摘要
盲源分离可以对相互统计独立的信号源经线性组合而产生的一组混合信号进行分离,从中得到各个独立的源信息。针对混合信号相位差对独立分量分析算法性能的影响问题,提出一种故障源信号的频域盲分离方法。该方法利用频谱的线性叠加性和无相位性,先将工程实测信号转换到频域,再对得到的信号频谱进行盲源分离。仿真实例和涡流传感器失效检测的成功应用表明,根据信号结构选择预处理方法十分重要,正确的预处理可以大大提高独立分量分析提取故障源特征的有效性。
Blind source separation (BSS) can be used to separate mixed signals which is combined by the original data linearly, and obtain the source component which is statistically independent. The capacity of independent component analysis (ICA) is usually effected by the phase difference of the mixed signals. For this reason, an improved method called frequency domain BSS is proposed. By the properties of linear addition and phase loss of spectrum analysis, the engineering signals are transformed to frequency domain firstly, and then the spectra are processed by BSS. Simulation results and the application of eddy-current sensor fault detection demonstrate that for ICA the correct preprocessing according to signal structure contribute to feature extraction of mechanical signals effectively.
出处
《机械强度》
CAS
CSCD
北大核心
2009年第1期14-18,共5页
Journal of Mechanical Strength
基金
国家”863”资助项目(2006AA04Z146)
国家自然科学基金资助项目(50475117)~~
关键词
盲源分离
独立分量分析
特征提取
故障诊断
Blind source separation
Independent component analysis
Feature extraction
Fault diagnosis