基于K-L变换的支持向量机在汽轮机故障诊断中的应用  

Application of Support Vector Machine Based on K-L Transform in Turbine Fault Diagnosis

作　　者：张超[1] 韩璞[2] 唐贵基[1] 

机构地区：[1]华北电力大学机械工程学院,保定071003 [2]华北电力大学自动化系,保定071003

出　　处：《汽轮机技术》2007年第2期148-150,共3页Turbine Technology

基　　金：华北电力大学博士教师学位科研基金(92104392)资助

摘　　要：支持向量机应用于故障诊断是近年来研究的热点,在支持向量机算法的基础上,以汽轮机故障为例,引入了K-L变换对故障特征进行提取。结果表明,经K-L变换后的支持向量机算法能够保证故障信息的完整性,有效识别临界故障状态,提高了故障的分类精度,扩展了支持向量机的应用范畴。The application of support vector machine in fault diagnosis is the research hotspots in recent years. This paper first researches the algorithm of support vector machine, and introduces K - L transform method to extract the characteristic of the diagnosis of turbine. The result indicates that the algorithm of support vector machine based on K - L transform can ensure the integrality of diagnosis characteristic, and effectively recognize the critical diagnosis, which improves the precision of classification and extends thee application bound of support vector machine.

关 键 词：支持向量机 K—L变换 特征提取 故障诊断 

分 类 号：TK264.11[动力工程及工程热物理—动力机械及工程]