浏览全部资源
扫码关注微信
1.云南烟叶复烤有限责任公司宣威复烤厂,云南 宣威 655400
2.云南烟叶复烤有限责任公司技术中心,云南 昆明 650000
3.浙江中烟工业有限责任公司技术中心,浙江 杭州 310024
4.浙江中烟工业有限责任公司物资部,浙江 杭州 310002
5.云南铭帆科技有限公司,云南 昆明 650051
毕一鸣,博士研究生,高级工程师,研究方向:卷烟产品设计,E-mail:biyiming@zjtobacco.com
收稿日期:2024-08-26,
修回日期:2024-09-30,
录用日期:2024-10-22,
纸质出版日期:2025-03-15
移动端阅览
杨泽会,吴箭,李瑞东,郝贤伟,吕小芳,田雨农,张志成,吴灵通,李正莹,夏春艳,张恺,徐梦瑶,毕一鸣,夏自麟.卷积桥接孪生自编码器的近红外光谱转移研究[J].分析测试学报,2025,44(03):471-478.
YANG Ze-hui,WU Jian,LI Rui-dong,HAO Xian-wei,LÜ Xiao-fang,TIAN Yu-nong,ZHANG Zhi-cheng,WU Ling-tong,LI Zheng-ying,XIA Chun-yan,ZHANG Kai,XU Meng-yao,BI Yi-ming,XIA Zi-lin.Study on Near Infrared Spectrum Transfer of Convolutional Bridged Twin Denoising Reduction Autoencoder[J].Journal of Instrumental Analysis,2025,44(03):471-478.
杨泽会,吴箭,李瑞东,郝贤伟,吕小芳,田雨农,张志成,吴灵通,李正莹,夏春艳,张恺,徐梦瑶,毕一鸣,夏自麟.卷积桥接孪生自编码器的近红外光谱转移研究[J].分析测试学报,2025,44(03):471-478. DOI: 10.12452/j.fxcsxb.240826343.
YANG Ze-hui,WU Jian,LI Rui-dong,HAO Xian-wei,LÜ Xiao-fang,TIAN Yu-nong,ZHANG Zhi-cheng,WU Ling-tong,LI Zheng-ying,XIA Chun-yan,ZHANG Kai,XU Meng-yao,BI Yi-ming,XIA Zi-lin.Study on Near Infrared Spectrum Transfer of Convolutional Bridged Twin Denoising Reduction Autoencoder[J].Journal of Instrumental Analysis,2025,44(03):471-478. DOI: 10.12452/j.fxcsxb.240826343.
近红外光谱仪器间的差异使得不同仪器共用预测模型变得困难,限制了技术的推广应用。为减少光谱偏移后重新建立预测模型的难度,该文提出了一种基于卷积桥接孪生降噪自编码器(CBSDAE)的近红外光谱模型转移方法。该方法利用卷积降噪自编码器(CDAE)的编码器提取光谱的隐藏特征,并通过卷积神经网络拟合从机与源机光谱隐藏特征的转移映射函数,最后通过卷积降噪自编码器的解码器重构转移后的光谱。为验证其有效性,该文对烟叶近红外光谱图及化学成分预测结果进行评估。结果显示,CBSDAE方法转移后的从机光谱与源机光谱高度重合。相比于直接标准化(DS)、分段直接标准化(PDS)、光谱差值校正算法(SSC)、Shenk’s算法、卷积神经网络(CNN)、深度自编码器算法,使用该方法进行光谱转移后,预测烟碱的平均相对误差分别下降了6.42%、5.84%、5.32%、5.24%、4.35%和4.85%,预测的均方根误差(RMSEP)和相关系数也均优于上述方法。结果表明该方法是一种有效的模型转移方法。
The differences between near infrared(NIR) spectrometers make it challenging to share prediction models across different instruments,limiting the widespread application of this technology. To reduce the difficulty of rebuilding prediction models after spectral shift,this paper proposes a near infrared spectral model transfer method based on a convolutional bridged twin denoising autoencoder(CBSDAE). This method utilizes the encoder of the convolutional denoising autoencoder(CDAE) to extract the hidden features of the spectra and fits a transfer mapping function between the hidden spectral features of the target and source instruments using a convolutional neural network(CNN). Finally,the transferred spectra are reconstructed through the decoder of the CDAE. To validate its effectiveness,evaluations were conducted from two perspectives:NIR spectra of tobacco leaves and chemical component prediction results. The findings show that the spectra from the target instrument closely overlap with those from the source instrument after transfer using the CBSDAE method. Compared with direct standardization(DS),piecewise direct standardization(PDS),spectral subtraction correction(SSC),Shenk’s algorithm,CNN and deep autoencoder,the average relative error in nicotine prediction decreased by 6.42%,5.84%,5.32%,5.24%,4.35% and 4.85%,respectively,after applying the CBSDAE method for spectral transfer. Additionally,the root mean square error of prediction(RMSEP) and correlation coefficient were superior to those of the aforementioned methods. These results indicate that the proposed method is an effective approach for model transfer.
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 .
Zheng K Y , Shen Y , Zhang W , Zhou C G , Ding F Y , Zhang X , Zhang R J , Shi J Y , Zou X B . Spectrosc . Spectral Anal. (郑开逸,沈烨,张文,周晨光,丁福源,张锡,张柔佳,石吉勇,邹小波. 光谱学与光谱分析), 2022 , 42 ( 12 ): 3783 - 3788 .
Zhou Z K , Li C X , Wang Z , Liu R , Chen W L , Xu K X . Spectrosc . Spectral Anal. (周子堃,李晨曦,王哲,刘蓉,陈文亮,徐可欣. 光谱学与光谱分析), 2020 , 40 ( 11 ): 3562 - 3566 .
Liu C L , Liu H Y , Sun X R , Wu J Z , Yang Y F . Trans . Agric. Mach . (刘翠玲,刘浩言,孙晓荣,吴静珠,杨雨菲. 农业机械学报), 2020 , 51 ( 9 ): 344 - 349 .
Chen Q . Model Transfer Strategy of NIR Analysis for Pulpwood Lignin Based on DS and PDS . Nanjing : Nanjing Forestry University(陈琴. 基于DS与PDS的纸浆材木质素近红外分析模型传递策略研究. 南京:南京林业大学) , 2022 .
Xu Y Y , Wen X Y , Li M G , Zhang T L , Tang H S , Li H . Chin. J. Anal. Chem. (徐艳艳,温晓燕,李茂刚,张天龙,汤宏胜,李华. 分析化学), 2021 , 49 ( 10 ): 1758 - 1765 .
Zhang N H , Zhao L , Wang D , Liu Y , Wang H B , Li B B , Liang Y Y , Guo J W . Tobacco Sci . Technol . (张诺涵,赵乐,王迪,刘雨,王洪波,李蓓蓓,梁友艳,郭军伟. 烟草科技), 2024 , 57 ( 2 ): 18 - 26 .
Xu H R , Li Q Q . Trans . Chin. Soc. Agric. Mach. (徐惠荣,李青青. 农业机械学报), 2017 , 48 ( 9 ): 312 - 317 .
Zhong K J , Bin J , Wang Z G , Du W , Chen Z P . Agric. Technol. (钟科军,宾俊,王志国,杜文,陈增萍. 农业与技术), 2022 , 42 ( 22 ): 10 - 14 .
Liu Z W , Xu L J , Chen X J . Spectrosc . Spectral Anal. (刘贞文,徐玲杰,陈孝敬. 光谱学与光谱分析), 2020 , 40 ( 7 ): 2313 - 2318 .
Liu X P , Qin Y H , Zhang F M , Jiang W , Yin Z J . J . Instrum. Anal .(刘鑫鹏,秦玉华,张凤梅,蒋薇,尹志豇. 分析测试学报), 2022 , 41 ( 11 ): 1621 - 1628 .
Li Y H , Xie M , Yi Y . Appl . Res. Comput . (李阳辉,谢明,易阳. 计算机应用研究), 2017 , 34 ( 2 ): 374 - 377 .
Fan Y C , Luo T J , Zhou C L . J. Xiamen Univ.:Nat . Sci. (范亚超,罗天健,周昌乐. 厦门大学学报:自然科学版), 2018 , 57 ( 6 ): 885 - 889 .
Zhang L Z , Jing L Y , Xu W X , Tan J W . Comb. Mach. Tool Autom. Mach. Technol . 张立智 , 井陆阳 , 徐卫晓 , 谭继文 . 组合机床与自动化加工技术) , 2019 ,( 6 ): 58 - 62 .
Hong S J , Sun M H , Wang Z T , Qiu Z Y . J . Detect. Control (洪淑婕,孙闽红,王之腾,仇兆炀. 探测与控制学报), 2022 , 44 ( 5 ): 83 - 89,96 .
Cai G Q , Hu Y J , Li C P , Ji Y , Wang H L . J . Liaoning Univ. Petrol. Chem. Technol. (蔡广庆,胡益炯,李春澎,纪晔,王弘历. 辽宁石油化工大学学报), 2024 , 44 ( 2 ): 1 - 6 .
Shi W J , Dai C G , Zhao Y , Wang Y , Wang Z J . J . Geomatics Sci. Technol. (史文洁,戴晨光,赵莹,王岩,王志坚. 测绘科学技术学报), 2021 , 38 ( 4 ): 391 - 397 .
Luo J J , Wang B , Zhang X Y , Cai Y Y , Wu H L , Yang B . Comput. Era(罗佳杰 , 王宝 , 张馨嫣 , 蔡耀仪 , 吴浩粼 , 阳波 . 计算机时代) , 2022 ,( 5 ): 1 - 5 .
0
浏览量
42
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构