首页 | 本学科首页   官方微博 | 高级检索  
     

基于RBF网络的高炉热流分析传感器故障诊断
引用本文:陈至坤,陈少敏,李福进,王福斌,郭建飞,董传阳.基于RBF网络的高炉热流分析传感器故障诊断[J].传感器与微系统,2007,26(6):58-59.
作者姓名:陈至坤  陈少敏  李福进  王福斌  郭建飞  董传阳
作者单位:1. 河北理工大学,计算机与自动控制学院,河北,唐山,063009
2. 唐山科技职业技术学院,计算机系,河北,唐山,063009
3. 河北理工学院,唐山深信测控中心,河北,唐山,063009
摘    要:在炼铁高炉热流强度分析系统中要用到温度、流量等传感器,为确保热流分析系统中传感器数据的可靠性及系统的连续、稳定运行,诊断系统用径向基函数(RBF)神经网络对传感器进行故障判断。系统由上位机、温度及流量采集装置、传感器等组成,采用RBF神经网络为每一个传感器建立预测模型,网络的输入为传感器采集信号最近的n个值,输出为该传感器在n+1时刻的预测输出值。网络通过在线学习实现对传感器的在线故障监测,经仿真分析表明:用RBF神经网络构建预测模型可满足实时性的诊断要求,提高了诊断系统的诊断精度。

关 键 词:炼铁高炉  RBF神经网络  传感器  故障诊断
文章编号:1000-9787(2007)06-0058-02
修稿时间:2006-11-29

Fault diagnosis for heat quality analysis sensor of puddling furnace based on RBF neural network
CHEN Zhi-kun,CHEN Shao-min,LI Fu-jin,WANG Fu-bin,GUO Jian-fei,DONG Chuan-yang.Fault diagnosis for heat quality analysis sensor of puddling furnace based on RBF neural network[J].Transducer and Microsystem Technology,2007,26(6):58-59.
Authors:CHEN Zhi-kun  CHEN Shao-min  LI Fu-jin  WANG Fu-bin  GUO Jian-fei  DONG Chuan-yang
Affiliation:1. Computer and Automatic Control College, Hebei Polytechnic University, Tangshan 063009, China; 2. Department of Computer, Tangshan Science and Technology Profession College, Tangshan 063009, China; 3. Tangslmn Shenxin Center of Measure and Control, Hebei Institute of Technology, Tangshan 063009, China
Abstract:Temperature or flux sensors may be used in the the heat quality intensity analysis system for puddling furnace,RBF neural network is used to judge sensor fault for insureing the credibility of sensor data and the stability running of the heat quality intensity analysis system.The system is composed with computer,temperature and flux data acquire installation and sensor.Forecast model for every sensor using RBF neural network is found.The number of lately input signal for the net is n,the output of the net is the forecast value at n+1 occasion.The fault diagnosis of sensor is carried out by the on-line learning method.Emulation analysis shows forecast model for every sensor using RBF neural network can fulfil fault diagnosis and improve the diagnosis precision.
Keywords:puddling furnace  RBF neural network  sensor  fault diagnosis
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