基于VMD和ICA的发动机故障特征增强研究
|
摘要
针对发动机噪声信号信噪比低、故障特征提取困难等问题,提出一种基于变分模态分解(VMD)结合独立分量分析(ICA)的降噪方法。首先通过VMD分解得到分量中心频率确定合适的分解层数,以峭度准则重构噪声信号和故障信号,然后通过FastICA将重构信号再次分解,得到降噪后的故障信号,最后与经验模态分解(EMD)降噪对比,结合实例和仿真表明,该方法能够有效抑制模态混叠,增强发动机噪声信号故障特征。
To solve the engine noise signal problems such as low signal-to-noise ratio and difficult extraction of fault features,the paper puts forward a new noise reduction method on the basis of variational mode decomposition(VMD) and independent component analysis(ICA). This method determines the proper decomposition layers by component center frequency decomposed with VMD, uses kurtosis criterion to reconstruct the noise and fault signals, which are decomposed again with FastICA to obtain the denoised fault signal. Both example and simulation results show that when compared to empirical mode decomposition(EMD) noise reduction, this method can effectively suppress modal overlap and enhance fault features.
To solve the engine noise signal problems such as low signal-to-noise ratio and difficult extraction of fault features,the paper puts forward a new noise reduction method on the basis of variational mode decomposition(VMD) and independent component analysis(ICA). This method determines the proper decomposition layers by component center frequency decomposed with VMD, uses kurtosis criterion to reconstruct the noise and fault signals, which are decomposed again with FastICA to obtain the denoised fault signal. Both example and simulation results show that when compared to empirical mode decomposition(EMD) noise reduction, this method can effectively suppress modal overlap and enhance fault features.
引文
[1]HSIAO Y Z,PEI S C.Edge detection,color quantization,segmentation,texture removal,and noise reduction of color image using quaternion iterative filtering[J].Journal of Electronic Imaging,2014,23(4):43.
[2]贾伟宽,赵德安,阮承治,等.苹果夜视图像小波变换与独立成分分析融合降噪方法[J].农业机械学报,2015,46(9):9-17.
[3]HAN J,VAN DER BAAN M.Microseismic and seismic denoising via ensemble empirical mode decomposition and adaptive thresholding[J].Geophysics,2015,80(6):69-80.
[4]BAGHAIE A,D'SOUZA R M,YU Z.Application of independent component analysis techniques in speckle noise reduction of retinal OCT images[J].Optik-International Journal for Light and Electron Optics,2016,127(15):5783-5791.
[5]杨伟新,王平.EMD-ICA与SVM在滚动轴承故障诊断中的应用[J].噪声与振动控制,2014,34(3):182-185.
[6]张俊红,李林洁,马文朋,等.EMD-ICA联合降噪在滚动轴承故障诊断中的应用[J].中国机械工程,2013,24(11):1468-1472.
[7]GILLES J.Empirical wavelet transform[J].IEEE Transactions on Signal Processing,2013,61(16):3999-4010.
[8]赵昕海,张术臣,李志深,等.基于VMD的故障特征信号提取方法[J].振动.测试与诊断,2018(1):2.
[9]郑近德,姜战伟,代俊习,等.基于VMD的自适应复合多尺度模糊熵及其在滚动轴承故障诊断中的应用[J].航空动力学报,2017,32(7):1683-1689.
[10]马增强,李亚超,刘政,等.基于变分模态分解和Teager能量算子的滚动轴承故障特征提取[J].振动与冲击,2016,35(13):134-139.
[11]向玲,张力佳.基于VMD和1.5维Teager能量谱的滚动轴承故障特征提取[J].振动与冲击,2017,36(18):98-104.
[12]徐信,李志华,杨越.基于EMD-ICA的激电数据降噪处理方法[J].计算机应用研究,2017,34(6):1737-1739.
[13]WEI T.A convergence and asymptotic analysis of the generalized symmetric FastICA algorithm[J].IEEE Transactions on Signal Processing,2015,63(24):6445-6458.
[14]蒋章雷,徐小力,卞家磊.LMD-ICA联合降噪方法在滚动轴承振动信号中的降噪性能分析[J].北京信息科技大学学报(自然科学版),2017,32(3):13-17.
[2]贾伟宽,赵德安,阮承治,等.苹果夜视图像小波变换与独立成分分析融合降噪方法[J].农业机械学报,2015,46(9):9-17.
[3]HAN J,VAN DER BAAN M.Microseismic and seismic denoising via ensemble empirical mode decomposition and adaptive thresholding[J].Geophysics,2015,80(6):69-80.
[4]BAGHAIE A,D'SOUZA R M,YU Z.Application of independent component analysis techniques in speckle noise reduction of retinal OCT images[J].Optik-International Journal for Light and Electron Optics,2016,127(15):5783-5791.
[5]杨伟新,王平.EMD-ICA与SVM在滚动轴承故障诊断中的应用[J].噪声与振动控制,2014,34(3):182-185.
[6]张俊红,李林洁,马文朋,等.EMD-ICA联合降噪在滚动轴承故障诊断中的应用[J].中国机械工程,2013,24(11):1468-1472.
[7]GILLES J.Empirical wavelet transform[J].IEEE Transactions on Signal Processing,2013,61(16):3999-4010.
[8]赵昕海,张术臣,李志深,等.基于VMD的故障特征信号提取方法[J].振动.测试与诊断,2018(1):2.
[9]郑近德,姜战伟,代俊习,等.基于VMD的自适应复合多尺度模糊熵及其在滚动轴承故障诊断中的应用[J].航空动力学报,2017,32(7):1683-1689.
[10]马增强,李亚超,刘政,等.基于变分模态分解和Teager能量算子的滚动轴承故障特征提取[J].振动与冲击,2016,35(13):134-139.
[11]向玲,张力佳.基于VMD和1.5维Teager能量谱的滚动轴承故障特征提取[J].振动与冲击,2017,36(18):98-104.
[12]徐信,李志华,杨越.基于EMD-ICA的激电数据降噪处理方法[J].计算机应用研究,2017,34(6):1737-1739.
[13]WEI T.A convergence and asymptotic analysis of the generalized symmetric FastICA algorithm[J].IEEE Transactions on Signal Processing,2015,63(24):6445-6458.
[14]蒋章雷,徐小力,卞家磊.LMD-ICA联合降噪方法在滚动轴承振动信号中的降噪性能分析[J].北京信息科技大学学报(自然科学版),2017,32(3):13-17.
© 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 |