首页 | 本学科首页   官方微博 | 高级检索  
     

基于PNN的水轮发电机组振动故障诊断
引用本文:熊建秋,李祚泳,汪嘉杨,徐婷婷.基于PNN的水轮发电机组振动故障诊断[J].水力发电,2005,31(7):55-57.
作者姓名:熊建秋  李祚泳  汪嘉杨  徐婷婷
作者单位:1. 四川大学水电学院,四川,成都,610065;成都信息工程学院环境工程系,四川,成都,610041
2. 成都信息工程学院环境工程系,四川,成都,610041
基金项目:973国家重点基础研究发展规划资助项目(2002CB412301);国家自然科学基金资助项目(40271024)
摘    要:概率神经网络(PNN)是一种训练速度快、结构简洁明了、应用广泛的人工神经网络。它采用贝叶斯分类决策理论建立系统的数学模型,以高斯函数作为激励函数,具有非线性处理和抗干扰能力强等特点。提出基于PNN的水轮发电机组振动故障诊断方法,并在水轮发电机组振动频谱波形特征的基础上,对几种典型故障模式进行了实例研究。理论分析和实例结果验证了基于PNN的水轮发电机组振动故障诊断方法是正确和有效的。

关 键 词:概率神经网络  水轮发电机组  振动  故障诊断  预测
文章编号:0559-9342(2005)07-0055-03
收稿时间:04 29 2005 12:00AM
修稿时间:2005-04-29

Research on vibration fault diagnosis of hydroelectric generating unit based on PNN
Xiong Jian-qiu,LI Zuo-yong,WANG Jia-yang,XU Ting-ting.Research on vibration fault diagnosis of hydroelectric generating unit based on PNN[J].Water Power,2005,31(7):55-57.
Authors:Xiong Jian-qiu  LI Zuo-yong  WANG Jia-yang  XU Ting-ting
Affiliation:Xiong Jian-qiu1,2,Li Zuo-yong2,Wang Jia-yang2,Xu Ting-ting2
Abstract:Probabilistic neural network (PNN) model is a kind of artificial neural network, which is simple in structure, easy for training and widely used. The method uses Bayes classifying and decision-making theory to constitute the mathematic model of system; with Gauss function as activating one, it possesses the characteristics of strong nonlinear processing and anti-interfering ability. The paper expatiated the theory and algorithm of PNN, and then proposed the application of PNN to vibration fault diagnosis of hydroelectric generating unit. It is shown that the PNN method is very effectively by the theoretical analysis and practical application.
Keywords:probabilistic neural network  hydroelectric generating unit  vibration  fault diagnosis  forecast
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号