浏览全部资源
扫码关注微信
1.浙江中烟工业有限责任公司技术中心,浙江 杭州 310024
2.上海创和亿电子科技发展有限公司,上海 200084
3.浙江中烟工业有限责任公司杭州卷烟厂,浙江 杭州 310024
毕一鸣,博士,高级工程师,研究方向:卷烟产品数字化设计及近红外光谱分析技术,E-mail:biyiming@zjtobacco.com
收稿日期:2024-06-18,
修回日期:2024-07-25,
录用日期:2024-08-08,
纸质出版日期:2025-03-15
移动端阅览
李石头,廖付,吴继忠,张军,徐梦瑶,丁伟,李永生,李淑彪,何文苗,王辉,毕一鸣.基于卷积神经网络组合算法的卷烟牌号在线分类识别研究[J].分析测试学报,2025,44(03):514-520.
LI Shi-tou,LIAO Fu,WU Ji-zhong,ZHANG Jun,XU Meng-yao,DING Wei,LI Yong-sheng,LI Shu-biao,HE Wen-miao,WANG Hui,BI Yi-ming.Research on Online Classification and Recognition of Cigarette Brands Based on Convolutional Neural Network Combination Algorithm[J].Journal of Instrumental Analysis,2025,44(03):514-520.
李石头,廖付,吴继忠,张军,徐梦瑶,丁伟,李永生,李淑彪,何文苗,王辉,毕一鸣.基于卷积神经网络组合算法的卷烟牌号在线分类识别研究[J].分析测试学报,2025,44(03):514-520. DOI: 10.12452/j.fxcsxb.240618143.
LI Shi-tou,LIAO Fu,WU Ji-zhong,ZHANG Jun,XU Meng-yao,DING Wei,LI Yong-sheng,LI Shu-biao,HE Wen-miao,WANG Hui,BI Yi-ming.Research on Online Classification and Recognition of Cigarette Brands Based on Convolutional Neural Network Combination Algorithm[J].Journal of Instrumental Analysis,2025,44(03):514-520. DOI: 10.12452/j.fxcsxb.240618143.
为探究烟丝在线近红外光谱与卷烟牌号间的关系,提出了一种基于ResNeXt18-CNN-LightGBM混合模型的卷烟牌号分类识别方法。首先对采集的烟丝样本在线光谱数据进行预处理,并利用ResNeXt18网络模型对预处理后的光谱进行初次特征提取。然后将提取后的特征输入自定义的3层卷积神经(CNN)网络模型中,进行二次特征提取。最后将CNN提取的特征代入LightGBM分类器进行牌号分类训练。结果表明,ResNeXt18-CNN-LightGBM模型中烟丝牌号分类的准确率达97%。相较于传统的单个化学计量学算法,该文提出的基于卷积神经网络组合算法的卷烟牌号分类识别方法简单易行、准确性高、稳定性好,可应用于卷烟工业生产中卷烟牌号的在线识别,对卷烟品牌管理、生产质量评价及卷烟质量管控具有重要意义。
To explore the relationship between tobacco strip online near-infrared spectra and cigarette brand identification,a cigarette brand classification method based on the ResNeXt18-CNN-LightGBM hybrid model is proposed. Firstly,the collected tobacco strip sample online spectral data are preprocessed,and the ResNeXt18 network model is used to extract initial features from the preprocessed spectra. Then,the extracted features are input into a custom 3-layer CNN network model for secondary feature extraction. Finally,the features extracted by the CNN are fed into a LightGBM classifier for brand classification training. The results show that the classification accuracy of tobacco strip brand identification in the ResNeXt18-CNN-LightGBM model reaches 97%. Compared with traditional single chemometrics algorithms,the proposed cigarette brand classification method based on a convolutional neural network combination algorithm is simple,accurate,and stable. It can be applied to the online identification of cigarette brands in cigarette manufacturing,with significant implications for cigarette brand management,production quality evaluation,and cigarette quality control.
Pan X , Liu H , Wang H , Liu J , He Y L , Huang W C , Qiu C G . J. Instrum. Anal. (潘曦,刘辉,王昊,刘静,何昀潞,黄伟初,邱昌桂. 分析测试学报), 2020 , 39 ( 11 ): 1385 - 1391 .
Pan X , Li R , Wei M , Wei Q , Qiu C G . Food Mach . (潘曦,李冉,魏敏,卫青,邱昌桂. 食品与机械), 2022 , 38 ( 7 ): 85 .
Cao M L . Discrimination of Cigarettes Brands Based on Their Routine Testing Chemical Indicators and Near Infrared Spectra. Shanghai:East China University of Science and Technology (曹妙玲. 基于卷烟常规化学检测数据及近红外信息的卷烟牌号识别. 上海:华东理工大学),2012 .
Chu X L , Chen P , Li J Y , Liu D , Xu Y P . J. Instrum. Anal . (褚小立,陈瀑,李敬岩,刘丹,许育鹏. 分析测试学报), 2020 , 39 ( 10 ): 1181 - 1188 .
Lu M Y , Yang K , Song P F , Shu R X , Wang L P , Yang Y Q , Liu H , Li J H , Zhao L L , Zhang Y H . Spectrosc . Spectral Anal. (鲁梦瑶,杨凯,宋鹏飞,束茹欣,王萝萍,杨玉清,刘慧,李军会,赵龙莲,张晔晖. 光谱学与光谱分析), 2018 , 38 ( 12 ): 3724 .
LE B T , Xiao D , Mao Y C , Song L , He D K , Liu S J . Spectrosc . Spectral Anal. (LE Ba Tuan ,肖冬,毛亚纯,宋亮,何大阔,刘善军. 光谱学与光谱分析), 2018 , 38 ( 7 ): 2107 .
Bao G H , Huang Y X . Autom . Electr. Power Syst . (鲍光海,黄逸欣. 电力系统自动化), 2023 , 47 ( 13 ): 110 .
He Z F , Huang J X , Liu Q , Zhang Y H . Trans . Chin. Soc. Agric. Mach . (何自芬,黄俊璇,刘强,张印辉. 农业机械学报), 2021 , 52 ( 8 ): 221 .
Wang L , Huan K W , Liu X X , Yue D , Han F D , Zhang W J . Chin. J. Anal. Chem. (王磊,宦克为,刘小溪,岳丹,韩丰地,张文捷.分析化学), 2022 , 50 ( 12 ): 1918 .
Yu S , Huan K W , Wang L , Liu X X , Han X Y . Chin. J. Anal. Chem . 于水 , 宦克为 , 王磊 , 刘小溪 , 韩雪艳 . 分析化学) , 2024 ,( 5 ): 695 - 705 .
Zhang W J , Jiao A R , Tian J , Wang X J , Wang B , Xu X X . J. Instrum. Anal. (张文杰,焦安然,田静,王晓娟,王斌,徐晓轩. 分析测试学报), 2021 , 40 ( 7 ): 1062 - 1067 .
Wang J , Yi Z P , Yue L L , Dong H F , Pan J C , Bu Y D . Spectrosc . Spectral Anal. (王晶,衣振萍,岳丽丽,董慧芬,潘景昌,卜育德.光谱学与光谱分析) , 2019 , 39 ( 7 ): 2288 - 2292 .
Wang Y D , Jia J W , Tan W J , Lei M . J. Instrum. Anal. (王亚栋,贾俊伟,谭韦君,雷萌. 分析测试学报), 2024 , 43 ( 4 ): 607 - 613 .
Song J P , Liang K , Zhang C , Mei X M , Jiang P F , Yuan R . J. Instrum. Anal. (宋金鹏,梁琨,张驰,梅秀明,蒋鹏飞,袁锐.分析测试学报), 2023 , 42 ( 7 ): 784 - 793 .
Huang H X , Li Y X , Zhang Z Y . Forest. Eng.(黄海霞 , 李耀翔 , 张哲宇 . 森林工程) , 2023 ,( 6 ): 164 - 171 .
Wu J Z , Shi Y D , Huang H , Li X R . J. Instrum. Anal. (吴继忠,时艺丹,黄慧,厉小润. 分析测试学报), 2023 , 42 ( 9 ): 1112 - 1118 .
0
浏览量
28
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构