摘要
为了提高烤烟烟叶香型判定的效率,基于热分析图谱和机器学习提出了一种烤烟烟叶香型判别的新方法.采用热重分析仪测定了中国八大香型烤烟烟叶热分析图谱,通过各香型烟叶样品热解温度差异比较,提取了不同香型烟叶样品的热解特征温度;依据遗传算法改进的支持向量机构建了香型判别模型,并测定了模型判定的准确率.结果表明:①八大香型烤烟烟叶热分析图谱在150~400℃区间存在明显差异.②Ⅰ、Ⅱ、Ⅲ、Ⅳ、Ⅴ、Ⅵ、Ⅶ、Ⅷ香型热解特征温度分别为368.3、763.4、613.0、517.2、611.2、652.6、336.1、383.5℃.③GA-SVM方法构建的香型判定模型对烤烟烟叶香型判定准确率为83.3%.
In order to promote the efficiency in discriminating flue-cured tobacco leaf categories,a new method based on thermal analysis spectra and machine learning was developed.The thermal analysis spectra from eight leaf flavor types were determined by a thermogravimetric analyzer.Via comparing the pyrolysis temperature differences among the eight flavor types,the characteristic pyrolysis temperatures for the different leaves were extracted.A flavor type discriminant model was constructed based on the support vector machine(SVM)improved by a genetic algorithm(GA),and its discriminant accuracy was verified.The results showed that:1)There were significant differences in the thermal analysis spectra of the tobacco samples in 150-400℃.2)The pyrolysis characteristic temperatures for typeⅠ-Ⅷwere 368.3,763.4,613.0,517.2,611.2,652.6,336.1,383.5℃respectively.3)The flavor type determination model constructed with GA-SVM method had a prediction accuracy rate of 83.3%.
作者
张同琢
王乐
梅吉帆
王安然
乔学义
王兵
李巧灵
李斌
ZHANG Tongzhuo;WANG Le;MEI Jifan;WANG Anran;QIAO Xueyi;WANG Bing;LI Qiaoling;LI Bin(Zhengzhou Tobacco Research Institute of CNTC,Zhengzhou 450001,China;National Tobacco Cultivation&Physiology&Biochemistry Research Center,College of Tobacco Science,Henan Agricultural University,Zhengzhou 450002,China;Technology Center,China Tobacco Fujian Industrial Co.,Ltd.,Xiamen 361022,Fujian,China)
出处
《烟草科技》
EI
CAS
CSCD
北大核心
2020年第6期75-80,共6页
Tobacco Science & Technology
基金
中国烟草总公司科技重点项目“全国烤烟烟叶香型风格区划研究”(110201402031)。
关键词
烤烟
烟叶
香型判定
机器学习
热分析谱图
Flue-cured tobacco
Tobacco leaf
Flavor type discrimination
Machine learning
Thermal analysis spectrum
