基于独立分量分析与相关系数的机械故障特征提取

提出一种基于独立分量分析与相关系数的机械故障特征提取方法。首先对不同工况的机械振动信号分别进行独立分量分析，获得各种工况信号的独立分量，这些独立分量中蕴含了该工况的一些内在特征；接着利用样本与不同工况信号提取的独立分量的相关系数绝对值的和作为该样本的特征，与直接利用相关系数作为特征相比鲁棒性与区分程度都得到提高；最后使用支持向量机作为分类器进行识别。分别进行了齿轮故障特征提取与轴承故障特征提取实验，实验结果表明，此方法可以很好地提取机械故障特征信息。本文方法的优点在于直接从振动信号的原始数据中进行特征提取，获取机械故障蕴含的一些特征，应用范围广，具有较高地工程应用价值。

Machinery fault feature extraction based on independent component analysis and correlation coefficient

This paper proposed a machinery fault feature extraction method based on Independent Component Analysis (ICA) and correlation coefficient. First, the ICA is used for vibration signal of each fault category. The extracted independent components include the information of the fault. Then the absolute sum of the correlation coefficients of the test sample and the extracted indepent components of each category are used as the feature vetor. Finally the support vector machine is used as the classification method for fault diagnosis. The proposed fault feature extraction method is applied to two tasks: gear feault diagnosis and roller bearing fault diagnosis tasks. The ICA is applied to extracting independent features in the proposed method. Through experiments, we demonstrate that the ICA of each fault category and correlation coefficient can extract useful features for machinery fault diagnosis.