基于核的多故障分类器及其应用  

Multi-fault classifier with kernels and its applications

作　　者：杜京义[1] 侯媛彬[1] 

机构地区：[1]西安科技大学电气与控制工程学院,陕西西安710054

出　　处：《煤炭学报》2007年第1期103-106,共4页Journal of China Coal Society

基　　金：陕西省科学基金资助项目(2004JC12)

摘　　要：提出了一种基于核的多类别模式识别算法(简称核子空间法,KSPM),依据此算法建立了多故障分类器.该方法的主要思想是:将原输入空间中的数据经一个非线性映射,映射到一个高维的特征空间(或核空间),突出各类样本之间的特征差异,利用线性子空间模式识别思路进行分类.经核矩阵特征分解,可以形成各类别对应的特征子空间,然后分别计算待分类模式与各类特征子空间的距离实现模式分类.多故障分类器应用于液压泵故障诊断结果表明,该故障分类器可实现多故障的识别和诊断,并且具有算法简单和故障分类能力强的优点.A novel multi-class classifier with kernels, namely Kernel Subspace Methods （ KSPM）, was presented, and a multi-fault classifier based on the algorithm was constructed. The idea of the method is firstly map the data from their original space to a high dimensional space （or kernel space） where the data are expected to be more separable then perform subspace pattern recognition in the high dimensional space. With the eigen-decomposition of kernel matrix, it can construct the feature subspace that reflects each class feature. Then the distance between unknown-classification feature vector and each feature subspace is calculated to determine the class to which the vector belongs. The muhi-fauh classifier was applied to fault diagnosis of hydraulic pump, and the results show that it has such advantages as simple algorithm and excellent capability of fault classification.

关 键 词：多故障分类器 故障诊断 核矩阵 子空间模式识别 液压泵 

分 类 号：TP306.3[自动化与计算机技术—计算机系统结构]