摘要
利用傅里叶近红外漫反射光谱技术结合偏最小二乘法(PLS),建立了黄酒酒醅中酒精度的快速定量检测模型。通过优化波数范围和维数,选择最佳光谱预处理方法,在建立的酒醅酒精度的模型中,用相关系数(R)、交叉验证均方差(RMSECV)和相对分析误差(RPD)衡量模型的预测精度和稳定性。模型的R值达0.9912,RMSECV值为0.347,RPD为7.16,说明该模型有较好的预测能力。因此,近红外光谱法可用于发酵过程中黄酒酒醅的快速检测,对于保障黄酒食品安全质量、提高工作效率具有重要意义。
Based on Fourier transform near-infrared diffuse reflectance spectroscopy and partial least square analysis(PLS),we established the quantitative model for rapid determination of alcohol content in fermented grains of Huangjiu.By comparing different wavenumber regions and ranks,the optimal pretreatment method was obtained.The accuracy and stability of the model was evaluated by the correlation coefficient(R),the root mean square error of cross validation(RMSECV)and the relative predictive deviation(RPD).The R value was 0.9912,the RMSECV value was 0.347,and the RPD value was 7.16.The model had good prediction performance,and could be applied in the rapid determination of fermented grains of Huangjiu.This study is of great significance in guaranteeing the safety and quality of Huangjiu with high efficiency.
作者
龚辉
夏乔浪
黄媛媛
GONG Hui;XIA Qiaolang;HUANG Yuanyuan(Technical Center of Shanghai Jinfeng Winery Co.Ltd.,Shanghai 201501,China)
出处
《酿酒科技》
2021年第7期125-129,共5页
Liquor-Making Science & Technology
基金
上海黄酒工程研究技术中心能力提升项目(20DZ2281500)。
关键词
近红外漫反射光谱
黄酒
酒醅
快速检测
模型
near-infrared spectroscopy
Huangjiu
fermented grains
rapid determination
model
