基于信息融合的浓香型白酒发酵入窖条件研究  

Research on Cellar Inlet Condition of Luzhou Flavor Liquor Fermentation Based on Information Fusion

作　　者：周晓阳 姚毅 贾金玲[3,2] 陈博 

机构地区：[1]四川理工学院自动化与信息工程学院,四川自贡643000 [2]人工智能四川省重点实验室,四川自贡643000 [3]四川理工学院计算机学院,四川自贡643000

出　　处：《四川理工学院学报（自然科学版）》2017年第6期61-65,共5页Journal of Sichuan University of Science & Engineering(Natural Science Edition)

基　　金：四川省教育厅应用基础计划项目(2015JY0208)

摘　　要：浓香型白酒的发酵过程几乎不可控,因此入窖条件是白酒发酵重要的参考指标。在研究浓香型白酒入窖条件的基础上,采用了云模型与改进的D-S证据理论实现了对白酒发酵的入窖条件定量评估。通过资料和工人的经验验证,首先介绍了对白酒入窖情况影响较大的四种参数,分别为温度、酸度、淀粉含量、水分。通过Matlab仿真对入窖情况建立隶属度云模型,使得每一个参数都有其对应的隶属度函数。将已采集的样本参数通过云模型实现各个评判标准的隶属度情况,并利用改进的D-S证据理论对样本数据进行分析。经验证,对白酒的入窖状况分析可以达到比较准确的定量分析,大大降低了人工判别的主观性和随机性。The fermentation process of Luzhou flavor liquor is almost uncontrollable, therefore the cellar inlet condition is an important reference index for liquor fermentation. Based on the study of the cellar conditions of Luzhou flavor liquor, the cloud model and the improved D-S evidence theory are adopted to realize the quantitative evaluation of cellar inlet condition of liquor fermentation. After studying considerable data and experience of workers, four kinds of parameters affecting the condition of fermentation are introduced, which are temperature, acidity, starch content and moisture content. Through the Matlab simulation, the cloud model is established to make each parameter own its corresponding membership function. The sampled data is realized to evaluate the membership standard by the cloud model, and the improved D-S evidence theory is used to analyze the sampled data. It has been proved that the analysis of the cellar inlet condition of Luzhou flavor liquor can achieve an accurate quantitative analysis, meanwhile greatly reduces the subjectivity and randomness of artificial discrimination.

关 键 词：D-S证据理论云模型 入窖条件 信息融合 白酒发酵 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]