Method of gas sensor fault detection based on SVR

FU Hua; YANG Xin; GAO Ting

doi:10.13873/j.1000-97872009.02.037

Chinese

您当前的位置：

首页 >

文章列表页 >

Method of gas sensor fault detection based on SVR

更新时间：2025-09-11

- Method of gas sensor fault detection based on SVR
- Vol. 28, Issue 2, Pages: 10-12(2009)
- 作者机构：
  
  辽宁工程技术大学电气与控制工程学院
- 作者简介：
- 基金信息：
- DOI：10.13873/j.1000-97872009.02.037
  CLC： TP212
- Published：2009
- 稿件说明：
移动端阅览
[1]付华,杨欣,高婷.基于SVR的瓦斯传感器故障诊断方法[J].传感器与微系统,2009,28(02):10-12.

FU Hua, YANG Xin, GAO Ting. Method of gas sensor fault detection based on SVR[J]. 2009, 28(2): 10-12.
[1]付华,杨欣,高婷.基于SVR的瓦斯传感器故障诊断方法[J].传感器与微系统,2009,28(02):10-12. DOI： 10.13873/j.1000-97872009.02.037.

FU Hua, YANG Xin, GAO Ting. Method of gas sensor fault detection based on SVR[J]. 2009, 28(2): 10-12. DOI： 10.13873/j.1000-97872009.02.037.

摘要

介绍了回归型支持向量机（SVR）的基本原理

建立了基于SVR的传感器时间预测模型

对时间预测器实行离线训练、在线应用的方法

用训练好的SVR模型模拟煤矿井下瓦斯传感器系统的动态特性

阐述了瓦斯传感器故障诊断和信号恢复的实现过程。仿真结果表明:SVR时间预测器能准确预测和跟踪瓦斯传感器的输出

及时诊断出传感器故障信息

并对传感器信号进行恢复

实验验证了该方法的正确性和有效性。

Abstract

The theory of support vector regression（SVR）is introduced

a sensor predictor based on SVR is proposed.The SVR is trained out of line and used on line.The trained SVR model is use to simulate the dynamic characteristic of coal mine gas sensor system.The implementation procedures of gas sensor fault detection and signal recovery are expounded.The simulation results show that the SVR predictor can predict and follow the output of gas sensor accurately

fault message of sensor is diagnosed in time

and sensor signal is recoved.The method is verified by the experiment to be correct and valid.

关键词

Keywords

references

一种基于SVR的传感器系统故障诊断方法 [J]. 金卫民,神显豪,巩传雷. 微计算机信息 . 2007(07)

基于SVM预测器的传感器故障诊断与信号恢复研究 [J]. 刘东,葛运建. 传感技术学报 . 2005(02)

瓦斯监测系统故障智能诊断技术研究 [D]. 王其军. 山东科技大学 2007

煤矿瓦斯灾害特征提取与信息融合技术研究 [D]. 付华. 辽宁工程技术大学 2006

基于支持向量机的故障智能诊断方法研究 [D]. 翟永杰. 华北电力大学（河北） 2004

Views

186

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fault diagnosis of gas sensor based on PCA and artificial neural network ensemble

Study on gas detection based on laser ultrasound surface wave detection

Gas sensor fault diagnosis based on wavelet packet and neural network

Fault detection and diagnosis for sensors based on DPCA

Related Author

YANG Zhen

DENG Fang-ming

HAO Yong

XU Chang-ying

WANG Hong

WU Xiang

FU Hua

QIAO De-hao

Related Institution

Modern Educational Technology Center,East China Jiaotong University

School of Electrical and Electronic Engineering,East China Jiao Tong University

Engineering Training Center,Nanchang Hangkong University

School of Electrical and Control Engineering,Liaoning Engineering Technology University

School of Automation,Harbin Engineering University

⁰