基于小波神经网络的车辆构架人工蛇形波重构技术的研究
|
摘要
在我国铁路行业,随着高速列车的出现以及铁路的进一步提速,列车脱轨事件也呈上升趋势。脱轨造成人民生命和财产的巨大损失,给铁路安全运输造成了极大的威胁。为了得到列车的安全行驶速度,测量和重构作为列车—桥梁(轨道)系统激励源的车辆构架实测横向振动波(俗称蛇行波)具有重要的理论和工程实际意义。
预测车桥系统的振动响应,关键在于要求得与实际构架实测蛇行波接近的构架人工蛇行波,基于Monte-Carlo的人工蛇行波随机模拟方法只保留了实测数据中的方差作为重构的唯一约束条件,而其他一些重要特征参数,如频率、概率等都没有得到充分的利用,造成了重构过程中的频率和相位的机会平均,导致了最后重构的蛇行波与实测蛇行波有一定的差距。本文针对小波良好的时频局部性及神经网络强大的非线性映射能力,用小波基代替了神经网络中的Sigmoid函数,构造了带有轮盘赌遗传选择机制的小波神经网络,并对160公里/小时广深铁路实测蛇行波数据进行了分析、重构,仿真结果表明这种方法能够有效地保留实测蛇行波的特征参数。
与传统基于Monte-Carlo方法的三角级数随机重构方法相比,基于小波神经网络的人工蛇行波重构方法能够克服重构过程中的频率、相位机会平均,波形可能会出现突变等缺点,经过重构所得到的波形中带有更多实测蛇行波的信息,过渡、衔接地更加自然。该方法也适用于行驶速度高于160公里/小时的高速列车。
In the railroad industry of our country, the appearance of high-speed train and railway system's speed level increasing induce the derail event increasing. Derailed brings huge losing to human being and society property which menace the safety of railway transportation. In order to get the safety speed of the train, measure and rebuild the train crawl wave which is regard as the actuator of Vehicle-Bridge System is the most important.
Firstly, the paper summarize the Vehicle-Bridge System、the factor which results system's vibration and the effect of system's actuator to train's safety in briefly, get the result that the key to predict the response of the Vehicle-Bridge System is to get the artificial crawl wave which is very close to the real crawl wave by measured. Then particular introduce the Monte-Carlo method which is the main means to rebuild artificial crawl wave nowadays. In method research, the random simulation of artificial crawl wave based on Monte-Carlo method only used variance while neglect many other useful information such as frequency and probability, it make chance average of frequency and phase, lead the result is not close the real crawl wave. This paper put out a new method to rebuild the crawl wave, construct the wavelet neural network which contain the roulette wheel select mechanism , process the data which is measured on GuangShen railway at speed 160km/h by wavelet neural networks, utilize the amplitude, frequency and probability adequately, and rebuild the crawl wave by computer. The result show this method can rebuild the crawl wave well.
Compare to the Monte-Carlo method, the method based on wavelet neural network conquer the flaws such as chance average and wave saltation, the wave rebuild by wavelet neural network can be close to the real measured crawl wave. Meanwhile this method can also apply in rebuild high-speed train's crawl wave.
预测车桥系统的振动响应,关键在于要求得与实际构架实测蛇行波接近的构架人工蛇行波,基于Monte-Carlo的人工蛇行波随机模拟方法只保留了实测数据中的方差作为重构的唯一约束条件,而其他一些重要特征参数,如频率、概率等都没有得到充分的利用,造成了重构过程中的频率和相位的机会平均,导致了最后重构的蛇行波与实测蛇行波有一定的差距。本文针对小波良好的时频局部性及神经网络强大的非线性映射能力,用小波基代替了神经网络中的Sigmoid函数,构造了带有轮盘赌遗传选择机制的小波神经网络,并对160公里/小时广深铁路实测蛇行波数据进行了分析、重构,仿真结果表明这种方法能够有效地保留实测蛇行波的特征参数。
与传统基于Monte-Carlo方法的三角级数随机重构方法相比,基于小波神经网络的人工蛇行波重构方法能够克服重构过程中的频率、相位机会平均,波形可能会出现突变等缺点,经过重构所得到的波形中带有更多实测蛇行波的信息,过渡、衔接地更加自然。该方法也适用于行驶速度高于160公里/小时的高速列车。
In the railroad industry of our country, the appearance of high-speed train and railway system's speed level increasing induce the derail event increasing. Derailed brings huge losing to human being and society property which menace the safety of railway transportation. In order to get the safety speed of the train, measure and rebuild the train crawl wave which is regard as the actuator of Vehicle-Bridge System is the most important.
Firstly, the paper summarize the Vehicle-Bridge System、the factor which results system's vibration and the effect of system's actuator to train's safety in briefly, get the result that the key to predict the response of the Vehicle-Bridge System is to get the artificial crawl wave which is very close to the real crawl wave by measured. Then particular introduce the Monte-Carlo method which is the main means to rebuild artificial crawl wave nowadays. In method research, the random simulation of artificial crawl wave based on Monte-Carlo method only used variance while neglect many other useful information such as frequency and probability, it make chance average of frequency and phase, lead the result is not close the real crawl wave. This paper put out a new method to rebuild the crawl wave, construct the wavelet neural network which contain the roulette wheel select mechanism , process the data which is measured on GuangShen railway at speed 160km/h by wavelet neural networks, utilize the amplitude, frequency and probability adequately, and rebuild the crawl wave by computer. The result show this method can rebuild the crawl wave well.
Compare to the Monte-Carlo method, the method based on wavelet neural network conquer the flaws such as chance average and wave saltation, the wave rebuild by wavelet neural network can be close to the real measured crawl wave. Meanwhile this method can also apply in rebuild high-speed train's crawl wave.
引文
[1]曾庆元,向俊,娄平.突破列车脱轨难题的能量随机分析道路.中国工程学报,2002,4(12):9-19
[2]向俊,曾庆元,娄平.再论列车脱轨能量随机分析.中国铁道科学,2002,23(2):26-32
[3]王荣辉,曾庆元,郭向荣,朱汉华.告诉列车构架人工蛇行波V—σ曲线关系的确定.长沙铁道学院学报,1996,14(1):13-19
[4]Zeng Qingyuan,Lou Ping,Xiang Jun.The principle of total potential energy with stationary value in elastic system dynamics and its vibration analysis[A].Proceedings of International Conference on Engineering and Technological Sciences 2000[C],Edited by Song Jian and Zhou Ganshi,Chinese Academy of Engineering,Beijing:Science Press,2000
[5]王荣辉,郭向荣,曾庆元.高速列车构架人工蛇行波的随机模拟方法.1995,13(2):1-7
[6]铁道部科学研究院,济南铁路局,徐州分局.南津浦线货物列车脱轨实验报告.1997
[7]张贤达,保铮.非平稳信号分析与处理[M].北京国防工业出版社1999.
[8]A.V.奥本海姆等,刘树棠译.信号与系统.西安:西安交通大学出版社.1985
[9]郑方,徐明星.信号处理原理.清华大学出版社,2001.
[10]胡广书.数字信号处理理论、算法与实现.北京:清华大学出版社,2003.
[11]杨福生.小波变换的工程分析与应用[M].北京:科学出版社,2000
[12][美]崔景泰著.小波分析导论.程正兴译.西安:西安交通大学出版社,1995
[13]飞思科技产品研发中心.MATLAB6.5辅助小波分析与应用.北京:电子出版社,2003.
[14]程正兴.国外小波及应用概况.工程数学学报,1992,9(3):125-126
[15]关履泰.Wavelet interpolation and decomposition in a finite interval with boundary conditions.工程数学学报,1995,12(3):1-9
[16]Sweldens W.Wavelet:What next?.Proc IEEE,1996,84:680-685
[17]何建军.小波变换及其在电机故障信号检测和分析中的应用研究[D].重庆大学博士论文,1999.
[18]Chui C K,ed.Approximation Theory and Functional Analysis.Boston:Academic Press,1991
[19]Brigham E O著.快速傅立叶变换.柳群译.上海:上海科学技术出版社, 1979
[20]马建仓,吴启彬,薛建武等.基于小波变换的频谱细化分析方法[J].信号处理.1997,13(3):274-279
[21]李银国,曹长修.小波神经网络的构造及其算法的鲁棒性分析.重庆大学学报(自然科学版),1995,18(6):88-95
[22]朱文革.人工神经网络与小波变换.复旦学报(自然科学版),1996,35(1):113-118
[23]虞和济,周永,张省.小波神经网络诊断系统的应用与进展.振动、测试与诊断,1998,18(2):85-90
[24]李银国,张邦礼,等.小波神经网络及其结构设计方法.模式识别与人工智能,1997,9(3):197-205
[25]李焦成.神经网络的应用与实现.西安:西安电子科技大学出版社,1995 215-252
[26]Zhang QingHua and Benveniste A.Wavelet networks.IEEE trans on NN,1992,3(6):889-898
[27]陈哲,冯天瑾.小波神经网络研究进展及展望.青岛海洋大学学报,1999,29(4):663-668
[28]李弼程,罗建书.小波分析及其应用.北京:电子工业出版社,2003.
[29]程正兴.小波分析算法与应用.西安:西安交通大学出版社,2001.
[30]Meyer Y.Wavelet:Algorithms and Applications.Philadelphia.PA:SIAM Press,1993
[31]Chui C K.An Introduction to Wavelets.NewYork:Academic Press,1992
[32]彭玉华.小波变换与工程应用.北京:科学出版社,2000.
[33]曹豫宁,李永丽,梅云等.基于小波变换的频谱细化方法在电动机故障检测中的应用.继电器,2002,(6)
[34]铁道部科学研究院,济南铁路局,徐州分局.南津浦线货物列车脱轨实验报告.1997
[35]Daubechies I.Ten lectures on Wavelets.CBMS-NSF Conference Series in Applied Mathematics.SIAM Ed.1992.
[36]McInerny,S.A.;Dai,Y.;Basic vibration signal processing for bearing fault detection.Education,IEEE Transactions on,Volume:46,Issue:1,Feb.2003 Pages:149-156
[37][印]N.C尼格姆,何成慧等译,随机振动概论,上海:上海交通大学出版 社,1985,10-80
[38]康中尉,罗飞路,潘孟春,等.小波神经网络在缺陷数据压缩和信号重构中的应用.NDT无损检测,2005,27(12):632-636
[39]蔡自兴.智能控制.北京:电子工业出版社,2004
[40]Grossberg S.Neural Networks and Neural Intelligence.Cambridge,Mass :MIT Press,1998
[41]Grant E,Zhang B.A neural net approach to supervised learning of pole balancing.In:Proc.IEEE Int.Symp.On Intelligent Control,1989:123-129
[42]Hopfield J J.Artificial neural networks.IEEE Circuit and Devices Magazine,1988,12
[43]Hunt E B.Artificial Intelligence.New York:Academic Press,1975
[44]Hebb D O.The Organization of Behavior:A NeuropsychoIogical Theory.John Wiley and Sons,New York,1949:60-78
[45]吴大正,杨林耀,张永瑞.信号与线性系统分析.北京:高等教育出版社1998
[46]秦前清,杨宗凯.实用小波分析.西安:西安电子科技大学出版社,1994
[47]胡昌华,张军波等.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
[48]Wavelet Toolbox User's Guide.Mathworks Inc,2002
[49]The Math Works,Inc.http://www.mathworks.com,2002
[50]刘培森.应用傅立叶变换.北京:北京理工大学出版社.1990
[51]胡昌华,李国华,刘涛,周志杰.基于MATLAB 6.x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,2004
[52]陈涛,屈梁生.多分辨小波网络的理论及应用.中国机械工程,1997(8):57-59
[53]吕柏权,李天铎,刘兆辉.基于BP神经网络与小波的控制研究.系统仿真学报,1997(9):40-48
[54]许静,韩雷.基于神经网络的小波分析及其在突发噪声识别中的应用.传感技术学报,1999(3):189-194
[55]魏恒义,程竹林,刘伟娜,曹雪.基于小波分析的网络流量随机模拟.西安交通大学学报,2003(2):188-191
[56]谢培甫.基于小波分析和BP神经网络的滚动轴承的故障诊断.农业装备与车辆工程,2006(2):45-47
[57]尹念东,夏宇.小波分析在车辆工程中的应用.黄石高等专科学校学报,2000(16):1-3
[58]邵辉成,杜兴信,金学申,杜长娥.小波分析在地震趋势预测中的应用.中国地震,2000(16):48-53
[59]张民,丁常富,韩中合.小波分析在振动信号处理领域中的应用.电力情报,2001(3):5-8
[2]向俊,曾庆元,娄平.再论列车脱轨能量随机分析.中国铁道科学,2002,23(2):26-32
[3]王荣辉,曾庆元,郭向荣,朱汉华.告诉列车构架人工蛇行波V—σ曲线关系的确定.长沙铁道学院学报,1996,14(1):13-19
[4]Zeng Qingyuan,Lou Ping,Xiang Jun.The principle of total potential energy with stationary value in elastic system dynamics and its vibration analysis[A].Proceedings of International Conference on Engineering and Technological Sciences 2000[C],Edited by Song Jian and Zhou Ganshi,Chinese Academy of Engineering,Beijing:Science Press,2000
[5]王荣辉,郭向荣,曾庆元.高速列车构架人工蛇行波的随机模拟方法.1995,13(2):1-7
[6]铁道部科学研究院,济南铁路局,徐州分局.南津浦线货物列车脱轨实验报告.1997
[7]张贤达,保铮.非平稳信号分析与处理[M].北京国防工业出版社1999.
[8]A.V.奥本海姆等,刘树棠译.信号与系统.西安:西安交通大学出版社.1985
[9]郑方,徐明星.信号处理原理.清华大学出版社,2001.
[10]胡广书.数字信号处理理论、算法与实现.北京:清华大学出版社,2003.
[11]杨福生.小波变换的工程分析与应用[M].北京:科学出版社,2000
[12][美]崔景泰著.小波分析导论.程正兴译.西安:西安交通大学出版社,1995
[13]飞思科技产品研发中心.MATLAB6.5辅助小波分析与应用.北京:电子出版社,2003.
[14]程正兴.国外小波及应用概况.工程数学学报,1992,9(3):125-126
[15]关履泰.Wavelet interpolation and decomposition in a finite interval with boundary conditions.工程数学学报,1995,12(3):1-9
[16]Sweldens W.Wavelet:What next?.Proc IEEE,1996,84:680-685
[17]何建军.小波变换及其在电机故障信号检测和分析中的应用研究[D].重庆大学博士论文,1999.
[18]Chui C K,ed.Approximation Theory and Functional Analysis.Boston:Academic Press,1991
[19]Brigham E O著.快速傅立叶变换.柳群译.上海:上海科学技术出版社, 1979
[20]马建仓,吴启彬,薛建武等.基于小波变换的频谱细化分析方法[J].信号处理.1997,13(3):274-279
[21]李银国,曹长修.小波神经网络的构造及其算法的鲁棒性分析.重庆大学学报(自然科学版),1995,18(6):88-95
[22]朱文革.人工神经网络与小波变换.复旦学报(自然科学版),1996,35(1):113-118
[23]虞和济,周永,张省.小波神经网络诊断系统的应用与进展.振动、测试与诊断,1998,18(2):85-90
[24]李银国,张邦礼,等.小波神经网络及其结构设计方法.模式识别与人工智能,1997,9(3):197-205
[25]李焦成.神经网络的应用与实现.西安:西安电子科技大学出版社,1995 215-252
[26]Zhang QingHua and Benveniste A.Wavelet networks.IEEE trans on NN,1992,3(6):889-898
[27]陈哲,冯天瑾.小波神经网络研究进展及展望.青岛海洋大学学报,1999,29(4):663-668
[28]李弼程,罗建书.小波分析及其应用.北京:电子工业出版社,2003.
[29]程正兴.小波分析算法与应用.西安:西安交通大学出版社,2001.
[30]Meyer Y.Wavelet:Algorithms and Applications.Philadelphia.PA:SIAM Press,1993
[31]Chui C K.An Introduction to Wavelets.NewYork:Academic Press,1992
[32]彭玉华.小波变换与工程应用.北京:科学出版社,2000.
[33]曹豫宁,李永丽,梅云等.基于小波变换的频谱细化方法在电动机故障检测中的应用.继电器,2002,(6)
[34]铁道部科学研究院,济南铁路局,徐州分局.南津浦线货物列车脱轨实验报告.1997
[35]Daubechies I.Ten lectures on Wavelets.CBMS-NSF Conference Series in Applied Mathematics.SIAM Ed.1992.
[36]McInerny,S.A.;Dai,Y.;Basic vibration signal processing for bearing fault detection.Education,IEEE Transactions on,Volume:46,Issue:1,Feb.2003 Pages:149-156
[37][印]N.C尼格姆,何成慧等译,随机振动概论,上海:上海交通大学出版 社,1985,10-80
[38]康中尉,罗飞路,潘孟春,等.小波神经网络在缺陷数据压缩和信号重构中的应用.NDT无损检测,2005,27(12):632-636
[39]蔡自兴.智能控制.北京:电子工业出版社,2004
[40]Grossberg S.Neural Networks and Neural Intelligence.Cambridge,Mass :MIT Press,1998
[41]Grant E,Zhang B.A neural net approach to supervised learning of pole balancing.In:Proc.IEEE Int.Symp.On Intelligent Control,1989:123-129
[42]Hopfield J J.Artificial neural networks.IEEE Circuit and Devices Magazine,1988,12
[43]Hunt E B.Artificial Intelligence.New York:Academic Press,1975
[44]Hebb D O.The Organization of Behavior:A NeuropsychoIogical Theory.John Wiley and Sons,New York,1949:60-78
[45]吴大正,杨林耀,张永瑞.信号与线性系统分析.北京:高等教育出版社1998
[46]秦前清,杨宗凯.实用小波分析.西安:西安电子科技大学出版社,1994
[47]胡昌华,张军波等.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
[48]Wavelet Toolbox User's Guide.Mathworks Inc,2002
[49]The Math Works,Inc.http://www.mathworks.com,2002
[50]刘培森.应用傅立叶变换.北京:北京理工大学出版社.1990
[51]胡昌华,李国华,刘涛,周志杰.基于MATLAB 6.x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,2004
[52]陈涛,屈梁生.多分辨小波网络的理论及应用.中国机械工程,1997(8):57-59
[53]吕柏权,李天铎,刘兆辉.基于BP神经网络与小波的控制研究.系统仿真学报,1997(9):40-48
[54]许静,韩雷.基于神经网络的小波分析及其在突发噪声识别中的应用.传感技术学报,1999(3):189-194
[55]魏恒义,程竹林,刘伟娜,曹雪.基于小波分析的网络流量随机模拟.西安交通大学学报,2003(2):188-191
[56]谢培甫.基于小波分析和BP神经网络的滚动轴承的故障诊断.农业装备与车辆工程,2006(2):45-47
[57]尹念东,夏宇.小波分析在车辆工程中的应用.黄石高等专科学校学报,2000(16):1-3
[58]邵辉成,杜兴信,金学申,杜长娥.小波分析在地震趋势预测中的应用.中国地震,2000(16):48-53
[59]张民,丁常富,韩中合.小波分析在振动信号处理领域中的应用.电力情报,2001(3):5-8
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |