基于RBF神经网络的齿轮箱故障诊断
|
摘要
阐述径向基函数(radial base function,RBF)神经网络的基本原理和算法,将其应用于齿轮箱故障诊断与识别,建立齿轮箱的BRF故障诊断模型,并与BP(back propagation)神经网络、学习率自适应BP神经网络进行对比分析研究。结果表明,RBF神经网络性能优于BP神经网络,具有较快的训练速度、较强的非线性映射能力和精度较高的故障识别能力,非常适用于齿轮箱的状态监测和故障诊断。但在具体应用中应当注意,RBF网络的训练样本必须含有一定的噪声,以提高网络的容噪性能;各类故障的训练样本数不能太少,否则RBF网络的故障分类能力很差。
The basic theory and arithmetic of RBF(radial basis function) neural network were expatiated,which was applied successfully to gearbox fault diagnosis,the RBF fault diagnosis model of gearbox was constructed,and was analyzed contrastively with the BP neural network and learning rate self-adaptive BP(back propagation) neural network. The study result shows that RBF neural network's well performance,with the quick training pace,strong nonlinear mapped capability and highly accurate capability of fault identification,is superior to the BP neural network,and it is very suitable to the condition monitoring and fault diagnosis of gearbox. But during the practical application,which must notice that,the trained samples must include some noise in order to improve network's capability of noise-tolerant; trained samples of each type fault can't be few,otherwise,the fault classification capability of RBF network is worse.
The basic theory and arithmetic of RBF(radial basis function) neural network were expatiated,which was applied successfully to gearbox fault diagnosis,the RBF fault diagnosis model of gearbox was constructed,and was analyzed contrastively with the BP neural network and learning rate self-adaptive BP(back propagation) neural network. The study result shows that RBF neural network's well performance,with the quick training pace,strong nonlinear mapped capability and highly accurate capability of fault identification,is superior to the BP neural network,and it is very suitable to the condition monitoring and fault diagnosis of gearbox. But during the practical application,which must notice that,the trained samples must include some noise in order to improve network's capability of noise-tolerant; trained samples of each type fault can't be few,otherwise,the fault classification capability of RBF network is worse.
引文
[1]Robert J,SchillingJames,Carroll J.Approximation of nonlinear systems withradial basisfunction neural networks[J].IEEETransactions on Neu-ral Networks,2001,12(1):21-28.
[2]李志农,丁启全,吴昭同,等.双相干谱和RBF网络在旋转机械故障诊断中的应用[J].机械强度,2003,25(4):360-363.LI ZhiNong,DINGQiQuan,WUZhaoTong,et al.Bicoherence spectrum andradial basisfunction network appliedtofault diagnosis of rotating ma-chinery[J].Journal of Mechanical Strength,2003,25(4):360-363(In Chinese).
[3]王炜,吴耿锋,张博锋,王媛.径向基函数(RBF)神经网络及其应用[J].地震,2005,25(2):19-25.WANG Wei,WU GengFeng,ZHANG BoFeng,WANG Yuan.Neural networks of radial basis function(RBF)and it’s application to earth-quake prediction[J].Earthquake,2005,25(2):19-25(In Chinese).
[4]Pedryz W.Conditional fuzzy clusteringinthe design of radial basisfunc-tion neural networks[J].IEEE Trans.Neural Networks,1998,9:601-612.
[5]Deng Chao,Xiong Fan-lun.An Efficient on-line Learning Method for Radial Basis Function Neural Networks[J].Journal of Electronics and Information Technology,2001,23(5):472-478.
[6]Bi Tianshu,Yan Zheng,Wen Fushuan,et.al.On-line distributed fault section estimation system with radial basis function neural network[J].Power SystemTechnology,2001,25(11):27-32;2001,25(11):37.
[7]郭秀荣,陆怀民,窦美霞,等.基于MATLAB软件包程序的电喷发动机故障诊断[J].中国工程机械学报,2007,5(1):95-99.GUOXiuRong,LU Haui Min,DOU MeiXia,et al.Fault diagnosis for electronic ejection engine using MATLAB software package[J].Chinese Journal of Construction Machinery,2007,5(1):95-9(In Chinese).
[8]丁康,朱小勇.齿轮箱典型故障振动特征与诊断策略[J].振动与冲击,2001,20(3):7-12.DING Kang,ZHU XiaoYong.Typical vibration character and diagnosis strategy of gearbox[J].Journal of Vibrationand Shock,2001,20(3):7-12(In Chinese).
[9]荆双喜,冷军发,李臻.基于小波-神经网络的矿用通风机故障诊断研究[J].煤炭学报,2004,29(6):736-739.JINGShuangXi,LENG JunFa,LI Zhen.Study on the mine ventilator fault diagnosis based on wavelet packet and neural network[J].Journal of China Coal Society,2004,29(6):736-39(In Chinese).
[2]李志农,丁启全,吴昭同,等.双相干谱和RBF网络在旋转机械故障诊断中的应用[J].机械强度,2003,25(4):360-363.LI ZhiNong,DINGQiQuan,WUZhaoTong,et al.Bicoherence spectrum andradial basisfunction network appliedtofault diagnosis of rotating ma-chinery[J].Journal of Mechanical Strength,2003,25(4):360-363(In Chinese).
[3]王炜,吴耿锋,张博锋,王媛.径向基函数(RBF)神经网络及其应用[J].地震,2005,25(2):19-25.WANG Wei,WU GengFeng,ZHANG BoFeng,WANG Yuan.Neural networks of radial basis function(RBF)and it’s application to earth-quake prediction[J].Earthquake,2005,25(2):19-25(In Chinese).
[4]Pedryz W.Conditional fuzzy clusteringinthe design of radial basisfunc-tion neural networks[J].IEEE Trans.Neural Networks,1998,9:601-612.
[5]Deng Chao,Xiong Fan-lun.An Efficient on-line Learning Method for Radial Basis Function Neural Networks[J].Journal of Electronics and Information Technology,2001,23(5):472-478.
[6]Bi Tianshu,Yan Zheng,Wen Fushuan,et.al.On-line distributed fault section estimation system with radial basis function neural network[J].Power SystemTechnology,2001,25(11):27-32;2001,25(11):37.
[7]郭秀荣,陆怀民,窦美霞,等.基于MATLAB软件包程序的电喷发动机故障诊断[J].中国工程机械学报,2007,5(1):95-99.GUOXiuRong,LU Haui Min,DOU MeiXia,et al.Fault diagnosis for electronic ejection engine using MATLAB software package[J].Chinese Journal of Construction Machinery,2007,5(1):95-9(In Chinese).
[8]丁康,朱小勇.齿轮箱典型故障振动特征与诊断策略[J].振动与冲击,2001,20(3):7-12.DING Kang,ZHU XiaoYong.Typical vibration character and diagnosis strategy of gearbox[J].Journal of Vibrationand Shock,2001,20(3):7-12(In Chinese).
[9]荆双喜,冷军发,李臻.基于小波-神经网络的矿用通风机故障诊断研究[J].煤炭学报,2004,29(6):736-739.JINGShuangXi,LENG JunFa,LI Zhen.Study on the mine ventilator fault diagnosis based on wavelet packet and neural network[J].Journal of China Coal Society,2004,29(6):736-39(In Chinese).
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