矢功率谱与概率神经网络结合在旋转机械故障诊断中的应用研究  

Vector power spectrum and probabilistic neural networks applied to rotating equipment fault diagnosis

作　　者：杨春燕[1] 朱茹敏[1] 吴超[1] 

机构地区：[1]郑州轻工业学院机电工程学院,郑州450002

出　　处：《现代制造工程》2010年第2期124-127,共4页Modern Manufacturing Engineering

基　　金：河南省教育厅自然科学研究资助计划项目(2009A460013);郑州轻工业学院博士基金资助项目

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,而概率神经网络学习速度快、收敛性好,基于此,结合矢功率谱和概率神经网络,提出一种故障诊断的新方法,该方法是以矢功率谱作为特征输入到概率神经网络分类器进行故障识别,并应用到旋转机械故障诊断中。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 Probabilistic Neural Networks（PNN） has high studying rate and good convergence and so on. Here, combining vector power spectrum and PNN, a new fault diagnosis approach is proposed, this approach is that the vector power spectrum is used as eigenvectors, PNN as a elassifier. The proposed approach has been successfully applied to the fault diagnosis of rotating machinery. The experiment result shows that the proposed approach is very effective.

关 键 词：矢功率谱 概率神经网络 故障诊断 信息融合 

分 类 号：TP391.7[自动化与计算机技术—计算机应用技术]