,小波神经网络应用到齿轮箱的故障诊断当中,有利于提高故障的确诊率,有着良好的发展前景。
利用MATLAB和Visual C++进行混合编程,并结合nnToolKit神经网络工具包设计出基于小波神经网络的智能诊断程序,该程序界面友好、易于操作、占用空间小、安装方便,并且脱离了MATLAB与VC环境。
With the appearance of tandem rolling, the rolling mills become more and more large-sized、sequential and roboticized. Once the gearing of rolling mill breaks down, the whole rolling mill will be unable to work normally, and the economic losses will be enormous. In the fault of rolling mill’s gearing system, gear-box’s fault holds a large proportion.
There are many methods about fault diagnosis, such as vibration diagnosis、acoustics diagnosis、oil sample analysis and so on. Viabration analysis is widely used in the condition monitoring and fault diagnosis of the gear-box system, and also is the most effective method. Analysing the viabration signal of gear and bearing is the main work of the dissertation.
In the dissertation, the mechanism of gear-box’s vibration is studied, and the reason of fault is found out. And through the theory of de-noise, the high frequency noise is excluded and the characteristic signal frequency band is abstracted.
Wavelet neural network which is based on wavelet analysis rationale is a sort of new neural network. It incorporates the time-frequency character of the wavelet analysis and the self-study function of the neural network. In the paper, the wavelet neural network is applied in fault diagnosis of the gear-box. The results of the experimentation show that the wavelet neural network which is applied in fault diagnosis will increase the accuracy and will have a good develop tendency.
The intelligentized diagnosis program is designed which combines nnToolKit neural network toolbox with MATLAB and Visual C++. The program , which gets rid of MATLAB and VC environment, has humanization interface , is easy to work and install.
引文
1虞和济,韩庆大.设备故障诊断工程.北京:冶金工业出版社,2001:1-15
2虞和济,陈长征,张省,等.基于神经网络的智能诊断.北京:冶金工业出版社,2002:3-5
3张建宇,高立新.故障诊断技术在轧机维护中的应用.轧钢,2005,4(22):44-45
4 James E.Berry.How of Track Rolling Element Bearing Health with Vibration Signature Analysis. Sound and Vibration, November,1991:24-35
5 G. J. Li. J. Ma, B.Hwang. Bearing Condition Monitoring by Pattern Recognition based on Bicoherence Analysis of Vibrations. Journal of Mechnical Engineering Science, 1999,Vol.210:277-285
6黄建鸿.基于小波包分析的滚动轴承故障智能诊断.[南昌大学硕士学位论文].2005:2-4
7姚俊武,徐超,袁斌.机械设备故障监测与诊断系统综述.黄石高等专科学校学报,2002,28(2):13-15
8 W.J.WANG, J.CHEN ,X.K.WU. The application of some non-linear methods in rotating machinery fault diagnosis. Mechanical Systems and Signal Processing, 2001,15(4):697- 705
9 Chong-Won Lee, Chee-Young Joh. Development of the use of directional frequency response functions for the diagnosis of anisotropy and asymmetry in rotating machinery. Mechanical Systems and Signal Processing,1994,8(6):665-678
10 Zaidi, J DAllen, E L Schwarts, et al. CREW: Compression with Reversible Embedded Wavelet[A]. In Proceedings of Data Compression Conference[C]. Snowbird, Utah, 1995:212-221
11钱学玲,闫晓薇,王建林.小波变换在信号处理中的应用.福建电脑,2006,(9):62-89
12 S Geronimo, D P Hardin, P R Massopust. Fractal Functions and Wavelet Expansions Based on Several Scaling Functions[J]. J of Approx Theory,1994,78:373-401
13 G Strang, V Strela. Short Wavelets and Matrix Dilation Equations[J].IEEE Trans on SP,1995,43:108-115
14 J Lebrun, M Vetterli. Short Wavelets and Matrix Dilation Equations[J].IEEE Trans on SP,1998,46(4):1119-1125
15 Q T Jiang. Orthogonal Multiwavelets with Optimum Time-frequency Resolutions[J]. IEE -E Trans SP,1998,46(4):830-844
16 Q T Jiang. On the Design of Multifilter Banks and Orthonormal Multiwavelet Bases[J].IEEE Trans SP,1998,46(12):3292-3304
17 H Ozkaramanli. Unified Approach for Constructing Multi-wavelets with Approximation Order Using Redinable Super-functions[C].IEEE Proc-Vis.Image Signal Process,2003, 150(3):143-152
18 T R Dowine, B W Silveiman. The Discrete Multiple Wavelet Transform and Thresholdin -g Methods[J].IEEE Trans SP,1998,46(9):2558-2561
19陈世福,陈兆乾编著.人工智能与知识工程.南京:南京大学出版社,1998:2-10
20韩捷,张瑞林.旋转机械故障机理及诊断技术.北京:机械工业出版社,1997:121-156
21陈克兴.设备状态监测与故障诊断技术.北京:科学技术文献出版社,1991:2-16
22 D.Bently. Predictive maintenance through the monitoring and diagnosties of rolling element bearing. Bently Nevada Co, Application Note,1989,44:2-8
23马亮.小波包络分析在滚动轴承和齿轮故障诊断中的应用.[东北大学硕士学位论文].2007:8-15
24屈梁生.机械故障诊断学.上海:上海科学技术出版社,1986:81-86
25廖伯瑜.机械故障诊断基础.北京:冶金工业出版社,1995:108-138
26李辉.滚动轴承和齿轮振动信号分析与故障诊断方法.[西北工业大学硕士学位论文].2001:10-25
27 Jan W.Kantelhardt, H.E Duardo, Roman, Martin Greiner. Discrete Wavelet Approach to Multifractality. Physica,A,1995(220):219-238
28 C.Karanikas. The Hausdorff Dimension of Very Weak Self-similar Fractals Described by the Harr Wavelet System .Chaos,Solitons and Fractals,2000,(11):275-280
29 R Zbigniew,Struzik. Wavelet Methods in (Financial)Time-series Processing. Physica A,2001,(296):307-319
30 Arnord J.Mandell,Karen A Selz,Michael F.Shlesinger. Wavelet Transformation of Protein Hydrophobicity Sequences Suggests Their Memberships in Structural Families. Physica,A,1997(220):254-262
31 R R Coifman,Y Meyer,M.V Wickerhauser. Wavelet Analysis and Signal Processing.In Wavelets and Their Applications. Boston: Jones and Barlett,1992:153-178
32孙延奎.小波分析及其应用.北京:机械工业出版社,2005:35-36
33叶高翔,王焱.基于小波变换的滚动轴承故障诊断系统[J].机电工程,2007,24(7):19-21
34郑治真,沈萍,杨选辉.小波变换及其MATLAB工具的应用.北京:地震出版社,2001:2-75
35胡昌华,张军波.基于MATLAB的系统分析与设计—小波分析.西安:西安电子科技大学出版社,1999:20-23
36高成,董长虹.Matlab小波分析与应用(第二版).北京:国防工业出版社,2007,7:105-107
37王平.基于小波神经网络的电机轴承故障诊断.[太原理工大学工学硕士学位论文].2005:33-35
38田岩涛.基于DSP的CCD信号的小波去噪方法研究.[燕山大学工学硕士学位论文].2005:37-44
39王洪元.人工神经网络技术及其应用.北京:中国石化出版社,2002:3-10
40韩力群.人工神经网络理论、设计及应用.北京:化学工业出版社,2001:25-26
41高隽.人工神经网络原理及仿真实例.北京:机械工业出版社,2003:45-49
42 Rao S S.Multi-objective Optimization of fuzzy Structural System.Int,J.Number,Methods in Eng,1987:1158-1170
43罗晓署.人工神经网络理论·模型·算法与应用.桂林:广西师范大学出版社,2005:45-47
44周宇恒,赵书玲,李钟侠.BP神经网络泛化能力的改进方法[J].测控技术,2004,23(5):63-64
45魏海坤,徐嗣鑫,宋文忠.神经网络的泛化理论和泛化方法[J].自动化学报,2001,27(6):806-815
46林俊,章兢.BP神经网络泛化性能的改善[J].计算机与现代化,2001,3:1-5
47孙功星,戴长江,戴贵亮.训练样本的选取对网络性能的影响[J].核电子学和探测技术,1996,16(6):401-404
48葛哲学,孙志强.神经网络理论与MATLABR2007实现.北京:电子工业出版社,2007:111-113
49聂国斌,赵亮,伉大俪.小波神经网络技术在故障诊断中的应用.工业技术,2007,16:51
50 A.M.Reza.“From Fourier transform to wavelet transform”.White Paper of UWM,Oct.1999:2-5
51赵纪元.基于小波理论·神经网络的实用诊断技术研究.[西安交通大学博士学位论文].1997:30-35
52荆双喜,张英琦.小波分析用于提升机振动故障诊断的研究.机械传动,1999,(23):26-29
53马建仓,吴启彬.小波包分析在旋转机械冲击故障诊断中的应用研究.机械科学与技术,1998,(17):310-312
54王芸.小波变换在转子故障诊断中的应用.[东北大学硕士学位论文].2005:37-39
55 Rachel E.Learned, Alan S.Willsky. A Wavelet Packet Approach to Transient Signal Classification[J]. Applied and Computational Harmonic Analysis,1995,(2):265-278
56杜建伟.基于神经网络的齿轮箱故障分析诊断系统.[燕山大学工学硕士学位论文].2008:61-63
57孙晔,李光耀.基于COM的VC与MATLAB联合编程在图像处理中的应用.微型电脑应用,2007,23(12):51-53
58周灵.基于COM的VC调用Matlab的方法及实现.中国科技信息,2006,24:131-133
59赵耀,吕运鹏.基于COM接口的VC++与MATLAB混合编程.计算机与信息技术,2008,(3):57-59
60张良均,曹晶,蒋世忠.神经网络实用教程.北京:机械工业出版社,2008:46-57
2虞和济,陈长征,张省,等.基于神经网络的智能诊断.北京:冶金工业出版社,2002:3-5
3张建宇,高立新.故障诊断技术在轧机维护中的应用.轧钢,2005,4(22):44-45
4 James E.Berry.How of Track Rolling Element Bearing Health with Vibration Signature Analysis. Sound and Vibration, November,1991:24-35
5 G. J. Li. J. Ma, B.Hwang. Bearing Condition Monitoring by Pattern Recognition based on Bicoherence Analysis of Vibrations. Journal of Mechnical Engineering Science, 1999,Vol.210:277-285
6黄建鸿.基于小波包分析的滚动轴承故障智能诊断.[南昌大学硕士学位论文].2005:2-4
7姚俊武,徐超,袁斌.机械设备故障监测与诊断系统综述.黄石高等专科学校学报,2002,28(2):13-15
8 W.J.WANG, J.CHEN ,X.K.WU. The application of some non-linear methods in rotating machinery fault diagnosis. Mechanical Systems and Signal Processing, 2001,15(4):697- 705
9 Chong-Won Lee, Chee-Young Joh. Development of the use of directional frequency response functions for the diagnosis of anisotropy and asymmetry in rotating machinery. Mechanical Systems and Signal Processing,1994,8(6):665-678
10 Zaidi, J DAllen, E L Schwarts, et al. CREW: Compression with Reversible Embedded Wavelet[A]. In Proceedings of Data Compression Conference[C]. Snowbird, Utah, 1995:212-221
11钱学玲,闫晓薇,王建林.小波变换在信号处理中的应用.福建电脑,2006,(9):62-89
12 S Geronimo, D P Hardin, P R Massopust. Fractal Functions and Wavelet Expansions Based on Several Scaling Functions[J]. J of Approx Theory,1994,78:373-401
13 G Strang, V Strela. Short Wavelets and Matrix Dilation Equations[J].IEEE Trans on SP,1995,43:108-115
14 J Lebrun, M Vetterli. Short Wavelets and Matrix Dilation Equations[J].IEEE Trans on SP,1998,46(4):1119-1125
15 Q T Jiang. Orthogonal Multiwavelets with Optimum Time-frequency Resolutions[J]. IEE -E Trans SP,1998,46(4):830-844
16 Q T Jiang. On the Design of Multifilter Banks and Orthonormal Multiwavelet Bases[J].IEEE Trans SP,1998,46(12):3292-3304
17 H Ozkaramanli. Unified Approach for Constructing Multi-wavelets with Approximation Order Using Redinable Super-functions[C].IEEE Proc-Vis.Image Signal Process,2003, 150(3):143-152
18 T R Dowine, B W Silveiman. The Discrete Multiple Wavelet Transform and Thresholdin -g Methods[J].IEEE Trans SP,1998,46(9):2558-2561
19陈世福,陈兆乾编著.人工智能与知识工程.南京:南京大学出版社,1998:2-10
20韩捷,张瑞林.旋转机械故障机理及诊断技术.北京:机械工业出版社,1997:121-156
21陈克兴.设备状态监测与故障诊断技术.北京:科学技术文献出版社,1991:2-16
22 D.Bently. Predictive maintenance through the monitoring and diagnosties of rolling element bearing. Bently Nevada Co, Application Note,1989,44:2-8
23马亮.小波包络分析在滚动轴承和齿轮故障诊断中的应用.[东北大学硕士学位论文].2007:8-15
24屈梁生.机械故障诊断学.上海:上海科学技术出版社,1986:81-86
25廖伯瑜.机械故障诊断基础.北京:冶金工业出版社,1995:108-138
26李辉.滚动轴承和齿轮振动信号分析与故障诊断方法.[西北工业大学硕士学位论文].2001:10-25
27 Jan W.Kantelhardt, H.E Duardo, Roman, Martin Greiner. Discrete Wavelet Approach to Multifractality. Physica,A,1995(220):219-238
28 C.Karanikas. The Hausdorff Dimension of Very Weak Self-similar Fractals Described by the Harr Wavelet System .Chaos,Solitons and Fractals,2000,(11):275-280
29 R Zbigniew,Struzik. Wavelet Methods in (Financial)Time-series Processing. Physica A,2001,(296):307-319
30 Arnord J.Mandell,Karen A Selz,Michael F.Shlesinger. Wavelet Transformation of Protein Hydrophobicity Sequences Suggests Their Memberships in Structural Families. Physica,A,1997(220):254-262
31 R R Coifman,Y Meyer,M.V Wickerhauser. Wavelet Analysis and Signal Processing.In Wavelets and Their Applications. Boston: Jones and Barlett,1992:153-178
32孙延奎.小波分析及其应用.北京:机械工业出版社,2005:35-36
33叶高翔,王焱.基于小波变换的滚动轴承故障诊断系统[J].机电工程,2007,24(7):19-21
34郑治真,沈萍,杨选辉.小波变换及其MATLAB工具的应用.北京:地震出版社,2001:2-75
35胡昌华,张军波.基于MATLAB的系统分析与设计—小波分析.西安:西安电子科技大学出版社,1999:20-23
36高成,董长虹.Matlab小波分析与应用(第二版).北京:国防工业出版社,2007,7:105-107
37王平.基于小波神经网络的电机轴承故障诊断.[太原理工大学工学硕士学位论文].2005:33-35
38田岩涛.基于DSP的CCD信号的小波去噪方法研究.[燕山大学工学硕士学位论文].2005:37-44
39王洪元.人工神经网络技术及其应用.北京:中国石化出版社,2002:3-10
40韩力群.人工神经网络理论、设计及应用.北京:化学工业出版社,2001:25-26
41高隽.人工神经网络原理及仿真实例.北京:机械工业出版社,2003:45-49
42 Rao S S.Multi-objective Optimization of fuzzy Structural System.Int,J.Number,Methods in Eng,1987:1158-1170
43罗晓署.人工神经网络理论·模型·算法与应用.桂林:广西师范大学出版社,2005:45-47
44周宇恒,赵书玲,李钟侠.BP神经网络泛化能力的改进方法[J].测控技术,2004,23(5):63-64
45魏海坤,徐嗣鑫,宋文忠.神经网络的泛化理论和泛化方法[J].自动化学报,2001,27(6):806-815
46林俊,章兢.BP神经网络泛化性能的改善[J].计算机与现代化,2001,3:1-5
47孙功星,戴长江,戴贵亮.训练样本的选取对网络性能的影响[J].核电子学和探测技术,1996,16(6):401-404
48葛哲学,孙志强.神经网络理论与MATLABR2007实现.北京:电子工业出版社,2007:111-113
49聂国斌,赵亮,伉大俪.小波神经网络技术在故障诊断中的应用.工业技术,2007,16:51
50 A.M.Reza.“From Fourier transform to wavelet transform”.White Paper of UWM,Oct.1999:2-5
51赵纪元.基于小波理论·神经网络的实用诊断技术研究.[西安交通大学博士学位论文].1997:30-35
52荆双喜,张英琦.小波分析用于提升机振动故障诊断的研究.机械传动,1999,(23):26-29
53马建仓,吴启彬.小波包分析在旋转机械冲击故障诊断中的应用研究.机械科学与技术,1998,(17):310-312
54王芸.小波变换在转子故障诊断中的应用.[东北大学硕士学位论文].2005:37-39
55 Rachel E.Learned, Alan S.Willsky. A Wavelet Packet Approach to Transient Signal Classification[J]. Applied and Computational Harmonic Analysis,1995,(2):265-278
56杜建伟.基于神经网络的齿轮箱故障分析诊断系统.[燕山大学工学硕士学位论文].2008:61-63
57孙晔,李光耀.基于COM的VC与MATLAB联合编程在图像处理中的应用.微型电脑应用,2007,23(12):51-53
58周灵.基于COM的VC调用Matlab的方法及实现.中国科技信息,2006,24:131-133
59赵耀,吕运鹏.基于COM接口的VC++与MATLAB混合编程.计算机与信息技术,2008,(3):57-59
60张良均,曹晶,蒋世忠.神经网络实用教程.北京:机械工业出版社,2008:46-57