Food and Fermentation Industries >

2025 , Vol. 51 >Issue 23: 123 - 132

DOI: https://doi.org/10.13995/j.cnki.11-1802/ts.041785

Research on quality grading of Luzhou flavor Baijiu based on big data and multi substance coordination

  • ZHANG Guiyu ,
  • YAN Jun ,
  • WANG Yibo ,
  • XIANG Xingrui ,
  • ZHANG Lei ,
  • ZHANG Yunlong
Expand
  • 1(School of Automation & Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, China)
    2(Intelligent Perception and Control Key Laboratory of Sichuan Province, Sichuan University of Science & Engineering, Yibin 644000, China)
    3(Solid-state Brewing Technology Innovation Center of Sichuan, Luzhou 646000, China)
    4(Liquor Making Biotechnology and Intelligent Manufacturing of Key Laboratory of China National Light Industry, Yibin 644000, China)

Received date: 2024-12-05

  Revised date: 2025-04-02

  Online published: 2025-12-25

Fold

Abstract

Various volatile substances in the base Baijiu are crucial to the quality of Chinese Baijiu.The volatile substances in Baijiu are complex in composition, in which a single substance has an insignificant effect on the quality of the base Baijiu, while a variety of substances coordinated together may have a great impact on the quality of the Baijiu.In this study, gas chromatography-mass spectrometry was used to analyze the volatile substances in Baijiu, and 89 major volatile compounds were identified to investigate and analyze the quality grade of Baijiu based on multi-substance coordination.Spearman-interaction features, maximum mutual information method-interaction feature, information gain ratio algorithm-interaction feature, and feature weight algorithm-interaction feature were combined to investigate the effect of multi-substance coordination on the quality of base Baijiu in Baijiu, and to screen out the most influential combination of coordinated substances.At the same time, all the feature combinations were trained in the model, the key substances were screened independently, and support vector machine, random forest, and extreme gradient boosting were used to discriminate the grade of Baijiu.It was found that the key substances screened independently had a general effect on the quality grade of Baijiu.In contrast, the feature combinations based on the coordinated screening of multi-substances had good effects, among which the random forest based on the fusion analysis of Spearman’s positive and negative correlation had the best effect in terms of accuracy.The accuracy of random forest based on Spearman’s positive and negative correlation fusion analysis was the best, reaching more than 94%, which effectively distinguished the quality grades of different Baijius.

Key words： gas chromatography-mass spectrometry; Baijiu; multi-substance coordination; interaction features; Baijiu quality grade modelling

Cite this article

ZHANG Guiyu , YAN Jun , WANG Yibo , XIANG Xingrui , ZHANG Lei , ZHANG Yunlong . Research on quality grading of Luzhou flavor Baijiu based on big data and multi substance coordination[J]. Food and Fermentation Industries, 2025 , 51(23) : 123 -132 . DOI: 10.13995/j.cnki.11-1802/ts.041785

References

[1] 石俊, 王旭亮, 于佳俊, 等.中国酿造酒及蒸馏酒起源分析研究[J].酿酒科技, 2022(12):121-128.
SHI J, WANG X L, YU J J, et al.Origin of Chinese fermented wines and distilled spirits[J].Liquor-Making Science & Technology, 2022(12):121-128.
[2] 刘芮荻, 张宿义, 殷鹏飞, 等.白酒蒸馏理论与技术的研究进展[J].酿酒科技, 2022(9):85-90.
LIU R D, ZHANG S Y, YIN P F, et al.Research progress in distillation theory and technology of Baijiu[J].Liquor-Making Science & Technology, 2022(9):85-90.
[3] 谢军, 罗恵波, 曾勇, 等.中国白酒产业蒸馏装置的演变历程及研究现状[J].中国酿造, 2022,41(2):9-14.
XIE J, LUO H B, ZENG Y, et al.Evolution and research status of distillation device in Chinese Baijiu industry[J].China Brewing, 2022,41(2):9-14.
[4] 杨紫萱, 曾珊, 孙敏, 等.白酒挥发性风味物质检测技术研究进展[J].中国酿造, 2024,43(6):1-8.
YANG Z X, ZENG S, SUN M, et al.Research progress on detection technology of volatile flavor substances in Baijiu[J].China Brewing, 2024,43(6):1-8.
[5] WEI Y, ZOU W, SHEN C H, et al.Basic flavor types and component characteristics of Chinese traditional liquors:A review[J].Journal of Food Science, 2020,85(12):4096-4107.
[6] HONG J X, ZHAO D R, SUN B G.Research progress on the profile of trace components in Baijiu[J].Food Reviews International,2023,39(3):1666-1693.
[7] QIAO L N, WANG J, WANG R F, et al.A review on flavor of Baijiu and other world-renowned distilled liquors[J].Food Chemistry:X, 2023, 20:100870.
[8] HONG J X, TIAN W J, ZHAO D R.Research progress of trace components in sesame-aroma type of Baijiu[J].Food Research International, 2020,137:109695.
[9] 张琦, 沈才洪, 孙啸涛, 等.浓香型白酒蒸馏过程中挥发性风味物质的变化规律[J].现代食品科技, 2018,34(6):244-254.
ZHANG Q, SHEN C H, SUN X T, et al.Variation regularity of volatile substances in Luzhou flavor liquor during distillation process[J].Modern Food Science and Technology, 2018,34(6):244-254.
[10] HUANG Q, LIU Y, TIAN L, et al.Effects of storage time on flavor characteristics of bran-free fermented Baijiu by using electronic sensory, descriptive sensory analysis, GC×GC-MS, and ICP-MS[J].Food Chemistry:X, 2024, 23:101667.
[11] 陈明举, 周迪, 王鸿, 等.基于GC-MS的浓香型白酒等级评判模型研究[J].中国酿造, 2021,40(10):102-107.
CHEN M J, ZHOU D, WANG H, et al.Quality evaluation model of strong-flavor Baijiu based on GC-MS[J].China Brewing, 2021,40(10):102-107.
[12] 林先丽, 张晓娟, 李晨, 等.气相色谱-质谱和电子舌对不同质量等级酱香型白酒的判别分析[J].食品科学, 2023, 44(24):329-338.
LIN X L, ZHANG X J, LI C, et al.Discriminant analysis of Jiang-Flavor Baijiu of different grades by gas chromatography-mass spectrometry and electronic tongue[J].Food Science, 2023,44(24):329-338.
[13] CHEN M J, CUI A L, DUAN Z X, et al.Evaluation quality of Chinese Baijiu using GC-MS based on SPCA and neural network[J].International Journal of Pattern Recognition and Artificial Intelligence, 2023, 37(8):2359016.
[14] LIU Q R, ZHANG X J, ZHENG L, et al.Machine learning based age-authentication assisted by chemo-kinetics:Case study of strong-flavor Chinese Baijiu[J].Food Research International, 2023, 167:112594.
[15] DU J Y, LI Y M, XU J C, et al.Characterization of key odorants in Langyatai Baijiu with Jian flavour by sensory-directed analysis[J].Food Chemistry, 2021, 352:129363.
[16] WANG Z, WANG Y, ZHU T T, et al.Characterization of the key odorants and their content variation in Niulanshan Baijiu with different storage years using flavor sensory omics analysis[J].Food Chemistry, 2022, 376:131851.
[17] 王金龙, 尹延顺, 田栋伟, 等.不同质量等级酱香白酒中风味物质及差异性分析[J].中国酿造, 2024, 43(1):41-49.
WANG J L, YIN Y S, TIAN D W, et al.Analysis of flavor substances and differences of sauce-flavor Baijiu with different quality grades[J].China Brewing, 2024, 43(1):41-49.
[18] QIN D, DUAN J W, LI H H, et al.Characterization and comparison of the aroma-active compounds on different grades of sesame-flavor Baijiu by headspace solid-phase microextraction and gas chromatography-olfactometry-mass spectrometry[J].Food Science and Human Wellness, 2023, 12(1):79-88.
[19] 胡雪. 基于质谱结合化学计量学对白酒产地、香型和等级判别分析[D].自贡:四川轻化工大学, 2021.
HU X.Based on ms combined with stoichiometrydiscriminant analysis on origin, flavor type and quality grade of liquor[D].Zigong:Sichuan University of Science & Engineering,2021.
[20] 朱开宪, 胡雪, 邓静, 等.基于GC-MS技术对不同香型白酒的判别分析[J].中国酿造,2023,42(1):213-218.
ZHU K X, HU X, DENG J, et al.Discriminant analysis of different flavor-type Baijiu based on GC-MS[J].China Brewing, 2023,42(1):213-218.
[21] WANG J S, CHEN H, WU Y S, et al.Uncover the flavor code of strong-aroma Baijiu:Research progress on the revelation of aroma compounds in strong-aroma Baijiu by means of modern separation technology and molecular sensory evaluation[J].Journal of Food Composition and Analysis, 2022,109:104499.
[22] GONG J X, MA Y, LI L L, et al.Comparative characterization and contribution of key aroma compounds in the typical base liquor of Jiang-flavor Baijiu from different distributions in the Chinese Chishui River basin[J].Food Chemistry:X, 2023, 20:100932.
[23] THANGE U, SHUKLA V K, PUNHANI R, et al.Analyzing COVID-19 dataset through data mining tool “orange”[C].2021 2nd International Conference on Computation, Automation and Knowledge Management (ICCAKM).IEEE, 2021:198-203.
[24] MURPHY K, SCHÖLKOPF B, DEMŠAR J, et al.Orange:Data mining toolbox in Python[J].Journal of Machine Learning Research, 2013, 14(1):2349-2353.
[25] CORTES C, VAPNIK V.Support-vector networks[J].Machine Learning, 1995, 20(3):273-297.
Options
Outlines

/

〈 〉

Powered by Beijing Magtech Co. Ltd,.