Quantitative analysis of pyrolysis characteristics and chemical components of tobacco materials based on machine learning

被引:3
作者
Wu, Zhifeng [1 ]
Zhang, Qi [1 ]
Yu, Hongxiao [2 ]
Fu, Lili [1 ]
Yang, Zhen [3 ]
Lu, Yan [1 ]
Guo, Zhongya [4 ]
Li, Yasen [3 ]
Zhou, Xiansheng [2 ]
Liu, Yingjie [5 ]
Wang, Le [1 ]
机构
[1] CNTC, Zhengzhou Tobacco Res Inst, Zhengzhou, Peoples R China
[2] China Tobacco Shandong Ind Co Ltd, Technol Ctr, Jinan, Peoples R China
[3] Minist Nat Resources, Minist & Municipal Jointly Build Key Lab Sichuan P, Chengdu, Peoples R China
[4] China Tobacco Guangdong Ind Co Ltd, Technol Ctr, Guangzhou, Peoples R China
[5] China Tobacco Shandong Ind Co Ltd, Qingzhou Cigarette Factory, Qinzhou, Peoples R China
来源
FRONTIERS IN CHEMISTRY | 2024年 / 12卷
关键词
tobacco material; chemical components; thermogravimetric analysis; machine learning; characteristic temperature range; CONSTITUENTS; PRODUCTS;
D O I
10.3389/fchem.2024.1353745
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
To investigate the quantitative relationship between the pyrolysis characteristics and chemical components of tobacco materials, various machine learning methods were used to establish a quantitative analysis model of tobacco. The model relates the thermal weight loss rate to 19 chemical components, and identifies the characteristic temperature intervals of the pyrolysis process that significantly relate to the chemical components. The results showed that: 1) Among various machine learning methods, partial least squares (PLS), support vector regression (SVR) and Gaussian process regression (GPR) demonstrated superior regression performance on thermogravimetric data and chemical components. 2) The PLS model showed the best performance on fitting and prediction effects, and has good generalization ability to predict the 19 chemical components. For most components, the determination coefficients R 2 are above 0.85. While the performance of SVR and GPR models was comparable, the R 2 for most chemical components were below 0.75. 3) The significant temperature intervals for various chemical components were different, and most of the affected temperature intervals were within 130 degrees C-400 degrees C. The results can provide a reference for the materials selection of cigarette and reveal the possible interactions of various chemical components of tobacco materials in the pyrolysis process.
引用
收藏
页数:11
相关论文
共 24 条
  • [1] Machine learning approach for the prediction of biomass pyrolysis kinetics from preliminary analysis
    Balsora, Hemant Kumar
    Kartik, S.
    Dua, Vivek
    Joshi, Jyeshtharaj Bhalchandra
    Kataria, Gaurav
    Sharma, Abhishek
    Chakinala, Anand Gupta
    [J]. JOURNAL OF ENVIRONMENTAL CHEMICAL ENGINEERING, 2022, 10 (03):
  • [2] Volatile Products Formed in the Thermal Decomposition of a Tobacco Substrate
    Barontini, Federica
    Tugnoli, Alessandro
    Cozzani, Valerio
    Tetteh, John
    Jarriault, Marine
    Zinovik, Igor
    [J]. INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2013, 52 (42) : 14984 - 14997
  • [3] Ensemble Partial Least Squares Algorithm Based on Variable Clustering for Quantitative Infrared Spectrometric Analysis
    Bi Yi-Ming
    Chu Guo-Hai
    Wu Ji-Zhong
    Yuan Kai-Long
    Wu Jian
    Liao Fu
    Xia Jun
    Zhang Guang-Xin
    Zhou Guo-Jun
    [J]. CHINESE JOURNAL OF ANALYTICAL CHEMISTRY, 2015, 43 (07) : 1086 - U62
  • [4] The applicability of different tobacco types to heated tobacco products
    Chen, Jie
    He, Xian
    Zhang, Xuyan
    Chen, Yi
    Zhao, Lu
    Su, Jiaen
    Qu, Shengbin
    Ji, Xinwei
    Wang, Tao
    Li, Zhenjie
    He, Chenggang
    Zeng, Erqing
    Jin, Yan
    Lin, Zhonglong
    Zou, Congming
    [J]. INDUSTRIAL CROPS AND PRODUCTS, 2021, 168
  • [5] The Use of the Artificial Neural Network (ANN) for Modeling of Thermogravimetric Curves of Tobacco Stalk Waste Exposed to Alkaline Treatment
    Dalle, Danieli
    Hansen, Betina
    Zattera, Ademir Jose
    Ornaghi, Heitor Luiz
    Monticeli, Francisco Maciel
    Catto, Andre Luis
    Borsoi, Cleide
    [J]. JOURNAL OF NATURAL FIBERS, 2022, 19 (15) : 12119 - 12128
  • [6] Machine Learning in Chemical Engineering: Strengths, Weaknesses, Opportunities, and Threats
    Dobbelaere, Maarten R.
    Plehiers, Pieter P.
    van de Vijver, Ruben
    V. Stevens, Christian
    Van Geem, Kevin M.
    [J]. ENGINEERING, 2021, 7 (09) : 1201 - 1211
  • [7] Determination of 27 chemical constituents in Chinese southwest tobacco by FT-NIR spectroscopy
    Duan, Jia
    Huang, Yue
    Li, Zuhong
    Zheng, Bo
    Li, Qianqian
    Xiong, Yanmei
    Wu, Lijun
    Min, Shungeng
    [J]. INDUSTRIAL CROPS AND PRODUCTS, 2012, 40 : 21 - 26
  • [8] Comparative investigation on thermal degradation of flue-cured tobacco with different particle sizes by a macro-thermogravimetric analyzer and their apparent kinetics based on distributed activation energy model
    Guo, Gaofei
    Liu, Chaoxian
    Wang, Yalin
    Xie, Shenglin
    Zhang, Ke
    Chen, Liangyuan
    Zhu, Wenkui
    Ding, Meizhou
    [J]. JOURNAL OF THERMAL ANALYSIS AND CALORIMETRY, 2019, 138 (05) : 3375 - 3388
  • [9] [郭恒 Guo Heng], 2022, [烟草科技, Tobacco Science and Technology], V55, P58
  • [10] Tobacco fractionation and its effects on pyrolysis chemistry
    Guo, Zhongya
    Zhang, Ke
    Zhang, Qi
    Fu, Lili
    Liu, Ze
    Kong, Zhen
    Wang, Le
    Liu, Chuan
    Hua, Lei
    Li, Bin
    [J]. JOURNAL OF ANALYTICAL AND APPLIED PYROLYSIS, 2022, 167