基于独立分量分析的水轮机振动信号信噪分离与特征提取

Signal Noise Separation and Feature Extraction of Hydraulic Turbine Vibration Signal Based on Independent Component Analysis

针对水轮机导轴承工作环境复杂,测得信号掺杂噪声给信号处理带来困难的问题,提出一种基于独立分量分析的水轮机振动信号的信噪分离方法,并通过信号仿真验证了该方法分离两源混合信号(原始信号和噪声)的准确性。在此基础上引入经验模态分解算法对采集振动信号的噪声分离,经过仿真信号与实测信号分离的对比,验证了所提方法在水力机械故障诊断方面的工程应用价值。

The turbine guide bearing's signal always contains noise because of its complex working environment,which brings about problem of the signal processing. To solve this problem,this paper proposed a signal noise separation method of turbine's vibration signal based on independent component analysis. The accuracy of the method is verified by the simulation of the signal in the separation of the two-source mixed signal( the original signal and the noise). On this basis,by introducing the empirical mode decomposition algorithm and constructing the characteristic signal,the noise can be separated completely from the vibration signal. The comparision of the simulation signal and measured signal proves that the proposed method has good engineering application value in hydraulic machinery fault diagnosis.