基于改进模糊SVM的转子振动故障诊断技术  

Technique for diagnosing fault of rotor vibration based on improved fuzzy SVM

作　　者：艾延廷[1] 费成巍[1] 王志[1] 

机构地区：[1]沈阳航空航天大学动力与能源工程学院,沈阳110136

出　　处：《航空动力学报》2011年第5期1118-1123,共6页Journal of Aerospace Power

基　　金：航空科学基金(2008ZB54006)

摘　　要：首先对常用的隶属度确定方法进行改进,提出了基于改进模糊支持向量机(FSVM)的融合故障诊断方法,并建立了改进FSVM故障诊断数学模型;然后,利用转子振动模拟实验台对四种典型的转子诊断故障进行模拟,并提取其故障信号特征;最后,通过实例计算分析,验证了该方法在转子振动故障诊断方面是可行的和有效的.A fuzzy support vector machine（FSVM） fault diagnosis method was proposed based on improvement of the ordinary diagnosis method used to determine memberships,and an improved diagnosis mathematical model was established.Then,four kinds of typical rotor vibration faults were simulated on a rotor vibration experimental rig,and effective samples of fault were collected.Finally,the validity and feasibility of this method used for rotor vibration fault diagnosis were validated by calculating and analyzing the obtained examples.

关 键 词：转子振动 故障诊断 隶属度 模糊理论 支持向量机(SVM) 模糊支持向量机(FSVM) 最优分类面 

分 类 号：V231.92[航空宇航科学与技术—航空宇航推进理论与工程] TH165.3[机械工程—机械制造及自动化]