核主元分析中核函数参数选优方法研究

Kernel Function Optimization in Kernel Principle Component Analysis and Its Application to Feature Extraction of Gear Faults

提出一种基于矩阵相似度的核函数参数选优方法,首先给出一种具有较好分类能力的核函数矩阵。然后,利用矩阵间的相似度量关系,在一定范围内寻找能近似此矩阵的核函数参数值。将该方法应用于直升机齿轮箱齿轮故障特征提取中,结果显示经过核函数参数选优的KPCA取得了较好的识别效果。

A kernel function parameter optimization method based on the matrix similarity is proposed.The method first gives a fine matrix of kernel function out,then searchs an approximate kernel function parameter value in a finite range based on the similarity between the given matrix and the kernel function matrix.The method is applied to the feature extraction of the helieoptor gearbox fault.The result shows KPCA using optimization kernel parameter value has a better fault classification performance.