基于MATLAB的汽轮机振动故障诊断仿真研究  

Research on Simulation of Turbine Vibration Fault Diagnosis Based on MATLAB

作　　者：刘海峰 

机构地区：[1]广东粤电靖海发电有限公司,广东揭阳515223

出　　处：《应用能源技术》2015年第8期10-13,共4页Applied Energy Technology

摘　　要：SOM神经网络是一种极具理论与使用价值的分类方法。基于SOM神经网络算法,在小样本情况下对汽轮机机组故障诊断进行了仿真研究,建立了多故障分类器,并将其应用于典型的汽轮机振动故障诊断。结果表明,应用该算法可以正确且快速有效地诊断多类汽轮机故障,可以为现场生产中汽轮机振动故障类型判断提供参考。SOM neural network is a classification method of theoretical use value highly. Based on SOM neural network algorithm,in the case of small sample turbine fault diagnosis simulation studies,the multi- fault classifier is established, and it is applied to a typical turbine vibration fault diagnosis. The results show that the algorithm can be applied quickly and efficiently diagnose and correct many types of turbine failure,which can determine the type of turbine vibration fault reference in the production site.

关 键 词：汽轮机组 振动故障 故障诊断 SOM神经网络 多故障分类器 

分 类 号：TK263.7[动力工程及工程热物理—动力机械及工程]