摘要
针对现有葡萄酒检测技术无法快速、高效鉴别葡萄酒品质的问题,基于无需建立标签、调参简单的聚类算法,提出了一种利用激光诱导荧光技术获取葡萄酒光谱信息的方法,实现了酒样鉴别。选取三个品牌、两个年份的四个葡萄酒样本,在同一酒精度的前提下,与水进行1∶10体积配比后,对每个酒样采集100个光谱信息。利用K-均值、自组织竞争网络和自组织特征映射神经网络三个聚类算法进行酒样的鉴别,实验结果表明:在光谱信息分析中,三个聚类算法均表现出较优越的性能,识别准确率均达到99%以上,自组织特征映射神经网络的分类准确率更是达到了100%,平均用时5.875 s,具有较高的鲁棒性和泛化能力。研究结论证明聚类算法对葡萄酒品质的检测是切实可行的。
Aiming at the problem that the existing wine detection technology cannot quickly and efficiently identify the quality of wine,this paper proposes a method to capture the spectral information of wine samples by laser-induced fluorescence technology,which is based on the clustering algorithm without label build and complex tuning.Four wine samples from three brands and two vintages were selected.After being mixed with water at 1∶10,under the premise of the same alcohol content,100 spectral informations were collected for each wine sample.We used K-means,self-organizing competition network and self-organizing feature mapping neural network(SO-FMNN)to identify wine samples.The experimental results show that the three clustering algorithms have superior performances in spectral information analysis,and the recognition accuracy rate can reach more than 99%.The classification accuracy rate of SO-FMNN is even 100%,the average time is 5.875 s,and it has high robustness and generalization ability.It is verified that the clustering algorithm for wine quality detection is feasible.
作者
周孟然
王骋
胡锋
来文豪
卞凯
Zhou Mengran;Wang Cheng;Hu Feng;Lai Wenhao;Bian Kai(College of Electrical and Information Engineering,Anhui University of Science and Technology,Huainan,Anhui 232001,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2021年第16期518-524,共7页
Laser & Optoelectronics Progress
基金
国家重点研发计划(2018YFC0604503)
国家“十二五”科技支撑计划重点项目(2013BAK06B01)
安徽省科技重大专项(201903a07020013)
安徽省自然科学基金青年项目(1808085QE157)。
关键词
光谱学
激光诱导荧光
聚类算法
荧光光谱识别
葡萄酒
自组织特征映射神经网络
spectroscopy
laser-induced fluorescence
clustering algorithm
fluorescence spectrum recognition
wine
self-organizing feature mapping neural network
