Research on Neural Network Temperature Control Algorithm in Wine Brewing

DOI: https://doi.org/10.62517/jbdc.202601134

Author(s)

Wang Laizhi1,2*, Zhang Erbing1, Feng Liyi1

Affiliation(s)

1Chongqing City Management College, Chongqing, China 2Intelligent Robotics Control and Interaction Engineering Research Center of Chongqing Education Commission of China, Chongqing, China *Corresponding Author.

Abstract

Baijiu brewing is an old craft, but it still lives and dies by one very modern thing: temperature control. When fermentation or distillation drifts off target, the result is familiar to anyone in a distillery—uneven quality, lower yield, and more steam and electricity burned than necessary. In many plants, temperature is still managed mainly by experience, which can be effective but also inconsistent and slow to respond. This paper examines neural-network-based temperature control for baijiu production. We sort out which temperature variables matter most in practice, build control rules around them (with the necessary mathematical expressions), and test the method against standard PID control. The PID baseline works, but the neural-network approach shows clearer gains in stability and performance in our comparison, and the experiments suggest it can be implemented on real equipment. Future work will focus on improving model tuning, making the control logic easier for operators to understand, and applying the approach across connected stages rather than optimizing each step separately.

Keywords

Baijiu Brewing; Temperature Control; Neural Network; Wine Body Quality

References

[1]Yu Zihan, Li Qingliang, Lu Yanxiang, et al. Research progress on automated and digital brewing processes for white liquor[J]. China Brewing. 2025,44(11):7-14. [2]Li Xianshu, Wang Yongzhong, Wu Junlong, et al. Feasibility study on brewing sauce-flavor liquor with high-temperature daqu in Xinjiang Yili [J]. Brewing. 2025,52(06):81-84 [3]Li Shenlong. Research on Development Trends of Intelligent Brewing Robots for Baijiu Based on Patent Big Data [J]. Robotics Technology and Applications. 2025(05):2-9. [4]Zhang J, Li YJ. Investigation on the Influence and Regulation of Temperature in Baijiu Brewing [J]. Food Safety Guide. 2021(28):165-166. [5]Jiang Xue, Su Yuanyuan, Cang Yipeng, et al. Research progress on the effects of fermentation temperature on Daqu and strong-aroma baijiu fermentation processes [J]. Brewing Science and Technology. 2025(08):106-110. [6]Wang XP. Influence and Control of Temperature in the Brewing Process of Strong Aroma Baijiu [J]. Brewing Science and Technology. 2018(06):88-90. [7]Zhang Xiaoming, Wu Dingchun, Yang Yi, et al. Research on Temperature Control of Winter Pit Loading of Fermented Grains in Mechanical Air-Drying Process for Strong Aroma Baijiu [J]. Brewing Science and Technology: 1-13. [8]Liao Qian. Research on Quality Grading and Blending Ratio Model for Small Qu Fragrant Type Baijiu Base Liquor [D]. Yunnan Agricultural University, 2024. [9]You Xiangtao. Key Technologies and Quality Characteristics of Baihe Multi-grain Baijiu Brewing [D]. Jishou University, 2023. [10]Hu Haicheng. Research on Online Segmentation and Reassembly Methods of Baijiu Based on Refractive Principles and Spectral Analysis [D]. Hebei University of Technology, 2023. [11]Xue Yuan. Research on Wine Extraction Equipment Based on Hops Image Classification for Baijiu [D]. Hebei University of Technology, 2021. [12]Li Pengbo. Research on Intelligent Wine Harvesting System Based on Baijiu Quality Grading [D]. Hebei University of Technology, 2021. [13]Yang YQ. Construction of a solid-state simulated fermentation system for baijiu and microbial community structure analysis during pile-up and pit fermentation of sauce-flavored baijiu [D]. Fujian Normal University, 2015. [14]Huang Xiaofeng. Research on Intelligent Blending System for China Distilled Spirits [D]. Zhejiang University, 2014.