【摘要】 基于核函数主元分析的独特优势,提出了滚动轴承故障诊断方法,通过核函数映射将非线性问题转换成高维的线性特征空间,然后对高维空间中的映射数据作主元分析,提取其非线性特征,对故障模式进行识别。并与主元分析方法进行了对比。试验结果表明,核函数主元分析法更适合提取故障的非线性特征,并能很好地识别滚动轴承故障模式。更多还原

【Abstract】 Based on the kernel principle component analysis(KPCA),a fault diagnosis method of roller bearing is proposed,where a nonlinear problem is transformed into a higher dimensional linear feature space by kernel function map.Then the PCA method is used to this dimensional space to extract the nonlinear features.The fault patterns can be recognized by these nonlinear features.At the same time,the recognition effect of the PCA and KPCA is compared.The experiment result shows that the KPCA method is able to extract the nonlinear feature of machine fault,and recognize the fault patterns effectively.更多还原