基于气体传感器阵列的矿井可燃混合气体分析

叶小婷; 张青春; 童敏明

基于气体传感器阵列的矿井可燃混合气体分析

计量
- 文章访问数: 1385
- HTML全文浏览量: 0
- PDF下载量: 0
出版历程
- 发布日期: 2012-02-09

Analysis of Mixed Inflammable Gases in Mine Based on Gas Sensor Arrays

摘要

摘要: 由于气体传感器的选择性差,交叉敏感严重,单一BP神经网络识别方法存在识别能力低,分析误差较大,在非期望节点有噪声输出等难题,影响气体分析的精度和效果。对基于常规BP神经网络的定量分析方法进行了改进,提出一种双层复合神经网络的气体分析模型,并以矿井中常见的H₂S,CO和CH₄ 3种可燃混合气体为实验对象,进行混合气体的定量分析。实验结果表明,基于双层复合神经网络的可燃混合气体定量分析最大相对误差为4.4%,大大提高了定量分析精度。
- 气体传感器阵列 /
- 神经网络 /
- 可燃混合气体 /
- 模式识别
Abstract: Poor selectivity and cross sensitivity are problems of gas sensors,general BP(back propagation) neural network has low recognition ability and its error is too high to accept.A hybrid two layers neural networks is developed to improve the quantitative analysis of general BP neural network.Using two layers neural networks,three mixed inflammable gases in mine are adopted for the quantitative analysis.The result shows that recognition ability of the neural network is increased and the maximum relative error of quantitative analysis is 4.4%,the precision of quantitative analysis is increased.
- gas sensor arrays /
- neural network /
- mixed inflammable gase /
- pattern recognition

HTML全文

参考文献(15)

[1]	J.W.Gardner,P.N.Bartlett.A brief history of electronicnose[J].Sensors and Actuators B,1994(18-19):211-220.
[2]	曲建岭,王磊,高峰.运用人工神经网络进行混合气体定量分析的研究[J].西北工业大学学报,2001,21(4):401-403.
[3]	M.A.Martin,J.P.Santos,J.A.Agapito.Application ofartificial neural networks to calculate the partial gas con-centrations in a mixture[J].Sensors and Actuators B,2001(77):468-471.
[4]	J.C.Chen,Y.H.Ju,C.J.Liu.Concentration determina-tion of gas by organic thin film sensor and back propaga-tion network[J].Sensors and Actuators B,1999(60):168-173.
[5]	M.C.Carotta,G.Martinelli,L.Crema,et al.Nanostruc-tured thick-film gas sensors for atmospheric pollutantmonitoring:quantitative analysis on field test[J].Sensorsand Actuators B,2001(76):336-342.
[6]	B.S.Joo,N.J.Choi,Y.S.Lee,et al.Pattern recognitionof gas sensor array using characteristics of impedance[J].Sensors and Actuators B,2001(77):209-214.
[7]	童敏明,叶小婷,王都霞.基于信息融合的矿井一氧化碳检测方法的研究[J].计量学报,2007,28(4):388-390.
[8]	叶小婷,汤劼.基于BP神经网络的矿井一氧化碳检测方法研究[J].仪表技术,2007(10):40-42.
[9]	常柄国.基于径向基函数神经网络识别变压器油中微量特征气体[J].西安交通大学学报,1999,33(12):13-17.
[10]	庞全,杨翠容,张玉清.人工神经网络气体分析方法的研究[J].仪器仪表学报,1999,20(2):121-124.
[11]	T.Eklov,I.Lundstrom.Gas mixture analysis using a dis-tributed chemical sensor system[J].Sensors and Actua-tors B,1999(57):274-282.
[12]	G.Huyberechts.Simultaneous quantification of carbonmonoxide and methane in humid air using a sensor arrayand an artificial neural network[J].Sensors and Actua-tors B,1997(45):123-130.
[13]	A.Szczurek.Application of sensor array and neural net-works for quantification of organic solvent vapours in air[J].Sensors and Actuators B,1999(58):427-432.
[14]	M.A.Martin.Study of the interferences of NO2 and COin solid state commercial sensors[J].Sensors and Actua-tors B,1999(58):469-473.
[15]	徐丽娜.神经网络控制[M].北京:电子工业出版社,2002.

施引文献

资源附件(0)

计量

文章访问数: 1385
HTML全文浏览量: 0
PDF下载量: 0
被引次数: 0

基于气体传感器阵列的矿井可燃混合气体分析

计量

出版历程

Analysis of Mixed Inflammable Gases in Mine Based on Gas Sensor Arrays

计量

出版历程

目录