分析测试学报2025，Vol.44Issue(3)：471-478,8.DOI:10.12452/j.fxcsxb.240826343
卷积桥接孪生自编码器的近红外光谱转移研究
Study on Near Infrared Spectrum Transfer of Convolutional Bridged Twin Denoising Reduction Autoencoder
摘要
Abstract
The differences between near infrared(NIR)spectrometers make it challenging to share prediction models across different instruments,limiting the widespread application of this technolo-gy.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 autoen-coder(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 vali-date 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),spec-tral subtraction correction(SSC),Shenk's algorithm,CNN and deep autoencoder,the average rela-tive 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 aforemen-tioned methods.These results indicate that the proposed method is an effective approach for model transfer.关键词
模型转移/编码器/孪生/卷积桥接/近红外光谱Key words
model transfer/encoder/twin/convolutional bridge/near infrared spectroscopy分类
化学引用本文复制引用
杨泽会,夏春艳,张恺,徐梦瑶,毕一鸣,夏自麟,吴箭,李瑞东,郝贤伟,吕小芳,田雨农,张志成,吴灵通,李正莹..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(3):471-478,8.基金项目
云南烟叶复烤有限责任公司科技计划项目(2022FK06) （2022FK06）
中国烟草总公司浙江中烟工业有限责任公司科技计划项目(ZJZY2023A012) （ZJZY2023A012）
