矢功率谱与RBF网络结合在旋转机械故障诊断中的应用  

Vector Power Spectrum and RBF Network Applied to Fault Diagnosis of Rotating Machinery

作　　者：潘玉娜[1] 韩捷[1] 李志农[1] 

机构地区：[1]郑州大学工学院振动工程研究所,郑州450002

出　　处：《机床与液压》2007年第1期223-225,共3页Machine Tool & Hydraulics

基　　金：国家自然科学基金(No.50675209);河南省杰出人才创新基金(0621000500);河南省重大科技攻关资助项目(No.0122022000)

摘　　要：与传统功率谱相比,矢功率谱融合了多通道的能量信息,反映的信息更全面。径向基函数网络具有良好的推广能力和分类能力。基于此,本文结合矢功率谱和径向基函数网络,提出了一种新的故障识别方法,该方法以矢功率谱为特征向量,径向基函数网络为分类器。并以转子裂纹、转子不对中、油膜涡动为例进行实验研究,实验结果表明,该方法是有效的。Compared with the traditional power spectrum, the vector power spectrum can fuse the power information from different channels, and reflect more comprehensive information. The radial basis function network （RBFN） has good extensible and classified ability. Combining vector power spectrum and RBFN, a new fault diagnosis approach was proposed, this approach is that vector power spectum is used as eigenvectors, RBFN as a classifier. The proposed approach was successfully applied to the recognition of three typical faults, i. e. rotor crack, rotor misalignment and oil whirl. The experiment result shows that this proposed approach is effective.

关 键 词：矢功率谱 RBF网络 故障诊断 旋转机械 

分 类 号：TH165.3[机械工程—机械制造及自动化] TN911[电子电信—通信与信息系统]