Food and Fermentation Industries >

2025 , Vol. 51 >Issue 17: 143 - 149

DOI: https://doi.org/10.13995/j.cnki.11-1802/ts.042871

Deep learning-based grading framework for Wuliangye Baobaoqu

  • ZHAO Pengju ,
  • LU Yanping ,
  • SU Jian ,
  • ZHAO Dong ,
  • LEI Xuejun ,
  • LUO Qingchun ,
  • LI Xi ,
  • YANG Hao ,
  • WANG Xingming ,
  • ZHANG Zhu ,
  • DAI Songlin ,
  • ZHENG Jia
Expand
  • 1(Yibin Wuliangye Co. Ltd., Yibin 644000, China)
    2(Solid-state Fermentation Resource Utilization Key Laboratory of Sichuan Province, Yibin 644000, China)
    3(Key Laboratory of Wuliangye-flavor Liquor Solid-state Fermentation, China National Light Industry, Yibin 644000, China)

Received date: 2025-03-28

  Revised date: 2025-04-15

  Online published: 2025-09-29

Fold

Abstract

Baobaoqu is a crucial fermentation material in the brewing process of Nongxiangxing Baijiu Wuliangye.Its precise grading plays a significant role in stabilizing brewing quality and improving production efficiency.However, traditional grading methods mainly depend on human expertise, resulting in low efficiency and long training periods to develop experienced engineers.This reliance introduces subjectivity and compromises the robustness of grading outcomes.This study presents a deep learning-based grading framework for Wuliangye Baobaoqu, comprising two core components:cross-section detection and classification.The framework is designed to digitize and streamline the grading process, supporting engineers in improving grading precision and operational efficiency.To overcome the limitations of manual assessment, a dedicated Baobaoqu image dataset was constructed, and a two-stage deep neural network framework was developed.The first stage utilizes an object detection model to identify Baobaoqu cross-sections, and the second stage employs an image classification model for grading decisions.Experimental results demonstrate that the classification performance of the proposed method is comparable to that of experienced engineers, providing technical support for the intelligent development of the Baijiu brewing industry.

Key words： Nongxiangxing Baijiu; Baobaoqu; cross-section recognition; Baobaoqu grading; deep learning; computer vision

Cite this article

ZHAO Pengju , LU Yanping , SU Jian , ZHAO Dong , LEI Xuejun , LUO Qingchun , LI Xi , YANG Hao , WANG Xingming , ZHANG Zhu , DAI Songlin , ZHENG Jia . Deep learning-based grading framework for Wuliangye Baobaoqu[J]. Food and Fermentation Industries, 2025 , 51(17) : 143 -149 . DOI: 10.13995/j.cnki.11-1802/ts.042871

References

[1] 沈怡方. 白酒生产技术全书[M].北京:中国轻工业出版社, 2015.
SHEN Y F.Encyclopedia of Baijiu Production Technology[M].Beijing:China Light Industry Press, 2011.
[2] 赵东, 杨韵霞.探秘五粮液:酿造·品质·科技[M].北京:化学工业出版社, 2022.
ZHAO D, YANG Y X.The Secrets of Wuliangye:Brewing, Quality, Technology[M].Beijing:Chemical Industry Press, 2022.
[3] 黄平, 王子豪, 郑佳, 等.浓香型白酒大曲微生物群落结构研究进展[J].微生物学通报, 2023, 50(7):3170-3186.
HUANG P, WANG Z H, ZHENG J, et al.Research progress in microbial community structure in Nongxiangxing Daqu[J].Microbiology China, 2023, 50(7):3170-3186.
[4] 杨雯净, 李煜滋, 黄丹, 等.浓香型白酒大曲产α-淀粉酶芽孢杆菌的分离鉴定及代谢特性研究[J].中国酿造, 2025, 44(2):80-86.
YANG W J, LI Y Z, HUANG D, et al.Isolation, identification and metabolic characteristic of α-amylase-producing Bacillus from strong-flavor Baijiu Daqu[J].China Brewing, 2025, 44(2):80-86.
[5] 赵东, 张晓莲, 陈双为, 等.五粮液“包包曲” 的特点及常见病害的剖析防治[J].酿酒科技, 2015(12):53-56.
ZHAO D, ZHANG X L, CHEN S W, et al.Features of wrapped starter of Wuliangye and prevention & control of its common disease[J].Liquor-Making Science & Technology, 2015(12):53-56.
[6] 钟莉, 郑佳, 彭志云, 等.五粮液“包包曲” 的生产特点和展望[J].酿酒科技, 2017(6):37-43.
ZHONG L, ZHENG J, PENG Z Y, et al.Production and development prospects of Wuliangye bulgy Daqu[J].Liquor-Making Science & Technology, 2017(6):37-43.
[7] 郑佳, 赵东, 何张兰, 等.利用GC×GC-TOFMS鉴定包包曲中的游离香气成分[J].酿酒科技, 2021(11):17-24;30.
ZHENG J, ZHAO D, HE Z L, et al.Identification of free aroma compounds in bulgy Daqu by GC×GC-TOFMS[J].Liquor-Making Science & Technology, 2021(11):17-24;30.
[8] 罗青春, 郑佳, 赵东, 等.浓香型白酒中优势乳酸菌和酵母菌间的相互关系[J].应用与环境生物学报, 2019, 25(5):1192-1199.
LUO Q C, ZHENG J, ZHAO D, et al.Interaction between dominant lactic acid bacteria and yeasts strains in strong aroma Baijiu[J].Chinese Journal of Applied and Environmental Biology, 2019, 25(5):1192-1199.
[9] 雷学俊, 张霞, 刘多涛, 等.包包曲及制曲环境中可培养霉菌的分离与鉴定[J].酿酒科技, 2019(12):17-22.
LEI X J, ZHANG X, LIU D T, et al.Isolation and identification of cultivable mold strains from bulgy Daqu and Daqu-making environment[J].Liquor-Making Science & Technology, 2019(12):17-22.
[10] 张倩, 韩保林, 李子健, 等.浓香型白酒包包曲微生物种群多样性及形成机制[J].食品与发酵工业, 2021, 47(18):99-106.
ZHANG Q, HAN B L, LI Z J, et al.Diversity and formation mechanism of the microflora in strong flavor Baijiu Baobaoqu[J].Food and Fermentation Industries, 2021, 47(18):99-106.
[11] 陈勇, 林涵瑞, 陈晓茹, 等.川派浓香型白酒大曲的典型产区差异性分析[J].中国酿造, 2024, 43(11):34-40.
CHEN Y, LIN H R, CHEN X R, et al.Difference analysis of Sichuan strong-flavor Baijiu Daqu in typical producing areas[J].China Brewing, 2024, 43(11):34-40.
[12] REN S Q, HE K M, GIRSHICK R, et al.Faster R-CNN:Towards real-time object detection with region proposal networks[C].IEEE Transactions on Pattern Analysis and Machine Intelligence.IEEE, 2017:1137-1149.
[13] LIN T Y, GOYAL P, GIRSHICK R, et al.Focal loss for dense object detection[C].2017 IEEE International Conference on Computer Vision (ICCV).IEEE, 2017:2999-3007.
[14] LECUN Y, BENGIO Y, HINTON G.Deep learning[J].Nature, 2015, 521(7553):436-444.
[15] KRIZHEVSKY A, SUTSKEVER I, HINTON G E.ImageNet classification with deep convolutional neural networks[C].Annual Conference on Neural Information Processing Systems.USA:Stateline, 2012.
[16] ZHAO P J, LIAO W J, HUANG Y L, et al.Intelligent design of shear wall layout based on attention-enhanced generative adversarial network[J].Engineering Structures, 2023, 274:115170.
[17] 丁浩晗, 田嘉伟, 谢祯奇, 等.机器学习和大数据在食品领域的应用[J].食品与发酵工业, 2024, 50(24):353-361.
DING H H, TIAN J W, XIE Z Q, et al.Applications of machine learning and big data in food industry[J].Food and Fermentation Industries, 2024,50(24):353-361.
[18] ZHOU L, ZHANG C, LIU F, et al.Application of deep learning in food:A review[J].Comprehensive Reviews in Food Science and Food Safety, 2019, 18(6):1793-1811.
[19] KAMILARIS A, PRENAFETA-BOLDÚ F X.Deep learning in agriculture:A survey[J].Computers and Electronics in Agriculture, 2018, 147:70-90.
[20] LUO T Y, ZHAO J Y, GU Y J, et al.Classification of weed seeds based on visual images and deep learning[J].Information Processing in Agriculture, 2023, 10(1):40-51.
[21] 张茹, 张奋楠, 周星宇, 等.基于机器视觉的生鲜牛肉冷藏时间识别研究[J].食品与发酵工业, 2022, 48(18):75-80.
ZHANG R, ZHANG F N, ZHOU X Y, et al.Identification of the refrigerated time for chilled beef based on machine vision[J].Food and Fermentation Industries, 2022, 48(18):75-80.
[22] LIN T Y, MAIRE M, BELONGIE S, et al.Microsoft COCO:Common objects in context[C].Computer Vision- ECCV 2014.Cham:Springer, 2014:740-755.
[23] HE K M, ZHANG X Y, REN S Q, et al.Deep residual learning for image recognition[C].2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE, 2016:770-778.
[24] LIU Z, MAO H Z, WU C Y, et al.A ConvNet for the 2020 s[C].2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE, 2022:11966-11976.
[25] TAN M, LE Q.EfficientNet:Rethinking model scaling for convolutional neural networks[C].Proceedings of Machine Learning Research.USA:Long Beach, 2019.
Options
Outlines

/

〈 〉

Powered by Beijing Magtech Co. Ltd,.