摘要
基于近红外(near-infrared,NIR)以及可见光(visible,VIS)高光谱技术快速评估窖泥总酸的分布。化学计量法结合计算机技术分析窖泥在近红外以及可见光波段下的高光谱数据,结合总酸实测值建立偏最小二乘回归、最小二乘支持向量机2种预测模型。根据模型的表现性能,最优模型为可见光区域下的SNV-SPA-SVM模型,训练集的决定系数Rcal2为0.9985,均方根误差为0.0049 g/kg,测试集的决定系数Rpre2为0.9991,均方根误差为0.0038 g/kg,并计算得到不同窖龄、不同层次窖泥总酸度的可视化分布图。结果表明,将高光谱技术应用于窖泥总酸的快速无损检测是可行的,此技术帮助白酒企业快速发现问题,及时调整工艺,防止窖泥酸化和老化现象的发生,同时为中国白酒行业传统技术的转型升级以及智能化在线实时监控窖泥质量提供了有力的技术支持。
The total acid distribution in pit mud was rapidly assessed using visible(VIS)/nearinfrared(NIR)hyperspectral technology.The hyperspectral data of pit mud in the near-infrared and visible wavebands were analyzed by stoichiometry combined with computer technology.Two prediction models,the partial least squares regression(PLSR)and a least squares-support vector machine(LSSVM)were constructed based on these measurements.The model performances indicated that the optimal model was the Standard Normal Variable Correction-Successive Projection Algorithm-SVM(SNVSPA-SVM)in the visible region.The coefficient of determination Rcal2 of the calibration set was0.9985,root mean square error of calibration(RMSEC)was 0.0049 g/kg,and the coefficient of the determination Rpre2 of the prediction set was 0.9991.Furthermore,the root mean square error of prediction(RMSEP)was 0.0038 g/kg and a visual distribution map of the total acid in pit mud was obtained.The results showed that it was feasible to employ hyperspectral technology for rapid and non-destructive detection of the total acid in pit mud,enabling baijiu enterprises to identify problems quickly,adjust processes in a timely manner,prevent pit mud acidification and aging,as well as provide strong technical support for the transformation and upgrading of traditional technology in the Chinese baijiu industry and intelligent online real-time monitoring of pit mud quality.
作者
朱敏
孙婷
白直真
罗惠波
田建平
黄丹
ZHU Min;SUN Ting;BAI Zhizhen;LUO Huibo;TIAN Jianping;HUANG Dan(College of Biotechnology Engineering,Sichuan University of Science and Engineering,Yibin 644000,China;College of Mechanical Engineering,Sichuan University of Science and Engineering,Yibin 644000,China)
出处
《食品与发酵工业》
CAS
CSCD
北大核心
2020年第8期111-117,共7页
Food and Fermentation Industries
基金
四川省科技厅重点研发计划(重大科技专项)项目(2018GZ0112)
四川轻化工大学研究生创新基金资助项目(Y2018069)。
关键词
VIS/NIR高光谱技术
窖泥
总酸
快速无损检测
可视化
VIS/NIR hyperspectral technology
pit mud
total acid
rapid and non-destructive detection
visualization
