摘要
本研究以茶鲜叶为原料,按照自然萎凋、远红外辐射3 h、远红外辐射6 h 3种工艺进行萎凋,测定主要滋味物质的含量,并采集萎凋样本的近红外光谱与图像数据,构建融合卷积注意力模块的一维卷积神经网络(onedimensional convolutional neural network with convolutional block attention module,CBAM-1DCNN)模型。结果显示,远红外辐射3 h条件下,萎凋15 h的酚氨比相比茶鲜叶下降了20.06%,感官得分最高。基于近红外光谱与机器视觉技术构建的CBAM-1DCNN模型比单一技术建立的模型判别能力更强,校正集准确率为99.11%,预测集准确率为96.00%。远红外辐射显著改变了主要滋味物质的含量,且通过近红外光谱与机器视觉技术可以实现红茶萎凋程度的快速判别。
In this study,fresh tea leaves were subjected to three withering processes:natural withering,far-infrared radiation for 3 h,and far-infrared radiation for 6 h.The contents of major taste substances were determined according to the Chinese national standards,and near infrared spectroscopy(NIR)and machine vision(MV)data of the withered samples were collected to build an improved one-dimensional convolutional neural network model integrated with a convolutional block attention module(CBAM-1DCNN).The results showed that the phenol/ammonia ratio after infrared radiation for 3 h followed by natural withering for 15 h decreased by 20.06%compared with fresh leaves,and this treatment group achieved the highest sensory score.The CBAM-1DCNN model based on the NIR-MV fused data exhibited stronger discrimination capacity than did the models based on the NIR and MV data with an accuracy of 99.11%for the calibration set and 96.00%for the prediction set.Far-infrared radiation significantly altered the contents of major taste substances,and NIR spectroscopy combined with MV enabled rapid discrimination of the withering degree of black tea.
作者
夏高帆
马圣洲
常惠林
李登珊
王雨
欧阳琴
XIA Gaofan;MA Shengzhou;CHANG Huilin;LI Dengshan;WANG Yu;OUYANG Qin(School of Food and Biological Engineering,Jiangsu University,Zhenjiang 212013,China;Zhenjiang Institute of Agricultural Sciences in Hill Area of Jiangsu Province,Zhenjiang 212400,China)
出处
《食品科学》
北大核心
2025年第24期9-17,共9页
Food Science
基金
江苏省自然科学基金项目(BK20250052)
中国博士后基金面上项目(2023M740628)。
关键词
红茶萎凋
远红外辐射
近红外光谱
机器视觉
卷积神经网络
black tea withering
far-infrared radiation
near infrared spectroscopy
machine vision
convolutional neural network
