[1]曾建仙,杨启斌.核独立分量分析在结构振动信号降噪中的应用[J].福建理工大学学报,2015,13(04):317-322.[doi:10.3969/j.issn.1672-4348.2015.04.003]
　Zeng Jianxian,Yang Qibin.The application of kernel independent component analysis in structural vibration signal noise reduction[J].Journal of Fujian University of Technology;,2015,13(04):317-322.[doi:10.3969/j.issn.1672-4348.2015.04.003]
点击复制

核独立分量分析在结构振动信号降噪中的应用()
分享到：

《福建理工大学学报》[ISSN:2097-3853/CN:35-1351/Z]

卷:
第13卷
期数:
2015年04期
页码:
317-322
栏目:
出版日期:
2015-08-25

文章信息/Info

Title:
The application of kernel independent component analysis in structural vibration signal noise reduction
作者:
曾建仙; 杨启斌
福建工程学院土木工程学院
Author(s):
Zeng Jianxian;  Yang Qibin
College of Civil Engineering, Fujian University of Technology
关键词:
核独立分量;  结构振动;  信号处理;  降噪;  HHT边际谱
Keywords:
kernel independent component (KIC);  structural vibration;  signal processing;  noise reduction;  marginal spectrum of Hilbert-Huang transform
分类号:
TU12; TB123
DOI:
10.3969/j.issn.1672-4348.2015.04.003
文献标志码:
A
摘要:
降噪处理是分析结构振动信号、提取特征参数、研究损伤识别方法的基础，核独立分量分析(KICA)采用的核方法为结构振动信号的降噪处理提供了新的方法；通过对比KICA与其他算法降噪后信号的HHT边际谱，验证了KICA对低阻尼钢框架结构标准损伤模型降噪的优良性能，特别是提高了对结构安全至关重要的低频振动部分的能量估计的准确度。
Abstract:
Noise reduction is the basis of analysing structural vibration signals, extracting feature parameters and exploring damage identification methods. The method of kernel independent component analysis (KICA) has provided a new way for the noise reduction of structural vibration signals. The marginal spectra of Hilbert-Huang transform ( HHT) of signals denoised by KICA were compared to that of other available algorithms. The reliable performance of KICA in noise reduction of standard damage model of steel frame structure with low damping was verified. The estimation accuracy of low frequency vibration energy that is the critical part of structural safety was considerably improved.

参考文献/References:

[1] 冯高明,朱高中,郑征，等.新型小波阈值法在变频调速系统信号消噪中的应用[J].河南理工大学学报：自然科学版, 2009(1):100-106.
[2] 杨燕,袁海庆,赵丽芝.独立分量分析在结构振动信号降噪中的应用[J].华中科技大学学报：城市科学版,2008(9):234-237.
[3] Hyvarinen A, Karhunen J, Oja E.独立成分分析[M].周宗潭，译.北京:电子工业出版社,2007.
[4] 段承璋.基于核独立分量分析的混合语音信号分离[J].重庆工学院学报：自然科学版,2009(11):113-122.
[5] 刘婷婷,任兴民,杨永锋.核独立分量分析在机械振动信号分离中的应用[J].西北工业大学学报,2011(2):109-113.
[6] Bach F R, Jordan M I. Kernel independent component analysis[J]. Journal of Machine Learning Research,2002,2（3）:1-48.
[7] Francis R B, Mmhael I J. Kernel independent component analysis[J]. Journal of Machine Learning Research,2002,2(3):1246-1248.
[8] Scholkopf B, Smola A, Muller K R. Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Computation,1998,10(5):1299-1319.
[9] 史习智.盲信号处理理论与实践[M].上海:上海交通大学出版社,2008.
[10] 吴琛.地震动的HilbertHuang变传统分析方法比较[J].福建工程学院学报,2012(2):5-11.

更新日期/Last Update: 2015-08-25