基于支持向量机的信息融合诊断方法  

Novel information fusion fault diagnosis method based on support vector machines

作　　者：尉询楷[1] 李应红[1] 刘建勋[1] 路建明[1] 

机构地区：[1]空军工程大学工程学院飞行器与动力工程系,陕西西安710038

出　　处：《系统工程与电子技术》2005年第9期1665-1668,共4页Systems Engineering and Electronics

摘　　要：提出了一种采用小波变换进行特征提取、支持向量机进行模式分类的多传感器信息融合诊断方法。该方法首先对多传感器的信息进行加权初级融合,接着利用小波变换的时频局部特性和多尺度、多分辨特性对传感器测量信号进行特征提取,最后利用支持向量机进行分类实现信息的特征级融合和分类。将其应用于某转子实验台的故障诊断中,取得了令人满意的结果。A novel fault diagnosis method based on multi-sensor irfformation fusion is presented. First,sensors＇ information is averagely fused before feature extraction. Then, signals＇ characteristic features are extracted by means of wavelet transform. Finally, supprt vector machines are adopted to realize character - level fusion and patter recognition. Samples of some kind of rotor platform＇s fault diagnosis are tested,the test results prove this method is effective and commendable.

关 键 词：支持向量机 小波变换 信息融合 特征提取 故障诊断 

分 类 号：TP206.3[自动化与计算机技术—检测技术与自动化装置]