基于全信息技术的远程诊断关键技术研究
|
摘要
随着机械设备的大型化、自动化、高速化和复杂化，使得设备状态监测和故障诊断技术变得越来越重要。传统的机械故障诊断大都以单通道信号分析为基础，从中提取有关机器行为的特征信息。虽然利用一种信息有时可以判断机器的故障，但在许多情况下得出的诊断结果并不可靠。转子一个截面上的振动信息一般是由相互垂直两个径向和一个轴向传感器拾取的，一个截面上的通道属同源信息，它们之间必然存在一定的关系，对这些信息在数据层次上采用全信息技术融合可以较全面的获得转子信息。然而转子的振动是一个空间的范畴，对一个截面的同源信息融合也只能最大限度反映这一个截面转子的振动信息，所以根据转子一个截面的振动信息诊断出来的结果往往也是片面的。因此，采用转子多个截面信息进行故障的诊断是必要的。
本文结合转子空间振动和现场实际，利用转子两截面信息，建立一种数据层、特征层和决策层三种层次混合融合诊断模型，全信息技术和集成概率神经网络是实现该模型的关键技术。本文把全信息技术中的全息谱、全谱和全矢谱分别应用于诊断模型，并对三种方法的诊断结果从各个方面进行了比较，最后得出结论是全矢谱是最有发展前途的一种全信息分析技术。
在全信息技术中，全矢谱由于其良好的信息处理方式，使其拓展出一系列的分析方法。本文讨论了在故障诊断中几种有意义的矢谱拓展分析方法：矢功率谱、矢倒谱和针对非平稳信号的矢Wigner分布，并把这些分析方法应用于故障诊断中，用实际信号验证了其诊断准确性。
本文在理论探讨的基础上，应用C++Builder5.0构建了基于Browser／Server模式的远程全信息故障诊断系统，系统实现了基于全信息技术及全矢谱拓展分析方法的故障诊断，诊断结论准确可靠。
With the advancement of modern science and technology, the equipments tend to be larger, faster as well as more roboticized and complicated, which makes technology of state monitoring and fault diagnosis more and more important. But the traditional fault diagnosis of machinery is based on the analysis of the signal coming from single channel from which the character information about the machinery action is picked up. Although using individual information can reflect the machinery faults sometimes, in many instances the diagnosis result is irresponsible. Commonly the vibration information of one rotor's section is picked up from two radial sensors and a axes sensor,one section's channels belong to same dimension,so inevitably each other of them exists certain relation, accordingly these information fusion at data level through full information technology can farthest show the section's informations the diagnosis result sometimes is unilateral on the basis of rotor's one section. Therefore it is necessary to
recognize faults according to the rotor's multi-sections information.
Combining with the rotor space vibration and the field practical situation.and making use of the rotor two ends, The thesis founds a model of data level and character level and decision level mixture fusion,and the key techniques to realize the model are the full information and integration Probabilistic Neural Network. The thesis applys Full-spectrum and Holospectrum and Vector-spectrum to the diagnosis model,and compare the diagnosis result of the three methods,finally the conclusion is that the Vector-spectrum is the best of the full information.
The Vector-spectrum of full information continues a series of analysis methods because of its good information processing way. The thesis discusses several important analysis methods to fault diagnosis: Vector power spectrum and Vector-cepstrum and Vector-Wigner that used to analysis stationary signals,and combines these methods width system model to diagnose faults as well as validates the methods veracity.
After the rigorous study of the theory, using the C++ Builder5.0 as the developing tool, a full information fault diagnosis system was visualized, which based on the mode of
Browser/Server and can run on the Internet. Also the full information and the Vector-spectrum's continued methods are visualized,and the diagnosis conclusion is exact and reliable.
本文结合转子空间振动和现场实际，利用转子两截面信息，建立一种数据层、特征层和决策层三种层次混合融合诊断模型，全信息技术和集成概率神经网络是实现该模型的关键技术。本文把全信息技术中的全息谱、全谱和全矢谱分别应用于诊断模型，并对三种方法的诊断结果从各个方面进行了比较，最后得出结论是全矢谱是最有发展前途的一种全信息分析技术。
在全信息技术中，全矢谱由于其良好的信息处理方式，使其拓展出一系列的分析方法。本文讨论了在故障诊断中几种有意义的矢谱拓展分析方法：矢功率谱、矢倒谱和针对非平稳信号的矢Wigner分布，并把这些分析方法应用于故障诊断中，用实际信号验证了其诊断准确性。
本文在理论探讨的基础上，应用C++Builder5.0构建了基于Browser／Server模式的远程全信息故障诊断系统，系统实现了基于全信息技术及全矢谱拓展分析方法的故障诊断，诊断结论准确可靠。
With the advancement of modern science and technology, the equipments tend to be larger, faster as well as more roboticized and complicated, which makes technology of state monitoring and fault diagnosis more and more important. But the traditional fault diagnosis of machinery is based on the analysis of the signal coming from single channel from which the character information about the machinery action is picked up. Although using individual information can reflect the machinery faults sometimes, in many instances the diagnosis result is irresponsible. Commonly the vibration information of one rotor's section is picked up from two radial sensors and a axes sensor,one section's channels belong to same dimension,so inevitably each other of them exists certain relation, accordingly these information fusion at data level through full information technology can farthest show the section's informations the diagnosis result sometimes is unilateral on the basis of rotor's one section. Therefore it is necessary to
recognize faults according to the rotor's multi-sections information.
Combining with the rotor space vibration and the field practical situation.and making use of the rotor two ends, The thesis founds a model of data level and character level and decision level mixture fusion,and the key techniques to realize the model are the full information and integration Probabilistic Neural Network. The thesis applys Full-spectrum and Holospectrum and Vector-spectrum to the diagnosis model,and compare the diagnosis result of the three methods,finally the conclusion is that the Vector-spectrum is the best of the full information.
The Vector-spectrum of full information continues a series of analysis methods because of its good information processing way. The thesis discusses several important analysis methods to fault diagnosis: Vector power spectrum and Vector-cepstrum and Vector-Wigner that used to analysis stationary signals,and combines these methods width system model to diagnose faults as well as validates the methods veracity.
After the rigorous study of the theory, using the C++ Builder5.0 as the developing tool, a full information fault diagnosis system was visualized, which based on the mode of
Browser/Server and can run on the Internet. Also the full information and the Vector-spectrum's continued methods are visualized,and the diagnosis conclusion is exact and reliable.
引文
[1] 韩捷，张瑞林等．旋转机械故障机理及诊断技术[M]．北京：机械工业出版社，1996
[2] 孙惠国，张瑞林．设备状态监测与故障诊断[M]．郑州：河南科学技术出版社，1992
[3] 袁小宏，屈梁生．机械故障诊断中的信息融合利用问题研究[J]．振动、测试与诊断，1999，19(3)：187-192
[4] 马平．多信息融合技术在旋转机械故障诊断中的应用研究(硕士论文)．哈尔滨工业大学，2002
[5] E. Waltz, J. Linas. Multisensor Data Fusion. Boston:Artech House, 1990
[6] 彭备战．信息融合技术在设备故障诊断中的应用研究(硕士论文)．广东工业大学，2002
[7] 王耀南，李树涛．多传感器信息融合及应用综述[J]．控制与决策，2001，16(5)：518-522
[8] N. Xiong, P. Svensson. Multi-sensor management for information fusion: issues and approaches[J]. Information Fusion, 2002,3:163-186
[9] Waltz E, Linas J. Multisensor Data Fusion. Boston:Attech House, 1990
[10] 潘泉等．信息融合理论的基本方法与进展[J]．自动化学报，2003，29(4)：599-615
[11] 刘同明等．数据融合技术及其应用[M]．北京：国防工业出版社，1998
[12] 徐毅等．数据融合研究的回顾与展望[J]．信息与控制，2002，31(3)：250-253
[13] 龚元明，萧德云，王俊杰．多传感器数据融合技术(上)．冶金自动化，2002，NO(4)：4-7
[14] Southwick, D., "Using Full Spectrum Plots," Orbit, Vol. 14, No 4, December 1993, Bently Nevada Corporation
[15] Southwick, D., "Using Full Spectrum Plots Part 2, "Orbit, Vol. 14, No 5, June 1993, Bently Nevada Corporation
[16] Laws, B., "When you use spectrum, don't use it halfway," Orbit, Vol. 18, No 2, June 1998, Bently Nevada Corporation
[17] Goldman, P.,Muszynska, A., "Apllication of full spectrum to rotating machinery diagnostics," Orbit, Vol., No 1, First Quarter 1999, Bently Nevada Corporation
[18] Qu LiangSheng, Liu Xiong, et al. Discovering the holospectrum. J. Noise & Vibration Vorldwide, 1989, 20(2): 58-63.
[19] 屈梁生，史东锋．全息谱十年：回顾与展望[J]．振动、测试与诊断，1998，18(4)：235-243．
[20] 韩捷，关惠玲，梁川等．矢谱——一种实用的旋转机械故障诊断分析方法[J]．机械强度，1998，20(3)：212～215．
[21] 韩捷，关惠玲，梁川等．旋转机械故障诊断的进动谱研究[J]．振动工程学报，1998，13(11)：67-71．
[22] 韩捷，张琳娜．旋转机械振动的谱强度计量[J]．计量技术，1997，6：22～25．
[23] Torfinn Taxt., Anne H. Schistad Solberg. Information fusion in remote sensing. Vistas in Astronomy, 1997,41(3):337-342
[24] 姜万绿，李冲祥，刘继刚．多传感器数据融合技术的现状及展望[J]．机床与液压，2003(3)：16-18
[25] 钟一谔，何衍宗．转子动力学[M]．北京：清华：大学出版社，1987．165-172．
[26] 韩捷，石来德．全谱分析技术及其在故障诊断种的应用[J]．郑州大学学报(工学版)，2002，23(3)：44-47
[27] 韩捷，石来德．旋转机械的全信息能量谱分析方法研究[J]．机械强度，2003，25(4)：364-368
[28] 杜永祚，秦志英．旋转机械动态信号全息谱分析[J]．振动、测试与诊断，2002，22(2)：81-89
[29] 张辉，张浩，严隽薇，王坚．基于神经元网络及CORBA的远程故障诊断系统[J]．计算机工程，2002，28(8)：143-145
[30] 叶志峰，孙健国．基于概率神经网络的发动机故障诊断[J]．航空学报，2002，23(2)：155～157
[31] 王柏生，倪一清，高赞明．用概率神经网络进行结构损伤位置识别[J]．振动工程学报，2001，14(1)：60-63
[32] 黄德双．神经网络模式识别系统理论[M]．北京：电子工业出版社，1996
[33] 姜绍飞，刘奎浩，廖云，贾连光．基于概率神经网络的悬索桥损伤定位研究[J]．东北大学学报，2002，23(5)：480-483
[34] Michael R. Berthold, Jay Diamond. Constructive training of probabilistic neural networks[J]. Neurocomputing, 1998(19): 167-183
[35] 徐旺林．概率神经网络及其在地球物理勘探中的应用(硕士论文)．兰州大学，2001
[36] P. Torfs. Local Probabilistic Neural Networks in Hydrology. Phys. Chem. Earth(B),2000,26(1),pp:9-14
[37] Z.R. Yang, Mariorie B. Platt. Probabilistic Neural Networks in Bankruptcy Prediction. J Bush Res, 1999:44:67-74
[38] Steven H. Kim, Se Hak Chun. Graded forecasting using an array of bipolar prediction: application of probabilistic neural networks to a stock market index. International Journal Forecasting, 1998(14):323-337
[39] S. Simani, C. Fantuzzi. Fault diagnosis in power plant using neural networks. Information Sciences, 2000(127):125-136
[40] 虞和济，陈长征，张省，周建南．基于神经网络的智能诊断[M]．北京：冶金工业出版社，2000
[41] 甘晓华，刘宝权．集成神经网络在设备诊断中的应用．机械科学与技术，2001，20(4)：638-640
[42] 张志学，霍志红，唐必光．基于集成神经网络的故障诊断[M]．风机技术，2002(5)
[43] R.J. Kuo, P.H. Cohen. Multi-sensor integration for on-line tool wear estimation through radial basis function networks and fuzzy neural network. Neural Networks, 1999(12):355-370
[43] 陈大喜，朱铁光．大型回转机械诊断现场实用技术，北京：机械工业出版社，2002
[44] 冯志鹏等．旋转机械振动故障诊断理论与技术紧张综述．振动与冲击，2001，20(4)：36-39
[45] 罗锦，孟晨，苏振中．故障诊断技术的发展与展望．自动化与仪器仪表，2003(2)：1－2
[46] 徐章遂，房立清，王希武，左宪章．故障信息诊断原理及应用，北京：国防工业出版社，2000
[47] 钟秉林，黄仁．机械故障诊断学，北京：机械工业出版社，1997
[48] 黄文虎，夏松波，刘瑞岩等．设备故障诊断原理、技术及其应用，北京：科学出版社，1996
[49] 胡广书．数字信号处理，北京：清华大学出版社，1997
[50] 毕果，韩捷，梁川．基于矢量振动信号的AR功率谱分析及应用．郑州大学学报，2003，24(2)，80-83
[51] Dalpiaz. G, Rivola. A, Rubini. R. Effectiveness and sensitivity of vibration processing techniques for laocal fault detection in gears. Mechanical Systems and Signal Processing, 2000,14(3):387-412
[52] 王萍辉，方应民．倒频谱分析在旋转机械故障诊断中的应用．长沙电力学院学报(自然科学版)，1999，14(3)：249-256
[53] S.A. Neild, P.D. McFadden, M.S. Willianms. A review of time-frequency methods for structural vibration analysis. Engineering Structures, 25(2003):713-728
[54] YONG BEUM KIM, ect. A study on technique to eatimate impact loacation of loose part using Wigner-Ville distribution. Progress in Nuclear Energy, 2003,43(1-4):261-266
[55] 何正嘉等．机械设备非平稳信号的故障诊断原理及应用．北京：高等教育出版社，2001
[56] W.J. Staszewski, ect. Time frequency analysis in gearbox fault detection using the Wigner-Ville distribution and pattern recognition. Mechanical System and Signal Processing, 1997, 11(5):673-692
[57] J.K. Hammond, P.R. White. The analysis of non-stationary signals using time-frequency method. Journal of Sound and Vibration, 1996, 190(3): 419-447
[58] (美)Rose．Z主编．C++Builder数据库与Web数据库．上海：浦东电子出版社，2002
[59] 周绪，韦文斌等．SQL Server7.0入门与提高[M]．北京：清华大学出版社，2000．
[60] 杨光，杨拥民，袁杰红等．基于B／S模型的设备远程诊断系统的研究[J]．测控技术，2002，20(6)：16-18．
[61] Bill Laws. Remote machinery diagnostics: Acost-effectiveway to improve plant safety, productivity and profitability[J]. Orbit, 1995,7:13-15.
[62] Nee A.Y.C. Web-based fault diagnostic and learning system[J]. International Journal of Advanced Manufacturing Technology, 2001, 18(7): 502-511.
[63] 劳佳锋，沈力学，盛颂恩．基于数据库技术的远程故障诊断专家系统的研究．机电工程，2003，20(5)：73-74
[2] 孙惠国，张瑞林．设备状态监测与故障诊断[M]．郑州：河南科学技术出版社，1992
[3] 袁小宏，屈梁生．机械故障诊断中的信息融合利用问题研究[J]．振动、测试与诊断，1999，19(3)：187-192
[4] 马平．多信息融合技术在旋转机械故障诊断中的应用研究(硕士论文)．哈尔滨工业大学，2002
[5] E. Waltz, J. Linas. Multisensor Data Fusion. Boston:Artech House, 1990
[6] 彭备战．信息融合技术在设备故障诊断中的应用研究(硕士论文)．广东工业大学，2002
[7] 王耀南，李树涛．多传感器信息融合及应用综述[J]．控制与决策，2001，16(5)：518-522
[8] N. Xiong, P. Svensson. Multi-sensor management for information fusion: issues and approaches[J]. Information Fusion, 2002,3:163-186
[9] Waltz E, Linas J. Multisensor Data Fusion. Boston:Attech House, 1990
[10] 潘泉等．信息融合理论的基本方法与进展[J]．自动化学报，2003，29(4)：599-615
[11] 刘同明等．数据融合技术及其应用[M]．北京：国防工业出版社，1998
[12] 徐毅等．数据融合研究的回顾与展望[J]．信息与控制，2002，31(3)：250-253
[13] 龚元明，萧德云，王俊杰．多传感器数据融合技术(上)．冶金自动化，2002，NO(4)：4-7
[14] Southwick, D., "Using Full Spectrum Plots," Orbit, Vol. 14, No 4, December 1993, Bently Nevada Corporation
[15] Southwick, D., "Using Full Spectrum Plots Part 2, "Orbit, Vol. 14, No 5, June 1993, Bently Nevada Corporation
[16] Laws, B., "When you use spectrum, don't use it halfway," Orbit, Vol. 18, No 2, June 1998, Bently Nevada Corporation
[17] Goldman, P.,Muszynska, A., "Apllication of full spectrum to rotating machinery diagnostics," Orbit, Vol., No 1, First Quarter 1999, Bently Nevada Corporation
[18] Qu LiangSheng, Liu Xiong, et al. Discovering the holospectrum. J. Noise & Vibration Vorldwide, 1989, 20(2): 58-63.
[19] 屈梁生，史东锋．全息谱十年：回顾与展望[J]．振动、测试与诊断，1998，18(4)：235-243．
[20] 韩捷，关惠玲，梁川等．矢谱——一种实用的旋转机械故障诊断分析方法[J]．机械强度，1998，20(3)：212～215．
[21] 韩捷，关惠玲，梁川等．旋转机械故障诊断的进动谱研究[J]．振动工程学报，1998，13(11)：67-71．
[22] 韩捷，张琳娜．旋转机械振动的谱强度计量[J]．计量技术，1997，6：22～25．
[23] Torfinn Taxt., Anne H. Schistad Solberg. Information fusion in remote sensing. Vistas in Astronomy, 1997,41(3):337-342
[24] 姜万绿，李冲祥，刘继刚．多传感器数据融合技术的现状及展望[J]．机床与液压，2003(3)：16-18
[25] 钟一谔，何衍宗．转子动力学[M]．北京：清华：大学出版社，1987．165-172．
[26] 韩捷，石来德．全谱分析技术及其在故障诊断种的应用[J]．郑州大学学报(工学版)，2002，23(3)：44-47
[27] 韩捷，石来德．旋转机械的全信息能量谱分析方法研究[J]．机械强度，2003，25(4)：364-368
[28] 杜永祚，秦志英．旋转机械动态信号全息谱分析[J]．振动、测试与诊断，2002，22(2)：81-89
[29] 张辉，张浩，严隽薇，王坚．基于神经元网络及CORBA的远程故障诊断系统[J]．计算机工程，2002，28(8)：143-145
[30] 叶志峰，孙健国．基于概率神经网络的发动机故障诊断[J]．航空学报，2002，23(2)：155～157
[31] 王柏生，倪一清，高赞明．用概率神经网络进行结构损伤位置识别[J]．振动工程学报，2001，14(1)：60-63
[32] 黄德双．神经网络模式识别系统理论[M]．北京：电子工业出版社，1996
[33] 姜绍飞，刘奎浩，廖云，贾连光．基于概率神经网络的悬索桥损伤定位研究[J]．东北大学学报，2002，23(5)：480-483
[34] Michael R. Berthold, Jay Diamond. Constructive training of probabilistic neural networks[J]. Neurocomputing, 1998(19): 167-183
[35] 徐旺林．概率神经网络及其在地球物理勘探中的应用(硕士论文)．兰州大学，2001
[36] P. Torfs. Local Probabilistic Neural Networks in Hydrology. Phys. Chem. Earth(B),2000,26(1),pp:9-14
[37] Z.R. Yang, Mariorie B. Platt. Probabilistic Neural Networks in Bankruptcy Prediction. J Bush Res, 1999:44:67-74
[38] Steven H. Kim, Se Hak Chun. Graded forecasting using an array of bipolar prediction: application of probabilistic neural networks to a stock market index. International Journal Forecasting, 1998(14):323-337
[39] S. Simani, C. Fantuzzi. Fault diagnosis in power plant using neural networks. Information Sciences, 2000(127):125-136
[40] 虞和济，陈长征，张省，周建南．基于神经网络的智能诊断[M]．北京：冶金工业出版社，2000
[41] 甘晓华，刘宝权．集成神经网络在设备诊断中的应用．机械科学与技术，2001，20(4)：638-640
[42] 张志学，霍志红，唐必光．基于集成神经网络的故障诊断[M]．风机技术，2002(5)
[43] R.J. Kuo, P.H. Cohen. Multi-sensor integration for on-line tool wear estimation through radial basis function networks and fuzzy neural network. Neural Networks, 1999(12):355-370
[43] 陈大喜，朱铁光．大型回转机械诊断现场实用技术，北京：机械工业出版社，2002
[44] 冯志鹏等．旋转机械振动故障诊断理论与技术紧张综述．振动与冲击，2001，20(4)：36-39
[45] 罗锦，孟晨，苏振中．故障诊断技术的发展与展望．自动化与仪器仪表，2003(2)：1－2
[46] 徐章遂，房立清，王希武，左宪章．故障信息诊断原理及应用，北京：国防工业出版社，2000
[47] 钟秉林，黄仁．机械故障诊断学，北京：机械工业出版社，1997
[48] 黄文虎，夏松波，刘瑞岩等．设备故障诊断原理、技术及其应用，北京：科学出版社，1996
[49] 胡广书．数字信号处理，北京：清华大学出版社，1997
[50] 毕果，韩捷，梁川．基于矢量振动信号的AR功率谱分析及应用．郑州大学学报，2003，24(2)，80-83
[51] Dalpiaz. G, Rivola. A, Rubini. R. Effectiveness and sensitivity of vibration processing techniques for laocal fault detection in gears. Mechanical Systems and Signal Processing, 2000,14(3):387-412
[52] 王萍辉，方应民．倒频谱分析在旋转机械故障诊断中的应用．长沙电力学院学报(自然科学版)，1999，14(3)：249-256
[53] S.A. Neild, P.D. McFadden, M.S. Willianms. A review of time-frequency methods for structural vibration analysis. Engineering Structures, 25(2003):713-728
[54] YONG BEUM KIM, ect. A study on technique to eatimate impact loacation of loose part using Wigner-Ville distribution. Progress in Nuclear Energy, 2003,43(1-4):261-266
[55] 何正嘉等．机械设备非平稳信号的故障诊断原理及应用．北京：高等教育出版社，2001
[56] W.J. Staszewski, ect. Time frequency analysis in gearbox fault detection using the Wigner-Ville distribution and pattern recognition. Mechanical System and Signal Processing, 1997, 11(5):673-692
[57] J.K. Hammond, P.R. White. The analysis of non-stationary signals using time-frequency method. Journal of Sound and Vibration, 1996, 190(3): 419-447
[58] (美)Rose．Z主编．C++Builder数据库与Web数据库．上海：浦东电子出版社，2002
[59] 周绪，韦文斌等．SQL Server7.0入门与提高[M]．北京：清华大学出版社，2000．
[60] 杨光，杨拥民，袁杰红等．基于B／S模型的设备远程诊断系统的研究[J]．测控技术，2002，20(6)：16-18．
[61] Bill Laws. Remote machinery diagnostics: Acost-effectiveway to improve plant safety, productivity and profitability[J]. Orbit, 1995,7:13-15.
[62] Nee A.Y.C. Web-based fault diagnostic and learning system[J]. International Journal of Advanced Manufacturing Technology, 2001, 18(7): 502-511.
[63] 劳佳锋，沈力学，盛颂恩．基于数据库技术的远程故障诊断专家系统的研究．机电工程，2003，20(5)：73-74