《烟草科技》：烟叶烘烤技术主题双语文章推荐

俗话说：“烟叶烤好是宝，烤坏是草”。烘烤工艺在烟叶制作环节至关重要。本期围绕烟叶烘烤技术主题，精选5篇发表在《烟草科技》上的双语文章，欢迎阅读！

精选文章

01

基于机器学习的密集烘烤过程烟叶失水率预测模型对比

Machine learning-based models for predicting dehydration rate of tobacco leaf during bulk curing and comparisons thereof

【摘要】为准确预测密集烘烤过程烟叶失水率，以精准调控烘烤工艺参数，基于机器学习建立烟叶失水率预测模型。以翠碧一号中部叶为材料，实时采集烘烤过程中烟叶图像和失水率；利用图像处理技术提取烟叶的10种颜色特征和10种纹理特征，通过变量聚类和皮尔逊相关性分析优选出2种颜色特征（a*/b*、R）和2种纹理特征（梯度熵、梯度分布不均匀性）；将训练集图像的4种优选特征和烟叶失水率作为输入变量，分别对建立的网格式支持向量机（GS-SVM）、遗传算法优化的BP神经网络（GA-BP）、极限学习机（ELM）3种预测模型进行训练。利用3种预测模型对测试集图像进行烟叶失水率预测并与实际失水率比较。结果表明，3种预测模型均能够较为准确地预测密集烘烤过程烟叶失水率（均方根误差RMSE≤0.014 0，决定系数R2≥0.996 1），对变黄期（0～40 h）和定色期（40～100 h）的预测误差小于干筋期（100～140 h）。该技术可为烟叶烘烤智能调控系统的研发提供支持。

【Abstract】This study aims to accurately predict the dehydration rate of tobacco leaf during bulk curing and precisely control curing process parameters. To be specific, three models for predicting the dehydration rate of tobacco leaf were established based on machine learning. Taking the middle leaves of cv. CB-1 as the material, the images and dehydration rates of tobacco leaves were collected in real time during the curing. Image processing technology was used to extract 10 color features and 10 textural features of the leaves, and 2 color features (a*/b*, R) and 2 textural features (gradient entropy, nonuniformity of gradient distribution) were selected through variable clustering and Pearson’s correlation analysis. The three established prediction models, the grid search support vector machine (GS-SVM), genetic algorithm optimized BP neural network (GA-BP), extreme learning machine (ELM) models, were subject to training with the four selected features of the images in the training set and the dehydration rates of tobacco leaves. The dehydration rates of tobacco leaves predicted by the three models were compared with the actual dehydration rates. The results showed that all the three prediction models could accurately predict the dehydration rates of tobacco leaves during bulk curing with the root mean square error (RMSE) ≤ 0.014 0 and coefficients of determination (R2) ≥ 0.996 1. The prediction errors for the leaves at yellowing stage (0–40 h) and leaf-drying stage (40–100 h) were lower than those at yellowing stage (100–140 h). This technology provides a support for the development of intelligent control system for tobacco leaf curing.

02

初烤烟叶不同区位色差变化及Fisher最优分割法分析

Chromatic aberrations of different parts of cured tobacco leaf by Fisher optimal segmentation analysis

【摘要】为探索色差法在烟叶分切打叶中的应用，选择K326 B2F、C3F、X2F初烤烟叶作为试验对象，分别将3个部位的烟叶去除叶柄后纵向平均分切成10个区位，利用色差计测定每个分切区位的色差值L*（明度值）、a*（红度值）、b*（黄度值），采用回归分析法研究K326烟叶不同区位色差值的变化趋势，通过Fisher最优分割法和感官评吸法分析各部位烟叶适宜的分段比例和感官质量差异。结果表明：①对于K326 3个部位的初烤烟叶，从叶基到叶尖，L*值呈逐渐降低的抛物线形变化趋势，a*、b*、△E（总色差）值呈先升高后降低的抛物线形变化趋势。②基于标准化的色差值矩阵，利用Fisher最优分割法确定了K326 3个部位初烤烟叶的最佳分段比例（叶基∶叶中∶叶尖）：B2F为20%∶50%∶30%、C3F为30%∶50%∶20%、X2F（叶基∶近基∶叶中∶叶尖）为10%∶30%∶40%∶20%。③三点法检验结果表明，分切后各段烟叶之间的整体感官品质均存在显著差异，说明色差法结合Fisher最优分割法能将同一烟叶品质差异较大的区位有效分离。

【Abstract】In order to evaluate the suitability of chromatic aberration as a method to monitor tobacco leaf cutting, we used K326 B2F, C3F, and X2F cured tobacco leaves as test samples. After the petiole was removed, a tobacco leaf was longitudinally divided into 10 locations at equal length. The lightness value (L*), redness value (a*), and yellowness value (b*) at each location were determined by a colorimeter. Regression analysis was performed to study the variations of chromatic aberration values at different locations of K326. Appropriate sectioning proportion and sensory quality of tobacco leaves from different stalk positions were analyzed by Fishers optimal segmentation method and sensory evaluation, respectively. The results are as follows. 1) For the upper, middle, and lower leaves of cured K326 and from the base to the tip, the L* value presented a decreasing parabolic trend, and the values of a*, b*, and △E (total chromatic aberration) presented an increasing parabolic trend first and then a decreasing one. 2) On the basis of the standardized chromatic aberration matrix, the optimal sectioning proportions for cured K326 were determined by Fisher optimal segmentation method as: 20%:50%:30% for B2F (base: middle: tip); 30%:50%:20% for C3F (base: middle: tip), and 10%:30%:40%:20% for X2F (base: near base: middle: tip), respectively. 3) The results of triangle test indicated that the overall sensory quality differed significantly at the different locations. It was suggested that the chromatic aberration combined with Fisher optimal segmentation could effectively separate the locations with greatest sensory quality difference of the same leaf.

03

初烤和复烤对烟叶真菌群落结构的影响

Effects of flue-curing and redrying on fungal community structure of tobacco leaves

【摘要】为了解初烤和复烤环节对烟叶真菌群落结构的影响，以贵州湄潭、平坝和惠水的烟叶为研究对象，通过高通量测序技术分析不同加工阶段（初烤前、初烤后、复烤前和复烤后）烟叶的真菌群落。12个样本共检测到真菌界4个门、23个纲、71个目、196个科、445个属、724个种和1 171个OTUs。结果表明初烤和复烤前后的烟叶真菌组成存在明显差异：在属水平上，初烤前Sampaiozyma和Symmetrospora为优势属，其相对丰度分别为44.27%和21.24%；初烤后Sampaiozyma、链格孢属（Alternaria）和未分类的亚隔孢壳科（Didymellaceae）真菌为优势属，其相对丰度分别为37.87%、18.42%和12.89%；复烤前曲霉属（Aspergillus）、Sampaiozyma和根霉属（Rhizopus）为优势属，其相对丰度分别为60.82%、24.12%和2.51%；复烤后Sampiozyma和曲霉属（Aspergillus）为优势属，其相对丰度分别为46.12%和25.78%。Sampaiozyma在4个加工阶段一直占据优势地位。

【Abstract】This study aims to investigate the effects of flue-curing and redrying on fungal community structure of tobacco leaves. To be specific, tobacco leaf samples were collected from Meitan, Pingba, and Huishui in Guizhou Province. The fungal community structure of the samples at different processing stages (before flue-curing, after flue-curing, before redrying, and after redrying) was analyzed by high-throughput sequencing technology. A total of 1 171 OTUs, 724 species, 445 genera, 196 families, 71 orders, 23 classes, and 4 phyla were detected from 12 leaf samples. The results showed that there were significant differences in the composition of tobacco fungi before and after flue-curing or redrying: At the genus level, Sampaiozyma and Symmetrospora were the dominant genera before flue-curing, and their relative abundance was 44.27% and 21.24%, respectively. After flue-curing, Sampaiozyma, Alternaria, and unclassified Didymellaceaewere the dominant genera with a relative abundance of 37.87%, 18.42%, and 12.89%, respectively. Before redrying, Aspergillus, Sampaiozyma, and Rhizopus were the dominant genera with a relative abundance of 60.82%, 24.12%, and 2.51%, respectively. After redrying, Sampiozyma and Aspergillus were the dominant genera with a relative abundance of 46.12% and 25.78%, respectively. Sampaiozyma dominated the fungi at all four processing stages.

04

基于响应曲面法的云产烟叶模块化打叶复烤工艺优化

Optimization of modular threshing and redrying of flue-cured tobacco from Yunnan based on response surface methodology

【摘要】为考察打叶复烤过程中关键工艺参数变化对云产烟叶模块质量的影响，选取“清甜香”风格特征适中的文山模块烟叶为研究对象，根据Box-Behnken Design（BBD）设计原理，以润叶含水率、润叶温度和复烤温度为主要影响因素，复烤叶片含水率和CCUI值为响应值，采用响应曲面法优化打叶复烤工艺条件，并建立相应的预测数学模型。结果表明：复烤叶片含水率、CCUI值与各关键工艺参数之间的变化均符合二次方程模型（R2分别为0.945 1和0.855 7），复烤温度对叶片含水率和CCUI值影响均较大，优化后最佳工艺参数为润叶含水率17.5%、润叶温度58.0℃、复烤温度406.0℃；优化条件下复烤叶片含水率9.627%、CCUI值0.851，其CCUI值较正常生产提高3.780%，内在品质提升显著（P<0.01），大片率和叶含梗率降低明显，干草香、正甜香和青香等香韵风格特征和感官品质更加凸显，说明适当提高润叶温度和复烤温度更有利于降低复烤叶片大片率、提升中小片率，彰显云产“清甜香”特征适中的烟叶模块风格和感官品质。

【Abstract】This study aims to investigate the influence of key parameters of threshing and redrying on the quality of tobacco leaf modular from Yunnan. To be specific, Wenshan leaves with a moderate “fresh-sweetness scent” style were studied. On the basis of Box-Behnken Design (BBD) principle, the conditions of threshing and redrying were optimized by adopting the response surface methodology and taking the moisture content in conditioning, conditioning temperature and redrying temperature as major influencing factors and the moisture content and CCUI values of redried strips as response values, and the corresponding prediction mathematical models were established. The results showed that the relationships between the moisture content and CCUI values of redried strips and key technological parameters were all consistent with the quadratic equation model (R2 = 0.945 1 and 0.855 7, respectively). Redrying temperature affected both the moisture content and CCUI values of the strips greatly. The optimal parameters were moisture content during conditioning at 17.5%, conditioning temperature at 58.0 °C, and redrying temperature at 406.0 °C. Under the optimized condition, the moisture content in the redried strips was 9.627% and its CCUI value was 0.851, which increased by 3.780% compared with that of regular production. The intrinsic quality of redried strips was significantly improved (P < 0.01). The percentage of large strips and the stems in the strips decreased significantly. The aroma notes of hay-like, pure-sweetness and green scents and sensory quality of the redried strips were more prominent. It indicated that properly raising conditioning temperature and redrying temperature were more beneficial in reducing the percentage of large strips, increasing the percentage of medium and small strips, and enhancing the style characteristics and the sensory quality of tobacco leaf modular from Yunnan.

05

基于配方原料均匀性的打叶复烤均质化调控策略选择

Selection of control strategy for homogenization in threshing and redrying based on uniformity of blended tobacco material

【摘要】为探索打叶复烤过程中均质化加工调控策略，采用把选和片选两种分选方式制备了具有不同化学成分均匀性的配方原料，采用三标度-层次分析法建立了均质化调控效果综合评价指标，对比了烟碱、颜色、光谱3种调控模式下的均质化调控效果。结果表明：（1）片选方式获得的配方原料均匀性明显优于把选方式。（2）调控模式对参评指标均匀性控制具有选择性，颜色调控模式能极显著提高成品片烟颜色均匀性。（3）配方原料均匀性较差时，调控策略宜选择涵盖多维度均质化信息的颜色或光谱调控因子；反之，选择烟碱调控因子即可获得较理想的综合均质化调控效果。该研究结果可为提高打叶复烤均质化加工水平提供支持。

【Abstract】To explore the control strategy for homogenized processing in threshing and redrying, the blended tobacco materials of different chemical uniformity were prepared through bundle-based and leaf-based selection methods separately. A three-scale analytic hierarchy process (AHP) was used to create a comprehensive evaluation index for assessing the result of homogenization control. The results of homogenization control under nicotine, color and spectrum control modes were compared. The results showed that: 1) The uniformity of blended tobacco material obtained through leaf-based selection was obviously better than that through bundle-based selection. 2) Different control modes showed different control results. The color control mode extremely significantly promoted color uniformity of redried tobacco strips. 3) When the blended tobacco material was not uniform, color or spectrum control modes that covered multi-dimensional homogenization information was preferable; otherwise nicotine control mode would offer more desirable result. This study provides a support for promoting the homogenized processing level of threshing and redrying.

期刊推荐

《烟草科技》期刊创办于1957年，是我国烟草行业创刊最早、发行量最大和影响面最广的综合性烟草科学研究和技术开发类学术刊物，由国家烟草专卖局主管、中国烟草总公司郑州烟草研究院主办。主要刊登烟草行业科学研究与技术研发方面的学术论文、研究报告以及反映国内外烟草科研进展、学术动态的综述性文章，设置的栏目有“烟草农学（含分子生物学）”“烟草化学”“烟草工艺”“设备与仪器”“信息技术”“综述”等。

中国知网“中文精品学术期刊外文版数字出版工程”（简称JTP）自2015年启动，已与400余种学术期刊合作出版了4万余篇双语对照论文，积累了丰富的学术翻译/英语加工/学术推广经验。形成了集双语出版、主题电子书出版、双语讲座视频制作、期刊英文内容编校加工、资讯编译、海外推广为一体的全方位服务体系，全面助力期刊提升国际影响力。

联系人：张老师13661148416；010-62969002-8173；zxd6974@cnki.net