| 428 | 2 | 196 |
| 下载次数 | 被引频次 | 阅读次数 |
【目的】明确烟丝回弹特性对烟支物理质量的影响。【方法】对不同牌号不同批次烟丝的回弹特性及对应卷制批次的烟支物理质量(烟支硬度、烟支含末率、端部落丝量)进行相关性分析，利用烟丝物理指标(长丝率、中丝率、碎丝率、填充值、含水率)及回弹特性基于机器学习分别搭建并优化烟支物理指标(烟支硬度、烟支含末率、端部落丝量)的预测模型。【结果】(1)烟丝回弹特性与烟支硬度为显著正相关，与烟支含末率及烟支端部落丝量之间的相关关系呈负相关关系。(2)烟支硬度的最佳预测模型为网格搜索优化的梯度提升回归，R2为0.95；烟支含末率的最佳预测模型为贝叶斯优化的梯度提升回归，R2为0.97；烟支端部落丝最佳预测模型为网格搜索优化的随机森林回归，R2为0.97。【结论】所构建的模型均具有较高的精准度，在一定实验条件下可用于对烟支物理指标的预测。
Abstract：[Background] This study aims to clarify the impact of the rebound characteristics of cut tobacco on the physical quality of cigarettes. [Methods] The rebound characteristics of cut tobacco of different brands and batches and the physical quality of cigarettes from corresponding production batches(cigarette hardness, cigarette dust content, and end loose filler) were analyzed for correlation. Based on the physical indicators of cut tobacco(long shred rate, medium shred rate, short shred rate, filling power, moisture content) and rebound characteristics, machine learning was used to build and optimize prediction models for the physical indicators of cigarettes(cigarette hardness, cigarette dust content, and end loose filler). [Results] (1) The rebound characteristics of cut tobacco were significantly positively correlated with cigarette hardness and negatively correlated with cigarette dust content and end loose filler.(2) The best prediction model for cigarette hardness was gradient boosting regression optimized by grid search, with an R2 of 0.95; the best prediction model for cigarette dust content was gradient boosting regression optimized by Bayesian optimization, with an R2 of 0.97; the best prediction model for end loose filler was random forest regression optimized by grid search, with an R2 of 0.97. [Conclusion] The constructed models all have high accuracy and can be used to predict the physical indicators of cigarettes under certain experimental conditions.
[1]任发军，胡发志，郭春晖，等.不同规格卷烟物质指标影响因素研究进展[J].湖南文理学院学报（自然科学版），2021, 33(04):83-87.REN Fajun, HU Fazhi, GUO Chunhui, et al. Research progress on influencing factors of substance indicators in different specifications of cigarettes[J]. Journal of Hunan. University of Arts and Sciences(Natural Science Edition), 2021, 33(04):83-87.
[2]方畅.基于PROTOS 90高速烟机设备的设备综合效率研究改造[D].华南理工大学，2019.FANG Chang. Research and Transformation of equipment comprehensive efficiency based on PROTOS 90 high Speed smoke machine equipment[D]. South China University of Technology,2019.
[3] YC/T 152—2001,卷烟烟丝填充值的测定[S].YC/T 152-2001, Determination of filling value of cut tobacco[S].
[4] YC/T 186—2004,卷烟烟丝弹性的测定方法[S].YC/T 186-2004, Test method for elasticity of cut tobacco[S].
[5]李晓，李劲锋，郭朋玮，等.烟丝回弹特性检测方法的建立及参数优化[J].中国烟草学报，2023, 29(02):1-10.LI Xiao, LI Jinfeng, GUO Pengwei, et al. Establishment and parameter optimization of a detection method for the rebound characteristics of cut tobacco[J]. Acta Tabacaria Sinica, 2023,29(02):1-10.
[6] 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/T31-1996 Preparation and determination of moisture in tobacco and tobacco products-oven method[S].
[7] YC/T 289—2009卷烟配方烟丝结构的测定[S].YC/T 289-2009 Determination of the structure of cut tobacco in cigarette formula[S].
[8] GB/T 22838.4—2009卷烟和滤棒物理性能的测定[S].GB/T 22838.4-2009 Determination of physical properties of cigarettes and filter rods[S].
[9]何华，申晓锋，华一崑,等.卷制质量的影响因素研究进展[C]//中国烟草学会工业专业委员会烟草工艺学术研讨会论文集.青岛：中国烟草学会，2010.HE Hua, SHEN Xiaofeng, HUA Yikun, et al. Research progress on influencing factors of roll quality[C]//Proceedings of the Tobacco Technology Academic Seminar of the Industrial Professional Committee of the China Tobacco Society Qingdao:China Tobacco Society, 2010.
[10]刘德强，贾洋，王乐军，等.烟丝结构对烟支卷制质量的影响[J].安徽农业科学，2010, 38(32):18589-18590.LIU Deqiang, JIA Yang, WANG Lejun, et al. The effect of cut tobacco structure on the quality of cigarette roll making[J]. Anhui Agricultural Science, 2010, 38(32):18589-18590.
[11]鲁平，楚文娟，崔春，等.烟丝填充状态对卷烟卷制品质及包灰性能的影响[J].轻工学报，2023,38(05):68-73+82.LU Ping, CHU Wenjuan, CUI Chun, et al. The influence of tobacco filling state on cigarette rolling quality and ash wrapping performance[J]. Journal of Light Industry, 2023,38(05):68-73+82.
[12]卢幼祥，叶浩，邵名伟，等.切丝宽度对细支卷烟质量影响分析[J].湖南文理学院学报（自然科学版），2023,35(01):53-57+88.LU Youxiang, YE Hao, SHAO Mingwei, et al. Analysis of the influence of cutting width on the quality of fine count cigarettes[J].Journal of Hunan University of Arts and Sciences(Natural Science Edition), 2023, 35(01):53-57+88.
[13]姚二民，邵宁，李晓，等.基于回归分析方法的烟丝结构与卷烟物理指标关系研究[J].食品工业科技，2017,38(20):21-24+29.YAO Ermin, SHAO Ning, LI Xiao, et al. Research on the relationship between cut tobacco structure and cigarette physical indicators based on regression analysis method[J]. Food Industry Technology, 2017, 38(20):21-24+29.
[14]堵劲松，申晓锋，李跃锋，等.烟丝结构对卷烟物理指标的影响[J].烟草科技，2008(08):8-13.DU Jinsong, SHEN Xiaofeng, LI Yuefeng, et al. The effect of tobacco structure on the physical indicators of cigarettes[J].Tobacco Technology, 2008(08):8-13.
[15]姚光明，李晓，尹献忠，等.烟丝整丝率变化率对卷烟卷接质量的影响[J].烟草科技，2004(11):3-6.YAO Guangming, LI Xiao, YIN Xianzhong, et al. The effect of the change rate of cut tobacco percentage on the quality of cigarette splicing[J]. Tobacco Science and Technology, 2004(11):3-6.
[16]付永民，范磊，李长进，等.基于BP神经网络的烟草制丝工艺参数优化研究[J].轻工学报，2023,38(05):104-111.FU Yongmin, FAN Lei, LI Changjin, et al. Study on optimization of tobacco silk production process parameters based on BP neural network[J]. Journal of Light Industry, 2023,38(05):104-111.
[17]郭奇，吴建德，邓为权，等.基于梯度提升树的烟丝水份控制研究[C]//第31届中国过程控制会议（CPCC 2020）摘要集.江苏：中国自动化学会, 2020.GUO Qi, WU Jiande, DENG Weiquan, et al. Research on tobacco moisture control based on gradient lifting tree[C]//Summary of the31st China Process Control Conference(CPCC 2020). Jiangsu:China Automation Society, 2020.
[18]付永民，范磊，李长进，等.基于计算机视觉与机器学习的烟丝杂质图像级联检测方法[J].轻工学报，2023,38(04):113-121.FU Yongmin, FAN Lei, LI Changjin, et al. A cascaded detection method for tobacco impurity images based on computer vision and machine learning[J]. Journal of Light Industry, 2023,38(04):113-121.
[19]田震，藏照阳，毛文龙，等.云南楚雄和丽江烟叶关键质量指标筛选及分类研究[J].中国烟草学报，2023, 29(04):10-21.TIAN Zhen, ZANG Zhaoyang, MAO Wenlong, et al. Screening and classification of key quality indicators for tobacco leaves in Chuxiong and Lijiang, Yunnan[J]. Acta Tabacaria Sinica, 2023,29(04):10-21.
[20]张立秀，张淑娟，孙海霞，等.高光谱技术结合网格搜索优化支持向量机的桃缺陷检测[J].食品与发酵工业，2023, 49(16):269-275.ZHANG Lixiu, ZHANG Shujuan, SUN Haixia, et al. Peach defect detection using hyperspectral technology combined with grid search optimization support vector machine[J]. Food and Fermentation Industry, 2023, 49(16):269-275.
[21]孟光磊，丛泽林，宋彬，等.贝叶斯网络结构学习综述[J/OL].北京航空航天大学学报：1-24.MENG Guanglei, CONG Zelin, SONG Bin, et al. A review of bayesian network structure learning[J/OL]. Journal of Beijing University of Aeronautics and Astronautics:1-24.
基本信息:
DOI：10.16472/j.chinatobacco.2023.T0182
中图分类号:TS452;TP181
引用信息:
[1]李宜馨,郭朋玮,周茂忠等.基于机器学习的烟丝回弹特性与烟支物理指标关系研究[J].中国烟草学报,2024,30(06):39-47.DOI:10.16472/j.chinatobacco.2023.T0182.
基金信息:
河南中烟工业有限责任公司重点项目“烟丝柔软性的检测与应用研究”（AW201911）