基于支持向量机的转子振动故障融合诊断技术  

Rotor vibration fault fusion diagnosis based on support vector machine

作　　者：艾延廷[1] 费成巍[1] 

机构地区：[1]沈阳航空航天大学辽宁省数字化工艺仿真与试验技术重点实验室,沈阳110136

出　　处：《沈阳工业大学学报》2010年第5期526-530,共5页Journal of Shenyang University of Technology

基　　金：辽宁省自然科学基金资助项目(2005400612)

摘　　要：针对某些大型复杂旋转机械振动信号特征提取和故障样本获取难的问题,提出了一种基于小波包特征谱熵支持向量机(SVM)的转子振动故障融合诊断方法.通过转子实验台模拟了转子振动的4种典型故障,并采集其振动故障数据.用小波包对振动故障信号进行分解,提取故障信息含量大的频带并计算出其小波特征谱熵作为故障特征,建立故障诊断模型.通过对故障类别的区分和故障严重程度的判断,验证了该方法在解决转子振动故障信号的特征提取及小样本情况下的故障诊断问题等方面是有效的.For the difficulties in extracting vibration signal features of some large-scale intricate rotating machinery and obtaining efficient fault samples,a rotor vibration fault fusion diagnosis method based on wavelet packet characteristic spectral entropy support vector machine ( SVM ) was proposed.Four typical rotor vibration faults were simulated through rotor experiment table,and some vibration fault data were collected.The vibration fault signals were disassembled.The frequency-band containing a large amoun...

关 键 词：小波包 空间特征谱熵 支持向量机(SVM) 转子振动 振动实验 特征提取 故障诊断 信息融合 

分 类 号：TH165.3[机械工程—机械制造及自动化]