(英)机动车尾气CO检测中神经网络多环境因子在线修正算法研究
投稿时间:2018-04-06  修订日期:2018-04-25  点此下载全文
引用本文:
摘要点击次数: 119
全文下载次数: 
作者单位E-mail
刘国华 中国科学院合肥物质科学研究院安徽光机所 ghliu@aiofm.ac.cn 
张玉钧 中国科学院合肥物质科学研究院安徽光机所  
张恺 中国科学院合肥物质科学研究院安徽光机所  
唐七星 中国科学院合肥物质科学研究院安徽光机所  
范博强 中国科学院合肥物质科学研究院安徽光机所  
鲁一冰 中国科学院合肥物质科学研究院安徽光机所  
尤坤 中国科学院合肥物质科学研究院安徽光机所  
何莹 中国科学院合肥物质科学研究院安徽光机所  
余冬琪 中国科学院合肥物质科学研究院安徽光机所  
基金项目:the National Key Research and Development Program of China (Project No.2016YFC0201000), and Anhui science and technology major project (Project No. 15czz04124).
中文摘要:对机动车高温尾气的CO进行准确检测,研究机动车尾气对大气环境的污染程度是环境监测与治理的工作重点。采用NDIR方法,利用取样测量系统,分析了温度、湿度、压力对预处理后尾气CO浓度测量的影响,提出了一种机动车尾气CO检测神经网络多环境因子在线修正算法,首先采用大量机动车尾气样本数据离线训练得到BP神经网络模型,然后将实时测得的样品气温度、湿度、压力及小数吸收值代入到模型进行在线修正,得到修正后CO浓度,解决了NDIR传感器在检测过程中因环境变化所带来的测量误差影响。通过标样实验、模拟实验,并和SEMTECH-EcoStar对比检测结果,在样品气温度30~50℃、相对湿度25~40%、压力95~115KPa、CO浓度0~0.2%范围内的最大相对偏差为4.8%。进一步进行车载外场实验,得到修正因子在0.8~1之间,验证了方法的必要性和可靠性,为实现机动车高温尾气的CO浓度的准确检测提供有效技术支持。
中文关键词:尾气CO检测  红外吸收  多环境因子  在线修正  BP神经网络
 
Research on Online Correction Algorithm withNeural Network Multi - environment Factors for CO Detection of Motor Vehicle Exhaust
Abstract:It is the focus of environmental monitoring and control to detect the CO concentration of high-temperature exhaust gas of a motor vehicle accurately and to study the pollution of the exhaust gas from the motor vehicle to the atmospheric environment. The NDIR method is used to analyze the effect of temperature, humidity and pressure on the measurement of CO concentration in exhaust gas after pretreatment. An on-line correction algorithm with multi-environment factors of neural network for the vehicle exhaust CO detection has been proposed. First, the exhaust gas sample data of a large number of motor vehicles has been trained offline to build the BP neural network model, and then the real-time measured temperature, humidity, pressure and decimal absorption value of the samples have been put into the model for its online correction. Then the corrected CO concentration has been achieved, so the measurement error of the NDIR sensor caused by environmental changes in the detection process has been solved. Through the prototype experiment, the simulation experiment and the comparison with SEMTECH-EcoStar, the maximum relative deviation of the CO with the concentration from 0 to 0.2% is 4.8% when the temperature range is from 30 to 50 ℃, relative humidity is from 25 to 40%, the pressure is from 95 to 115KPa. The further experiments have been carried out in the vehicle field to get the correction factor between 0.8 and 1, which verified the necessity and reliability of the method and provided effective technical support for the accurate detection of the CO concentration of the high-temperature exhaust gas from motor vehicles.
keywords:exhaust CO detection  infrared absorption  multiple environmental factors online correction  BP neural network
  查看/发表评论  下载PDF阅读器

版权所有:《红外与毫米波学报》编辑部