摘要
针对混合气体检测准确性较低问题,提出一种新型的二元混合气体检测方法。该方法利用核主成分分析（KPCA）对多路信号的非线性特征提取能力,提取不同成分组合下的二元混合气体的特征对k最近邻域（KNN）分类器进行建模,实现目标气体的识别。采用多变量相关向量机的多元非线性回归特性对二元混合气体组成成分进行定量估计。设计了以CO和CH4为目标气体的实验系统获取实验样本,对所提出的二元混合气体检测方法进行对比验证。实验结果表明,相比于基于主成分分析法和独立成分分析法的气体识别方法,提出方法的气体识别准确率分别提高了5.83%、14.16%,达到98.33%。相比于单一相关向量机（RVM）和最小二乘支持向量（LS-SVR）的混合气体浓度估计方法,方法有效提高了估计的准确性,CO和CH4浓度估计的平均相对误差分别仅有5.58%、5.38%。
In view of the low accuracy of the existing gas detection methods,a novel detection method for binary hybrid gas is proposed.Adopting multichannel nonlinear feature extraction ability,the kernel principal component analysis（KPCA） algorithm is used to extract the binary gas mixtures under different compositions. And the K-nearest neighbor classifier is utlized to achieve the target gas identification. Multivariate relevance vector machine（MVRVM） is used to measure the composition of binary mixture gas by taking advantage of its multivariate nonlinear regression performance. An experimental system is designed including CO gas and CH4 gas to obtain experimental samples,and the proposed binary mixed gas detection method is verified. The experimental results illustrate that,compared to gas identification methods based on principal componet analysis（PCA） and independent component analysis（ICA）,the gas recognition accuracy of proposed method improves 5. 83% and 14. 16%,respectively,and reaches to 98. 33%. Compared to gas estimation methods based on the single RVM and least squaret support vector regression（LS-SVR）,the proposed method based on MVRVM effectively improves the accuracy,and the average relative errors of CO and CH4 concentration estimation are only 5. 58% and5. 38% respectively.
作者
许永辉
陈寅生
张铭
Xu Yonghui;Chen Yinsheng;Zhang Ming(School of Electrical Engineering and Automation,Harbin Institute of Technology,Harbin 150001,China;School of Measurement and Communication Engineering,Harbin University of Science and Technology,Harbin 150001,China;Division of Communication Missions,Innovation Academy for Microsatellites of CAS,General Department of Communication Satellite,Shanghai 200000,China)
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2018年第5期179-187,共9页
Chinese Journal of Scientific Instrument
基金
国家自然科学基金青年基金(61501149)
中国博士后科学基金(2016M601437)项目资助
关键词
传感器阵列
气体检测
气体识别
核主成分分析
多变量相关向量机
sensor array
gas detection
gas identification
kernel principal component analysis （KPCA）
multivariate relevance vectormachine （MVRVM）
