高级搜索

基于集成神经网络的汽车尾气检测系统设计

,  , 

downloadPDF

上一篇

下一篇

刘萍, 简家文, 陈志芸. 基于集成神经网络的汽车尾气检测系统设计[J]. 环境工程学报, 2016, 10(4): 1883-1887. doi: 10.12030/j.cjee.20160448
引用本文: 刘萍, 简家文, 陈志芸. 基于集成神经网络的汽车尾气检测系统设计[J]. 环境工程学报, 2016, 10(4): 1883-1887. doi: 10.12030/j.cjee.20160448
shu
Liu Ping, Jian Jiawen, Chen Zhiyun. Design of detection system for automobile exhaust based on integrated neural network[J]. Chinese Journal of Environmental Engineering, 2016, 10(4): 1883-1887. doi: 10.12030/j.cjee.20160448
Citation: Liu Ping, Jian Jiawen, Chen Zhiyun. Design of detection system for automobile exhaust based on integrated neural network[J]. Chinese Journal of Environmental Engineering, 2016, 10(4): 1883-1887. doi: 10.12030/j.cjee.20160448
shu

基于集成神经网络的汽车尾气检测系统设计

  • 1.

    宁波大学信息科学与工程学院, 宁波 315211

  • 基金项目:

    国家自然科学基金资助项目(61471210)

    浙江省宁波市科技局自然科学基金资助项目(2013A610002)

  • 中图分类号: X701

Design of detection system for automobile exhaust based on integrated neural network

  • 1.

    School of Information Science and Engineering, Ningbo University, Ningbo 315211, China

  • Fund Project:

  • 摘要: 为了准确、有效地检测汽车尾气中各气体的质量分数,对传感器阵列和BP神经网络技术进行了研究,设计了一套汽车尾气检测系统。首先,根据汽车尾气成分选取4个相应传感器和一个温湿度传感器组成传感器阵列,搭建汽车尾气检测装置;其次,为了克服单一BP神经网络预测精度低,容易陷入局部极值的缺点,建立基于Adaboost算法和BP神经网络的集成神经网络模型;最后,利用集成神经网络模型对传感器阵列的响应信号进行回归分析。结果表明,集成神经网络模型预测的平均相对误差小于3%,能够有效处理汽车尾气的检测数据。
    Abstract: To test the mass fraction of gases in automobile exhaust accurately and effectively, an automobile exhaust detection system is designed by combining sensor array and BP neural network technologies in this study.An automobile exhaust detection device is built by madding a sensor array through the selection of four corresponding sensors and a temperature and humidity sensor according to the car's exhaust components.The single BP neural network can easily fall into the local extremum and has low prediction accuracy;thus, an integrated neural network model is established on the basis of the Adaboost algorithm and BP neural networks to overcome these disadvantages.This model is used for the regression analysis of experimental data.The results show that the average relative error predicted by the integrated neural network model is less than 3%.
  • 加载中
  • [1] 苏会波,林海龙,李凡,等.乙醇汽油对减少机动车污染排放的机理研究与分析.环境工程学报,2015,9(2):823-829 Su Huibo,Lin Hailong,Li Fan,et al.Mechanism study and analysis on emission reduction of pollutants with ethanol gasoline.Chinese Journal of Environmental Engineering,2015,9(2):823-829(in chinese)
    [2] 荆旭,胡方明,任爱锋.汽车尾气分析仪设计.电子科技,2014,27(2):106-108 Jing Xu,Hu Fangming,Ren Aifeng.Design of an automotive exhaust gas analyzer.Electronic Science and Technology,2014,27(2):106-108(in Chinese)
    [3] 张坤.交通排放在线检测的红外传感器研究.合肥:中国科学技术大学硕士学位论文,2015 Zhang Kun.A non-dispersive infrared sensor for the measurement of vehicle exhaust.Hefei:Masten Dissertation of University of Science and Technology of China,2015(in Chinese)
    [4] 方杨.基于国 Ⅲ 标准的汽车尾气检测分析系统.杭州:浙江大学硕士学位论文,2008 Fang Yang.Automotive exhaust detection and analysis system based on national Ⅲ standard.Hangzhou:Master Dissertation of Zhejiang University,2008(in Chinese)
    [5] Pati S.,Maity A.,Banerji P.,et al.Qualitative and quantitative differentiation of gases using ZnO thin film gas sensors and pattern recognition analysis.Analyst,2014,139(7):1796-1800
    [6] Zhang L.,Tian F.,Liu S.,et al.Chaos based neural network optimization for concentration estimation of indoor air contaminants by an electronic nose.Sensors and Actuators A:Physical,2013,189:161-167
    [7] 张覃轶.电子鼻:传感器阵列,系统及应用研究.武汉:华中科技大学博士学位论文,2005 Zhang Qinyi.Electronic nose:Studies on gas sensor arrays,systems and its applications.Wuhan:Doctoral Dissertation of Huazhong University of Science and Technology,2005(in chinese)
    [8] 林海军,滕召胜,杨进宝,等.基于 RBF 神经网络集成-模糊加权输出的数字温度传感器误差补偿.仪器仪表学报,2011,32(7):1675-1680 Lin Haijun,Teng Zhaosheng,Yang Jinbao,et al.Error compensation for digital temperature sensor based on RBF neural network ensembles-fuzzy weighing output.Chinese Journal of Scientific Instrument,2011,32(7):1675-1680(in Chinese)
    [9] Gao L.,Hu S.,Li Z.A face recognition method based on a combination of integrated neural network and KICA algorithm//Systems and Informatics (ICSAI),2012 International Conference on.IEEE,2012:2108-2112
    [10] 耿志广,王希武,王寅龙,等.基于人工神经网络的电子鼻对混合气体检测研究.现代计算机月刊,2010(5):45-48 Geng Zhiguang,Wang Xiwu,Wang Yinlong,et al.Research on detection of mixed gas by electronic nose based on artificial neural network.Modern Computer,2010(5):45-48(in Chinese)
    [11] 姚毓升,解永平,文涛.三电极电化学传感器的恒电位仪设计.仪表技术与传感器,2009(9):23-25 Yao Yusheng,Xie Yongping,Wen Tao.Design of potentiostat for three-electrode electrochemical sensors.Instrument Technioue and Sensor,2009(9):23-25(in Chinese)
    [12] 张伟,周凤星.基于 STM32 和 FPGA 的石油管道腐蚀测试仪.仪表技术与传感器,2015(2):39-42 Zhang Wei,Zhou Fengxing.Design of pipeline corrosion monitor instrument based on STM32 and FPGA.Instrument Technique and Sensor,2015(2):39-42(in Chinese)
    [13] 李翔,朱全银.Adaboost 算法改进BP神经网络预测研究.计算机工程与科学,2013,35(8):96-102 Li Xiang,Zhu Quanyin.Adaboost prediction of improved BP neural network by Adaboost algorithm.Computer Engineering and Science,2013,35(8):96-102(in Chinese)
    [14] 张文阳,张良均,李娜,等.多元回归和BP人工神经网络在预测混合厌氧消化产气量过程中的应用比较.环境工程学报,2013,7(2):747-752 Zhang Wenyang,Zhang Liangjun,Li Na,et al.Comparing multiple regression and BP artificial nerve net model used on prediction of anaerobic co-digestion gas-producing process.Chinese Journal of Environmental Engineering,2013,7(2):747-752(in chinese)
    [15] Yu F.,Xu X.A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network.Applied Energy,2014,134:102-113
    [16] Manohar V.,Povey D.,Khudanpur S.Semi-supervised maximum mutual information training of deep neural network acoustic models//Proceedings of Interspeech,2015
    [17] Zhang M.H.,Xu Q.S.,Daeyaert F.,et al.Application of boosting to classification problems in chemometrics.Analytica Chimica Acta,2005,544(1):167-176
    [18] Heo J.,Yang J.Y.AdaBoost based bankruptcy forecasting of Korean construction companies.Applied Soft Computing,2014,24:494-499
  • 加载中
WeChat 点击查看大图
计量
  • 文章访问数:  2488
  • HTML全文浏览数:  1966
  • PDF下载数:  763
  • 施引文献:  0
出版历程
  • 收稿日期:  2015-12-06
  • 刊出日期:  2016-04-15
刘萍, 简家文, 陈志芸. 基于集成神经网络的汽车尾气检测系统设计[J]. 环境工程学报, 2016, 10(4): 1883-1887. doi: 10.12030/j.cjee.20160448
引用本文: 刘萍, 简家文, 陈志芸. 基于集成神经网络的汽车尾气检测系统设计[J]. 环境工程学报, 2016, 10(4): 1883-1887. doi: 10.12030/j.cjee.20160448
shu
Liu Ping, Jian Jiawen, Chen Zhiyun. Design of detection system for automobile exhaust based on integrated neural network[J]. Chinese Journal of Environmental Engineering, 2016, 10(4): 1883-1887. doi: 10.12030/j.cjee.20160448
Citation: Liu Ping, Jian Jiawen, Chen Zhiyun. Design of detection system for automobile exhaust based on integrated neural network[J]. Chinese Journal of Environmental Engineering, 2016, 10(4): 1883-1887. doi: 10.12030/j.cjee.20160448
shu

基于集成神经网络的汽车尾气检测系统设计

  • 1. 宁波大学信息科学与工程学院, 宁波 315211
  • 收稿日期:  2015-12-06
基金项目:

国家自然科学基金资助项目(61471210)

浙江省宁波市科技局自然科学基金资助项目(2013A610002)

摘要: 为了准确、有效地检测汽车尾气中各气体的质量分数,对传感器阵列和BP神经网络技术进行了研究,设计了一套汽车尾气检测系统。首先,根据汽车尾气成分选取4个相应传感器和一个温湿度传感器组成传感器阵列,搭建汽车尾气检测装置;其次,为了克服单一BP神经网络预测精度低,容易陷入局部极值的缺点,建立基于Adaboost算法和BP神经网络的集成神经网络模型;最后,利用集成神经网络模型对传感器阵列的响应信号进行回归分析。结果表明,集成神经网络模型预测的平均相对误差小于3%,能够有效处理汽车尾气的检测数据。

English Abstract

    全文HTML

参考文献 (18)

返回顶部

目录

/

返回文章
返回

Copyright © 2019 中国科学院生态环境研究中心