基于K_L变换和支持向量机的滚动轴承故障诊断.pdfVIP

27 6 煤 矿 机 械 Vol27No6 2006 6 Coal Mine Machinery Jun 200 6 : 2006) 基于K- L 变换和支持向量机的滚动轴承故障诊断 1 2 , ( 1. , 130012; 2. , 130022) : 提出了应用K- L 变换和支持向量机相结合进行滚动轴承故障诊断的方法K- L 变 换可以 高维相关变量压缩为低维独立的主特征向量, 而支持向量机可以完成模式识别和非线性 回归试验结果表明, 利用主矢量分解后的主特征向量与支持向量机相结合可以有效准确地识别 轴承的故障模式, 为轴承故障诊断向智能化发展提供了新途径 : 滚动轴承; 故障诊断; K- L 变换; 支持向量机 : TH13333; TP181 : A Fault Pattern Recognition of Rolling Bearing Based on K- L Transformation and Support Vector Machine 1 2 MAO Zhi- yang , LU Shuang ( 1. Changchun Uni ersity of Technology, Changchun 130012 China; 2. Machinery Industry Institute of Changchun Uni ersity, Changchun 130022, China) A stract:On the basis of statistical learning theory and the feature analysis of ibration signal of rolling bear ing, a new method of fault diagnosis based on K- L transformation and support ector machine is presented. Multidimensional correlated ariable is transformed into low dimensional independent eigen ector by the means of K- L transformation. The pattern recognition and nonlinear regression are achie ed by the method of support ector machine. In the light of the feature of ibration signals, eigen ector is obtained using K- L transforma tion, fault diagnosis of rolling bearing is recognized correspondingly using support ector machine multiple fault classifier. Theory and experiment shows that the recognition of fault diagnosis of rolling bearing based on K- L transformation and support ector machine theory is a ailable to recognize the fault pattern accurately and pro ides