遗传算法结合小波神经网络的列车车轮扁疤故障检测方法
|
摘要
为了寻求一种更加有效的列车车轮扁疤故障分析算法,提出一种通过轮轨噪声来确定车轮扁疤严重程度的检测方法。该方法将遗传算法与小波神经网络相结合,同时为了避免出现局部极小值,加速学习速度,在小波神经网络中增加了动量模型;在搜寻小波神经网络隐含层链接权值之前,使用遗传算法进行计算以优化小波神经网络结构;硬件只需2组麦克风阵列以及2个速度感应器就可以提供实时结果,成本远低于我国现有的检测方法。对不同列车车速下的轮轨信号进行了实时测试,结果表明:与传统神经网络、小波神经网络和遗传算法相比,该方法的检测准确率最多分别提高了16%、11%和3%,并且收敛最快。
A novel strategy is proposed to provide a more effective wheel flat scar fault detection algorithm by means of wheel/rail noise.In this strategy,genetic algorithm is combined with a wavelet neural network,and a momentum model is added into the genetic wavelet neural network to avoid the local minimum and to accelerate the learning speed.Before searching the hidden-layer weights of the network,the structure of the network is optimized by genetic algorithm.This strategy requires only two groups of microphone arrays and two speed sensors for real-time measurements.Consequently,the cost is much lower than that of the existing detection methods in China.The proposed strategy has been applied to the real-time detection of train wheel/rail signals at different speeds.Numerical results reveal that the proposed strategy is of the fastest convergence,and its detection accuracy increases at most by 16%,10%,and 3%,respectively,compared with the conventional neural network,wavelet neural network,and genetic algorithm.
A novel strategy is proposed to provide a more effective wheel flat scar fault detection algorithm by means of wheel/rail noise.In this strategy,genetic algorithm is combined with a wavelet neural network,and a momentum model is added into the genetic wavelet neural network to avoid the local minimum and to accelerate the learning speed.Before searching the hidden-layer weights of the network,the structure of the network is optimized by genetic algorithm.This strategy requires only two groups of microphone arrays and two speed sensors for real-time measurements.Consequently,the cost is much lower than that of the existing detection methods in China.The proposed strategy has been applied to the real-time detection of train wheel/rail signals at different speeds.Numerical results reveal that the proposed strategy is of the fastest convergence,and its detection accuracy increases at most by 16%,10%,and 3%,respectively,compared with the conventional neural network,wavelet neural network,and genetic algorithm.
引文
[1]BELOTTI V,CRENNA F,MICHELINI R C,et al.Time evolutionary analysis:operator driven paradigms for fault diagnosis[C]∥Proceedings of the Third IEEE International Symposium on Diagnostics for Electrical Machines,Power Electronics and Drives.Piscataway,NJ,USA:IEEE,2001:253-258.
[2]SACKFIELD A,DINI D,HILLS D A.Contact of a rotating wheel with a flat[J].International Journal of Solids and Structures,2007,44:3304-3316.
[3]DALPIAZ G,RIVOLA A.Condition monitoring and diagnostics in automatic machines:comparison of vibration analysis techniques[J].Mechanical Systems and Signal Processing,1997,11:53-73.
[4]翟婉明.车辆-轨道耦合动力学[M].北京:中国铁道出版社,1997:40-47.
[5]刘继,冯铭.车轮踏面擦伤在线自动检测方法的研究和试验[J].铁道车辆,1995,31(2):28-30.
[6]小田博基,等.踏面擦伤检测装置的开发[J].国外铁道车辆,1993(2):53-56.
[7]张格明,冯毅杰,刘慕哥.车辆超偏载及运行状态安全监测系统的研究和运用[C]∥中国铁道学会2000年学术年会论文集.北京:中国铁道学会,2000:53-62.
[8]IONESCU O.车轮外形磨耗自动检测系统[J].国外铁道车辆,1995(4):53-57.
[9]卢汝钧.美国车轮踏面擦伤检测系统[J].国外铁道车辆,1994(6):54-56.
[10]郑治真,沈萍,杨选辉,等.小波变换及其MATLAB工具的使用[M].北京:地震出版社,2001:38-47.
[11]牛东晓,邢棉.时间序列的小波神经网络预测模型的研究[J].系统工程理论与实践,1999(5):89-92.NIU Dongxiao,XING Mian.A study on wavelet neural network prediction model of time series[J].Systems Engineering:Theory&Practice,1999(5):89-92.
[2]SACKFIELD A,DINI D,HILLS D A.Contact of a rotating wheel with a flat[J].International Journal of Solids and Structures,2007,44:3304-3316.
[3]DALPIAZ G,RIVOLA A.Condition monitoring and diagnostics in automatic machines:comparison of vibration analysis techniques[J].Mechanical Systems and Signal Processing,1997,11:53-73.
[4]翟婉明.车辆-轨道耦合动力学[M].北京:中国铁道出版社,1997:40-47.
[5]刘继,冯铭.车轮踏面擦伤在线自动检测方法的研究和试验[J].铁道车辆,1995,31(2):28-30.
[6]小田博基,等.踏面擦伤检测装置的开发[J].国外铁道车辆,1993(2):53-56.
[7]张格明,冯毅杰,刘慕哥.车辆超偏载及运行状态安全监测系统的研究和运用[C]∥中国铁道学会2000年学术年会论文集.北京:中国铁道学会,2000:53-62.
[8]IONESCU O.车轮外形磨耗自动检测系统[J].国外铁道车辆,1995(4):53-57.
[9]卢汝钧.美国车轮踏面擦伤检测系统[J].国外铁道车辆,1994(6):54-56.
[10]郑治真,沈萍,杨选辉,等.小波变换及其MATLAB工具的使用[M].北京:地震出版社,2001:38-47.
[11]牛东晓,邢棉.时间序列的小波神经网络预测模型的研究[J].系统工程理论与实践,1999(5):89-92.NIU Dongxiao,XING Mian.A study on wavelet neural network prediction model of time series[J].Systems Engineering:Theory&Practice,1999(5):89-92.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心