| 147 | 0 | 60 |
| 下载次数 | 被引频次 | 阅读次数 |
为建立准确、稳健的八大生态区烤烟判别模型，选取全国八大生态区烤烟样品，分析烟叶中70种常量和半微量成分，采用逐步引入方法对建模指标进行筛选，基于Fisher判别法和烟叶化学成分含量构建八大生态区烤烟判别模型，并将该模型拓展应用于企业库存醇化片烟。结果表明：(1)采用逐步引入法筛选指标，以出现70频次的化学成分作为建模指标构建的八大生态区烤烟判别模型，五折验证平均预测准确率最高，达91.5%。(2)采用Fisher判别法和化学成分含量构建的八大生态区烤烟判别模型，训练集判别准确率可达94.3%，测试集判别准确率达93.0%；各生态区空间投影位置整体上接近程度，与其实际地理位置接近程度、样本感官风格接近程度均较为吻合。(3)使用基于近红外光谱技术预测的70种烟叶化学成分含量数据，应用上述建模方法可实现对涵盖国内外烤烟的两家企业实际库存醇化片烟的精准和稳健判别。
Abstract：To construct accurate and robust discrimination models for flue-cured tobacco from eight major ecological areas, flue-cured tobacco samples were collected from eight domestic ecological areas and 70constants and semi-trace components in tobacco leaves were analyzed. The modeling indexes were screened using a stepwise selection method. Discrimination models for flue-cured tobacco from the eight ecological areas were constructed based on Fisher Discriminant Analysis(FDA) and contents of tobacco chemical components. The constructed models were used to discriminate aged tobacco strips in warehouses of sampled enterprises. The results showed that: 1) By using the stepwise selection method to screen the indexes and chemical components with a frequency of 70 as the modeling indexes, the average discrimination accuracy of the models was the highest, achieving 91.5% in the 5-fold cross-validation.2) The discrimination models for flue-cured tobacco from the eight ecological areas constructed using the FDA method and chemical component contents had a discrimination accuracy of 94.3% in the training set and a discrimination accuracy of 93.0% in the test set. The proximity of the spatial projection positions of each ecological area was generally consistent with the proximity of the actual geographic locations and sensory styles of the leaf samples. 3) With the data of the 70 tobacco chemical component contents predicted by near-infrared spectroscopy, the above-mentioned modeling methods could be applied to accurately and robustly distinguish the actual aged tobacco strips of domestic and foreign flue-cured tobacco leaves in the warehouses of two enterprises.
[1]罗登山，王兵，乔学义.《全国烤烟烟叶香型风格区划》解析[J].中国烟草学报，2019,25(4):1-9.LUO Dengshan, WANG Bing, QIAO Xueyi.Explanation of national regionalization of leaves style of flue-cured tobacco[J]. Acta Tabacaria Sinica,2019,25(4):1-9.
[2]张同琢，王乐，梅吉帆，等.烤烟热分析图谱的香型判定模型构建[J].烟草科技，2020,53(6):75-80.ZHANG Tongzhuo,WANG Le,MEI Jifan,et al.Construction of a flavor category discrimination model based on thermal analysis spectra of flue-cured tobacco[J]. Tobacco Science&Technology,2020,53(6):75-80.
[3]薛芳，施丰成，李耀光，等.基于电子鼻的星座图聚类分析法在烟叶分类中的应用[J].烟草科技，2015,48(7):25-28.XUE Fang,SHI Fengcheng,LI Yaoguang,et al.Classifying flue-cured tobacco leaves with electronic nose-based constellation diagram clustering analysis[J].Tobacco Science&Technology,2015,48(7):25-28.
[4]施丰成，李东亮，冯广林，等.基于近红外光谱的PLS-DA算法判别烤烟烟叶产地[J].烟草科技，2013(4):56-59.SHI Fengcheng,LI Dongliang,FENG Guanglin,et al.Discrimination of producing areas of flue-cured tobacco leaves with near infrared spectroscopy-based PLS-DA algorithm[J]. Tobacco Science&Technology,2013(4):56-59.
[5]束茹欣，蔡嘉月，杨征宇，等.应用近红外光谱投影模型法分析烟叶的产区与风格特征[J].光谱学与光谱分析，2014,34(10):2764-2768.SHU Ruxin,CAI Jiayue,YANG Zhengyu,et al.Analysis of tobacco style features using near-infrared spectroscopy and projection model[J]. Spectroscopy and Spectra Analysis,2014,34(10):2764-2768.
[6]栾丽丽，王宇恒，胡文雁，等.应用近红外光谱和多算法融合方法分析烤烟的香型风格特征[J].光谱学与光谱分析，2017,37(7):2046-2049.LUAN Lili,WANG Yuheng,HU Wenyan,et al.Analysis of flue-cured tobacco flavor style feature using near-infrared spectroscopy and multiple algorithms fusion[J]. Spectroscopy and Spectra Analysis,2017,37(7):2046-2049.
[7]郝贤伟，帖金鑫，何文苗，等.基于近红外光谱-感官评价的巴西烟叶风格模拟及替代[J].烟草科技，2018,51(10):83-89.HAO Xianwei,TIE Jinxin,HE Wenmiao,et al. Style simulation and substitution of Brazilian tobacco based on near infrared spectrum and sensory evaluation[J].Tobacco Science&Technology,2018,51(10):83-89.
[8]汪阳忠，张鑫，蔡振波，等.近红外光谱融合电子鼻数据对烟叶产地判别研究[J].河南师范大学学报（自然科学版），2024,52(2):104-110.WANG Yangzhong,ZHANG Xin,CAI Zhenbo,et al.Classification of tobacco leave parts based on the fusion of near-infrared spectroscopy and Heracles electronic nose data[J]. Journal of Henan Normal University(Natural Science),2024,52(2):104-110.
[9]申钦鹏，张霞，张涛，等.基于烟叶化学成分烤烟香型分类模型的建立[J].湖北农业科学，2015,54(5):1220-1226.SHEN Qinpeng,ZHANG Xia,ZHANG Tao,et al.Construction of tobacco flavor classification model based on the chemical components of tobacco leaves[J]. Hubei Agricultural Sciences, 2015, 54(5):1220-1226.
[10]李超，李娥贤，秦云华，等.基于因子分析和Bayers判别的烤烟香型分类模型构建与验证[J].中国烟草科学，2016,37(3):72-78.LI Chao,LI Exian,QIN Yunhua,et al. Construction and verification of classification model for flavor of flue-cured tobacco based on factor analysis and Bayes discriminant[J]. Chinese Tobacco Science, 2016,37(3):72-78.
[11]郭东锋，胡海洲，汪季涛，等.基于随机森林的烤烟香型分类研究[J].中国农学通报，2015,31(6):241-246.GUO Dongfeng,HU Haizhou,WANG Jitao,et al.Study on the classification of flue-cured tobacco based on the random forest algorithm[J]. Chinese Agricultural Science Bulletin,2015,31(6):241-246.
[12]许永，张涛，吴亿勤，等.基于烟叶致香成分建立烤烟香型分类模型方法研究[J].中国农学通报，2016,32(25):181-187.XU Yong,ZHANG Tao,WU Yiqin,et al. Flavor classification model based on aroma components of tobacco leaves[J]. Chinese Agricultural Science Bulletin,2016,32(25):181-187.
[13]邱昌桂，孔兰芬，杨式华，等.基于GA-SVM算法的烤烟香型自动识别研究[J].烟草科技，2019,52(2):101-108.QIU Changgui,KONG Lanfen,YANG Shihua,et al.Automatic recognition of flavor types of flue-cured tobacco based on GA-SVM algorithm[J]. Tobacco Science&Technology,2019,52(2):101-108.
[14]张诺涵，赵乐，王迪，等. Q型因子光谱转移法用于烟草化学成分近红外预测模型的传递[J].烟草科技，2024,57(2):18-26.ZHANG Nuohan,ZHAO Le,WANG Di,et al. Using Q-factor spectral transfer method to improve transferability of near-infrared prediction models for tobacco chemical components[J]. Tobacco Science&Technology,2024,57(2):18-26.
[15]Liang Y Y,Zhao L,Guo J W,et al. Just-in-time learning-integrated partial least-squares strategy for accurately predicting 71 chemical constituents in Chinese tobacco by near-infrared spectroscopy[J]. ACS Omega,2022(7):38650-38659.
[16]Guo J W,Zhao L,Liang Y Y,et al. Moisture-adaptive corrections of NIR for the rapid simultaneous analysis of 70 chemicals in tobacco:A case study on tobacco[J]. Microchemical Journal,2023(189):108522.
[17]YC/T 468—2013烟草及烟草制品总植物碱的测定连续流动（硫氰酸钾）法[S].YC/T 468—2013 Tobacco and tobacco products—Determination of total alkaloids—Continuous flow(potassium thiocyanate)method[S].
[18]YC/T 159—2019烟草及烟草制品水溶性糖的测定连续流动法[S].YC/T 159—2019 Tobacco and tobacco products—Determination of water soluble sugars—Continuous flow method[S].
[19]YC/T 161—2002烟草及烟草制品总氮的测定连续流动法[S].YC/T 161—2002 Tobacco and tobacco products—Determination of total nitrogen—Continuous flow method[S].
[20]YC/T 217—2007烟草及烟草制品钾的测定连续流动法[S].YC/T 217—2007 Tobacco and tobacco products—Determination of potassium—Continuous flow method[S].
[21]YC/T 162—2011烟草及烟草制品氯的测定连续流动法[S].YC/T 162—2011 Tobacco and tobacco products—Determination of chlorine—Continuous flow method[S].
[22]王冰，余晶晶，蔡君兰，等. GC-MS/MS法同时分析烟叶中42种有机酸[J].烟草科技，2020,53(11):49-58.WANG Bing, YU Jingjing, CAI Junlan, et al.Simultaneous determination of forty-two organic acids in tobacco leaves with gas chromatography-tandem mass spectrometry[J]. Tobacco Science&Technology,2020,53(11):49-58.
[23]YC/T 282—2009烟叶游离氨基酸的测定氨基酸分析仪法[S].YC/T 282—2009 Tobacco leaf—Determination of dissociated amino acids—Amino acid analyzer method[S].
[24]王晓瑜，王昇，刘鸿，等. HPLC-MS/MS法同时测定烟草中22种Amadori化合物[J].烟草科技，2021,54(4):40-48.WANG Xiaoyu,WANG Sheng,LIU Hong,et al.Simultaneous determination of 22 Amadori compounds in tobacco leaves by HPLC-MS/MS[J]. Tobacco Science&Technology,2021,54(4):40-48.
[25]YC/T 202—2006烟草及烟草制品多酚类化合物绿原酸、莨菪亭和芸香苷的测定[S].YC/T 202—2006 Tobacco and tobacco products—Determination of polyphenols—Chlorogenic acid,scopletin and rutin[S].
[26]郭军伟，王洪波，刘绍锋，等.一种用于测定烟草二氯甲烷提取物含量的抽滤装置：CN209123445U[P].2019-07-19.GUO Junwei,WANG Hongbo,LIU Shaofeng,et al.Suction filtration device for measuring content of dichloromethane extract in tobacco:CN209123445U[P]. 2019-07-19.
[27] YC/T 216—2013烟草及烟草制品淀粉的测定连续流动法[S].YC/T 216—2013 Tobacco and tobacco products—Determination of starch—Continuous flow method[S].
[28]王洪波，郭军伟，王晓瑜，等.电感耦合等离子体质谱法快速测定新鲜烟叶中的9种营养元素[J].烟草科技，2014(6):41-44.WANG Hongbo,GUO Junwei,WANG Xiaoyu,et al.Determination of nine nutrient elements in fresh tobacco leaves by ICP-MS[J]. Tobacco Science&Technology,2014(6):41-44.
[29]YC/T 248—2008烟草及烟草制品无机阴离子的测定离子色谱法[S].YC/T 248—2008 Tobacco and tobacco products—Determination of inorganic anion—Ion chromatographic method[S].
[30]GB/T 31758—2015烟叶和烟叶提取物中茄尼醇的测定高效液相色谱法[S].GB/T 31758—2015 Determination of solanesol in tobacco leaves and the extracts of tobacco leaves—High performance liquid chromatography method[S].
[31]YC/T 222—2007烟草及烟草制品p H的测定[S].YC/T 222—2007 Tobacco and tobacco products—Determination of pH[S].
[32]YC/T 31—1996烟草及烟草制品试样的制备和水分测定烘箱法[S].YC/T 31—1996 Tobacco and tobacco products—Preparation of test sample and determination of water content—Oven method[S].
[33]张学工.模式识别[M]. 3版.北京：清华大学出版社，2010.ZHANG Xuegong. Pattern recognition[M]. 3rd ed.Beijing:Tsinghua University Press,2010.
[34]陈辉，李军，李启飞.基于MATLAB的判别分析的改进与实现[J].计算机仿真，2007,24(9):79-81,94.CHEN Hui, LI Jun, LI Qifei. Improvement and realization of discriminant analysis in MATLAB[J].Computer Simulation,2007,24(9):79-81,94.
[35]谢娟，罗建群，姚鹤鸣，等.基于NIR和化学指标的国产烤烟烟叶产地、部位模式识别[J].烟草科技，2008,41(7):42-44,47.XIE Juan,LUO Jianqun,YAO Heming,et al. Pattern recognition of growing area and stalk position of domestic flue-cured tobacco based on NIR and chemical components[J]. Tobacco Science&Technology,2008,41(7):42-44,47.
[36]付博，杨永锋，刘向真，等.基于近红外光谱的烤烟香型分类模型研究[J].河南农业科学，2023,52(7):163-171.FU Bo,YANG Yongfeng,LIU Xiangzhen,et al. Study on aroma type classification model based on near infrared spectra of flue-cured tobacco[J]. Journal of Henan Agricultural Sciences,2023,52(7):163-171.
基本信息:
DOI：10.16135/j.issn1002-0861.2024.0506
中图分类号:TS411
引用信息:
[1]王聪,马胜涛,王志才等.基于Fisher判别法和烟叶化学成分的八大生态区烤烟判别模型构建[J].烟草科技,2025,58(02):1-10+64.DOI:10.16135/j.issn1002-0861.2024.0506.
基金信息:
中国烟草总公司科技项目“烤烟烟叶风格与质量的化学表征组学研究”（中烟办[2020]66号）;中国烟草总公司揭榜挂帅项目“全息化学组分的配方技术研究”（中烟办[2021]150号）; 河南中烟工业有限责任公司科技项目“烟叶原料质量数字化表征技术研究”（AW202183）