基于温度调制的电子鼻技术应用研究  

Research on Application of E-nose Technology Based on Temperature Modulation

作　　者：杨志蒙 赵永礼 温举洪 彭志 银建新 Yang Zhimeng;Zhao Yongli;Wen Juhong;Peng Zhi;Yin Jianxin(School of Mechanical and Automotive Engineering,Shanghai University of Engineering Science,Shanghai 201620,China)

机构地区：[1]上海工程技术大学机械与汽车工程学院,上海市201620

出　　处：《农业装备与车辆工程》2022年第12期82-86,共5页Agricultural Equipment & Vehicle Engineering

摘　　要：提出一种静态温度调制方法优化气体传感器的选择性,进而提高电子鼻分类精度。该温度调制方法通过提供两种加热温度实现气体传感器选择性的优化,并利用该方法实现不同产地苹果的智能识别。首先,设计了一种基于温度调制的电子鼻系统,并给出了硬件设计电路。其次,提取两种加热温度下4种产地苹果的电子鼻检测数据。最后,基于主成分分析(PCA)、支持向量机(SVM)和卷积神经网络(CNN)算法对不同产地的苹果进行分类识别。结果表明,基于温度调制数据的PCA-SVM和PCA-CNN算法分类精度高于单一加热温度下的算法识别精度,采用温度调制方法可以有效提升电子鼻的性能。A static temperature modulation method was proposed to optimize the selectivity of gas sensor and improve the classification accuracy of electronic nose(E-nose).The gas selectivity was optimized by modulating two different heating temperatures in the gas sensor,which was then applied to design E-nose for identifying apples from different regions.First,a temperature modulation circuit in E-nose was designed.Secondly,the feature data of apples from four regions detected by the as-designed E-nose under two heating temperatures were extracted.Finally,Principal Component Analysis(PCA),Support Vector Machine(SVM),and Convolutional Neural Network(CNN)algorithm were employed to identify the four regions.The results show that the classification accuracy of the PCA-SVM and PCA-CNN algorithms based on temperature modulation data are higher than that of the algorithms based on data without temperature modulation,which indicates that the proposed method can effectively improve the detection performance of the E-nose.

关 键 词：温度调制 硬件电路 电子鼻检测 分类识别 

分 类 号：TP212.6[自动化与计算机技术—检测技术与自动化装置]