论文部分内容阅读
研究了核函数主元分析在机械故障模式分类中的应用 .通过计算原始空间的内积核函数实现原始数据空间到高维数据空间的非线性映射 ,再对高维数据作主元分析 ,求取更易于分类的核函数主元 .实验表明 ,核函数主元分析更适于提取故障信号的非线性特征 ,能有效区分不同的故障模式 ,可以应用于机械设备的状态识别 .
The principal component analysis of kernel function is applied in the classification of mechanical failure modes. The nonlinear mapping between the original data space and the high-dimensional data space is calculated by calculating the inner product kernel function of the original space, and then the principal component analysis Experiments show that principal component analysis of kernel function is more suitable for extracting nonlinear characteristics of fault signals and can effectively distinguish different fault modes and can be applied to state recognition of mechanical equipment.