基于核独立分量分析的非线性混合机械故障盲分离方法研究

Studies on Blind Separation Method of Nonlinear Mixture Machine Faults Based on Kernel Independent Component Analysis

提出了一种基于核独立分量分析(KICA)的非线性混合机械故障源盲分离方法,即利用核函数的优点,将信号从低维的非线性原始空间变换到高维线性特征空间,实现以线性ICA方法进行分离。仿真结果表明:与传统的ICA方法相比,本方法在处理非线性混合源盲分离上具有明显的优势,并在轴承故障信号盲分离实验中验证了它的有效性。

A nonlinear mixture blind separation method of the mechanical fault sources based on kernel independent component analy-sis is proposed. In the proposed method, the signal is transformed from the low - dimensional nonlinear original space into a high - dimensional linear feature space by the kernel function, so that nonlinear mixture mechanical fault sources can be separated by the linear ICA method. The simulation result shows that the proposed method is superior to the traditional ICA method in processing nonlinear mixed blind separation problem. Finally the proposed method is applied to the blind separation of the bearing fault. The experiment re- sult further verifies the validity of the proposed method.