传统曲房在大曲发酵过程中受曲房空间、堆曲并房的影响,不同位置之间存在较大的温湿度差,最大温差可达22.90 ℃,最大湿度差可达41.40%相对湿度(relative humidity,RH),严重影响大曲的质量和一致性。T-S模糊神经网络控制具有响应速度快、超调量小等特点,能有效解决温湿度调节延迟的问题,从而使曲房内各区域温湿度保持均匀。因此,该文提出了将T-S模糊神经网络控制与曲房控制系统相结合的方法来调控曲房温湿度。搭建曲房的硬件与软件系统,设计T-S模糊神经网络控制器,并利用粒子群算法优化该控制器的参数,对控制器进行仿真和运用控制系统进行实际测试。结果表明,该控制器工作稳定,频率响应快;控制系统能够对曲房的温湿度进行实时测控,使发酵过程中不同发酵部位之间的最大温度差降低至6.30 ℃,最大湿度差降低至8.69%RH。通过该控制系统实现了大曲发酵过程中曲房内部各区域温湿度保持均匀,保证了大曲质量的一致性。
The space of the Daqu workshop, the stacking and combining of the Daqu, as well as other factors all had an impact on the fermentation of Daqu in the traditional Daqu workshop. As a result, there was a significant temperature and humidity difference between Daqu in various positions, with a maximum temperature difference of 22.90 ℃ and a maximum relative humidity difference of 41.40%. This had a significant impact on the quality and consistency of Daqu. T-S fuzzy neural network control, with its quick response speed and modest overshoot, could effectively solve the problem of temperature and humidity adjustment delay and ensure that each region of the Daqu workshop maintains uniform temperature and humidity. As a result, this research presented a method for controlling the temperature and humidity of the Daqu workshop by combining T-S fuzzy neural network control with the Daqu workshop control system. First, the hardware and software system of the Daqu workshop were built in this study. Second, the T-S fuzzy neural network controller was built, and the particle swarm algorithm was utilized to optimize the controller's parameters. Finally, this study simulated the controller and uses the control system for actual testing. The results demonstrated the stability and quick frequency response of the controller. The control system is able to monitor and adjust the temperature and humidity of the Daqu workshop in real time, resulting in a maximum temperature difference of 6.30 ℃ and a maximum relative humidity difference of 8.69% between the various fermentation parts of the fermentation process. Through the use of this control system, the temperature and humidity of every space inside the Daqu workshop were kept constant while Daqu was fermenting, guaranteeing the consistency of Daqu quality.
[1] 白云松, 田建平, 黄海飞, 等.大曲发酵过程中曲房环境温度的数值分析[J].中国酿造, 2019, 38(11):165-169.
BAI Y S, TIAN J P, HUANG H F, et al.Numerical analysis of ambient temperature during Daqu fermentation[J].China Brewing,2019, 38(11):165-169.
[2] 廖俊杰, 胡光忠, 夏秋, 等.基于改进SSA优化预测模型的大曲发酵湿度监控系统[J].食品与机械, 2022, 38(9):93-97.
LIAO J J, HU G Z, XIA Q, et al.Monitoring system of daqu fermentation humidity based on improved SSA optimization prediction model[J].Food & Machinery, 2022, 38(9):93-97.
[3] 候山山, 黄丹平, 张芯豪, 等.基于LabVIEW智能曲房测控系统研发[J].食品工业, 2018, 39(5):234-238.
HOU S S, HUANG D P, ZHANG X H, et al.Research and development of measurement and control system for intel igent fermentation room based on LabVIEW[J].The Food Industry, 2018, 39(5):234-238.
[4] 李修荣, 高瑜翔, 罗爱民.酒曲房温湿度检测系统[J].测控技术, 2014, 33(11):50-52;56.
LI X R, GAO Y X, LUO A M.Detection system of distiller’s yeast temperature and humidity[J].Measurement & Control Technology, 2014, 33(11):50-52;56.
[5] 赵殿臣, 马连松, 董福新, 等.温湿度无线控制自动开关窗技术在曲房的开发应用[J].酿酒, 2013, 40(1):42-44.
ZHAO D C, MA L S, DONG F X,et al.Temperature and humidity control automatic switch window technique in yeastroom applications[J].Liquor Making, 2013, 40(1):42-44.
[6] 肖晓. 白酒曲房的温度场及智能控制系统应用研究[D].成都:电子科技大学, 2021.
XIAO X. Research on temperature field and intelligent control system application of liquor qu Fang[D].Chengdu: University of Electronic Science and Technology of China, 2021.
[7] 李光尧, 曹阳, 刘维岗, 等.基于T-S模糊神经网络的新型烟叶烤房控制系统研究[J].甘肃农业大学学报, 2018, 53(5):217-224.
LI G Y, CAO Y, LIU W G, et al.Study on new tobacco bulk curing barn control system based on T-S neuro-fuzzy approach[J].Journal of Gansu Agricultural University, 2018, 53(5):217-224.
[8] 齐霁, 李威, 宁亮, 等.基于模糊神经网络的电网调度自动化控制系统[J].制造业自动化, 2022, 44(1):118-122.
QI J, LI W, NING L, et al.Power grid dispatching automation control system based on fuzzy neural network[J].Manufacturing Automation, 2022, 44(1):118-122.
[9] 和朋飞. 基于模糊神经网络控制的窑炉温控系统设计[D].石家庄:河北科技大学, 2019.
HE P F. Design of kiln temperature control system based on fuzzy neural network control[D].Shijiazhuang: Hebei University of Science and Technology, 2019.
[10] 李亨. 基于模糊神经网络的植物工厂温湿度控制研究[D].天津:天津职业技术师范大学, 2019.
LI H.Research on temperature and humidity control of plant factory based on fuzzy neural network[D].Tianjin:Tianjin University of Technology and Education, 2019.
[11] WU J A, YANG S X, TIAN F C.An adaptive neuro-fuzzy approach to bulk tobacco flue-curing control process[J].Drying Technology, 2017, 35(4):465-477.
[12] 张彩云. 基于改进PSO算法的模糊神经网络研究[D].哈尔滨:哈尔滨理工大学, 2014.
ZHANG C Y.Research on fuzzy neural network based on improved PSO algorithm[D].Harbin:Harbin University of Science and Technology, 2014.
[13] 李浩楠, 刘勇.模糊神经网络的优化及其应用[J].哈尔滨理工大学学报, 2020, 25(6):142-149.
LI H N, LIU Y.Optimization and application of fuzzy neural network[J].Journal of Harbin University of Science and Technology, 2020, 25(6):142-149.
[14] 彭辉, 曾碧.基于模糊神经网络的智能温室环境控制方案[J].农机化研究, 2017, 39(6):43-49.
PENG H, ZENG B.Intelligent greenhouse environment control based on fuzzy neural network[J].Journal of Agricultural Mechanization Research, 2017, 39(6):43-49.
[15] ZHANG W, QIAO J F.Multi variable direct self-organizing fuzzy neural network control for wastewater treatment process[J].Asian Journal of Control, 2020, 22(2):716-728.
[16] 邢希君, 宋建成, 吝伶艳.基于双模糊控制器的温室智能控制系统设计[J].北方园艺, 2018(18):62-68.
XING X J, SONG J C, LIN L Y.Design of intelligent control system in greenhouse based on double fuzzy controller[J].Northern Horticulture, 2018(18):62-68.
[17] 冯佳婷, 陆震鸣, 时伟, 等.不同培养温度对大曲微生物群落结构、酶活及挥发性化合物的影响[J].应用与环境生物学报, 2021, 27(3):760-767.
FENG J T, LU Z M, SHI W, et al.Effects of different culture temperatures on microbial community structure,enzyme activity,and volatile compounds in Daqu[J].Chinese Journal of Applied and Environmental Biology, 2021, 27(3):760-767.
[18] 刘伟. 基于模糊神经网络的啤酒灌装精度控制技术[J].食品与机械, 2022, 38(4):104-108.
LIU W.Control technology of beer filling accuracy based on fuzzy neural network[J].Food & Machinery, 2022, 38(4):104-108.
[19] ZHOU R M, ZHANG L X, FU C X, et al.Fuzzy neural network PID strategy based on PSO optimization for pH control of water and fertilizer integration[J].Applied Sciences, 2022, 12(15):7383.
[20] JIA Y J.Design of an intelligent greenhouse remote control system based on a fuzzy neural network[J].International Journal of Automation Technology, 2021, 15(2):243-248.
