文献类型：期刊文献

中文题名：烟叶总还原糖近红外光谱稳健模型的建立及其在多台仪器的长期应用

英文题名：Establishment of Robust Near Infrared Spectroscopy Model for Predicting of Total Reductive Sugar in Tobacco Leaves and Its Long-time Service on Multiple Instruments

作者：束茹欣[1];居雷[1];吴圣超[1];倪力军[2];王文俊[1];栾绍嵘[2];张立国[2]

机构：[1]上海烟草集团有限责任公司卷烟烟气重点实验室,上海201315;[2]华东理工大学化学与分子工程学院,上海200237

年份：2023

卷号：42

期号：11

起止页码：1479

中文期刊名：分析测试学报

外文期刊名：Journal of Instrumental Analysis

收录：CSTPCD;;Scopus;北大核心:【北大核心2020】；CSCD:【CSCD2023_2024】；

语种：中文

中文关键词：多步波长筛选;近红外光谱模型传递;模型寿命;烟叶;总还原糖;尺度不变特征变换

外文关键词：multi-step wavelength selection;transfer of near infrared spectroscopy model;service life of the model;tobacco leaves;total reductive sugar;scale invariant feature transformance

摘要：该文使用基于光谱图像特征抽提的尺度不变特征变换(SIFT)的多步波长筛选方法建立了烟叶总还原糖(TRS)的近红外光谱(NIRS)稳健模型,实现了其在多台仪器的直接共享和长期应用。首先采用SIFT方法根据代表性主机样品光谱挑选特征光谱点集合Uc,然后从Uc中剔除样本光谱标准方差(SDSS)过低的点,挑选重要特征光谱点集合Uic,此两步波长筛选法简称为SIFT-SDSS。随后进一步从Uic中挑选对水分不敏感(Mois?ture-unsensitive,MUS)的波长点,得到重要且稳定的光谱点集合Uisc,此3步波长筛选法简称为SIFT-SDSSMUS。从2011~2013年采集的292个主机烟叶样品中按TRS浓度区间选择80%样品作为建模集,建立不同波长集合下烟叶TRS的偏最小二乘回归(PLSR)校正模型。结果表明,基于SIFT-SDSS两步波长筛选的光谱点建立的TRS模型传递到6台从机预测另外77个2011~2013年样品的TRS时,所有从机样品的平均相对误差绝对值(MARE)均小于6%,满足企业内控要求。该模型对5台近红外仪上2014~2020年各年度样品、1台近红外仪上2014~2019年各年度样品的MARE均小于6%。而全波长模型及SIFT波长筛选方法所建模型在7台仪器上对多个不同年份下样品中TRS的MARE大于6%,难以实现长期应用。SIFT-SDSS-MUS方法所建TRS模型变量最少,但其模型传递能力和长期应用能力略逊于SIFT-SDSS模型。SIFT-SDSS所建TRS模型稳健性好、可解释性强、运算速度快,可在7台同型号近红外仪上直接共享、在6台仪器上连续应用至少6年,大大减少了烟叶TRS近红外光谱模型维护及传递的工作量。
Present work proposed multi-step wavelength selection methods based on scale invariant feature transformance(SIFT)algorithm of extracting features of spectra images to build robust near infrared spectra(NIRS)models for predicting total reduced sugar(TRS)in tobacco leaves.So that the models can be directly shared by multiple NIRS instruments and applied in long period.The SIFT method was firstly applied to select characteristic spectral points of Uc based on several representative spectra of primary samples.Then the spectral points with lower standard deviance of the sample spectra(SDSS)values were eliminated from Uc to obtain important characteristic spectral points of Uic.The two-step wavelength selection method was named as SIFT-SDSS.Furthermore,the moisture-unsensitive(MUS)wavelengths were selected from Uic to get important and stable characteristic spectral points of Uisc.The three-step wavelength selection method was named as SIFT-SDSS-MUS.The partial least square regression(PLSR)models for predicting TRS were established based on different wavelength sets by using 80%of 292 primary tobacco leaf samples according to their TRS concentration ranges as calibration set,which were harvested in 2011-2013.The results indicate that when the TRS model based on the wavelengths selected by the SIFT-SDSS method was transferred to six secondary instruments to predict TRS in another 77 samples harvested in 2011-2013,the mean of absolute relative errors(MAREs)obtained from the spectra tested on the six units were all below 6%,satisfying the internal control requirement of tobacco enterprises.For each year samples of 2014-2020 tested on 5 NIRS instruments,and each year samples of 2014-2019 tested on another NIRS instrument,the model built by the SIFT-SDSS can provide MARE lower than 6%.While MAREs of TRS in samples harvested in many years and tested on the 7 NIRS instruments,which were predicted by full-wavelength model and the model based on the SIFT were higher than 6%.The two models cannot be applied on multiple instruments in long period.The TRS model built by the SIFT-SDSS-MUS method has the fewest variables,but its transferability and long-time service ability is a little inferior to the model built by the SIFT-SDSS method.In conclusion,the TRS model established by important characteristic wavelength selection method of SIFT-SDSS is most robust,has strong interpretability and fast computation speed.It can be directly shared among seven NIRS instruments and continuously service on 6 instruments at least six years.The work amount on maintenance and transfer of the TRS model is therefore greatly reduced.