连续小波变换结合无参数模型增强框架对时序漂移的近红外光谱建模

引用本文: 张进, 叶世著, 吴艾璟, 李博岩, 李杰, 詹莜国, 彭海根, 徐兴阳. 连续小波变换结合无参数模型增强框架对时序漂移的近红外光谱建模[J]. 分析化学, 2022, 50(9): 1391-1398. doi: 10.19756/j.issn.0253-3820.211236 shu

Citation: ZHANG Jin, YE Shi-Zhu, WU Ai-Jing, LI Bo-Yan, LI Jie, ZHAN You-Guo, PENG Hai-Gen, XU Xing-Yang. Continuous Wavelet Transform Combined with Parametric-Free Calibration Enhancement Framework for Calibration of Time-shift Near-infrared Spectra[J]. Chinese Journal of Analytical Chemistry, 2022, 50(9): 1391-1398. doi: 10.19756/j.issn.0253-3820.211236 shu

连续小波变换结合无参数模型增强框架对时序漂移的近红外光谱建模

张进 ^1, ,
叶世著 ^2, ,
吴艾璟 ^2, ,
李博岩 ^1, ,
李杰 ^3, ,
詹莜国 ^3, ,
彭海根 ^4, ,
徐兴阳 ^{3,
,}

1.
贵州医科大学公共卫生与健康学院, 环境污染与疾病监控教育部重点实验室, 贵阳 550025;
2.
贵州中烟工业有限责任公司技术中心, 贵阳 550009;
3.
云南省烟草公司昆明市公司, 昆明 650051;
4.
四川威斯派克科技有限公司, 成都 610041

通讯作者: 徐兴阳,E-mail:yy_xxy@sina.com

基金项目:
国家自然科学基金项目（No.22004022）、贵州省科技厅科技计划项目（No.黔科合基础-ZK[2021]一般045）和贵州省教育厅普通高等学校青年科技人才成长项目（No.黔教合KY字[2021]163）资助。

摘要: 近红外(Near-infrared,NIR)光谱法具有高效、无损的特点,然而其采集的光谱容易受多种外界因素的影响而发生漂移,导致分析结果出现偏差。时序漂移是一种NIR光谱随检测时间发生持续且有规律漂移的普遍现象。本研究提出了一种时序漂移NIR光谱的建模新方法,将漂移信号分解为背景漂移和样本依赖的时序漂移。分别利用连续小波变换(Continuous wavelet transform,CWT)和半监督-无参数模型增强(Semi-supervised parameter-free calibration enhancement,SS-PFCE)消除NIR光谱中时序背景漂移和样本依赖的时序信号漂移部分,进而实现准确建模。通过对2019年和2020年在云南省境内分别采集的928个和962个土壤样品的时序漂移NIR光谱进行建模,以土壤有机质(Soil organic matter,SOM)含量的预测准确性验证本方法的建模效果。对2019年采集的光谱建模(预测均方根误差(Root mean squared error of prediction,RMSEP)=6.7 g/kg,R²=0.76),预测2020年采集的漂移光谱时出现了较大的偏差(RMSEP=31.3 g/kg,R²=0.50)。通过CWT处理后的光谱建模预测,2020年光谱的预测结果明显变好(RMSEP=11.6 g/kg,R²=0.66);通过SS-PFCE进行模型增强后有了进一步的提升(RMSEP=8.3 g/kg,R²=0.67)。结果表明,CWT结合SS-PFCE能够最大程度消除NIR光谱中的时序漂移,获得较好的建模结果。

关键词:

English

Continuous Wavelet Transform Combined with Parametric-Free Calibration Enhancement Framework for Calibration of Time-shift Near-infrared Spectra

1.
Key Laboratory of Environmental Pollution Monitoring and Disease Control, Ministry of Education, School of Public Health, Guizhou Medical University, Guiyang 550025, China;
2.
Technology Centre, China Tobacco Guizhou Industrial Co., Ltd, Guiyang 550009, China;
3.
Yunnan Tobacco Company Kunming Branch, Kunming 650051, China;
4.
Sichuan Vespec Technology Co. Ltd., Chengdu 610041, China

Corresponding author: XU Xing-Yang, yy_xxy@sina.com

Received Date: 20 March 2021
Revised Date: 11 April 2022
Fund Project:
Supported by the National Natural Science Foundation of China (No.22004022), the Guizhou Provincial Science and Technology Projects (No.ZK[2021]045) and the Department of Education of Guizhou Province of China (No.KY[2021]163).

Abstract: Near-infrared (NIR) spectroscopy is a highly efficient and non-destructive technology applied in many areas. The measured spectra, however, are susceptible to shift due to various external interferences, resulting in biased analytical results. Time-shifts in NIR spectra are typical phenomena of continuously shifting spectra with measuring time, which is common in practical applications. In this study,a new method for modeling the time-shift NIR spectra was proposed, in which the shifting signal was divided into shifting background and sample-dependent shifts, and then corrected by continuous wavelet transform (CWT) and semi-supervised parameter-free calibration enhancement (SS-PFCE), respectively. The efficiency of the method was evaluated by modeling 1941 time-shift NIR spectra of soil samples collected in Yunnan Province (China) in 2019 and 2020 to predict the soil organic matter (SOM) content. The spectra taken in 2019 were calibrated (Root mean squared error of prediction (RMSEP)=6.7 g/kg, R²=0.76) and a large deviation was observed in predicting the spectra taken in 2020 (RMSEP=31.3 g/kg, R²=0.50). After CWT treatment, the prediction of spectra measured in 2020 was significantly promoted by predicting the spectra (RMSEP=11.6 g/kg, R²=0.66), and the prediction was further improved by SS-PFCE (RMSEP=8.3 g/kg, R²=0.67). The results indicated that CWT and SS-PFCE were efficient for eliminating the shifting background and sample-related shifts in time-shift NIR spectra, respectively.

Key words:

Near-infrared spectroscopy
/ Time-shift
/ Semi-supervised parameter-free calibration enhancement
/ Soil organic matter

1. [1]
  ZIEGLER U J, LEITENBERGER M, LONGIN C, FRIEDRICH H, WURSCHUM T, CARLE R, SCHWEIGGERT R M. J. Food Compos. Anal., 2016, 51:30-36.ZIEGLER U J, LEITENBERGER M, LONGIN C, FRIEDRICH H, WURSCHUM T, CARLE R, SCHWEIGGERT R M. J. Food Compos. Anal., 2016, 51:30-36.
2. [2]
  DU Xia-Yu, XIONG Yan-Mei, XIA Jing-Jing, MIN Shun-Geng. Chin. J. Anal. Chem., 2020, 48(4):543-550. 杜夏瑜, 熊艳梅, 夏静静, 闵顺耕. 分析化学, 2020, 48(4):543-550.
3. [3]
  CHU Gang-Hui, WANG Kun, YIN Xue-Bo. Chin. J. Anal. Chem., 2020, 48(4):536-542. 楚刚辉, 王坤, 尹学博. 分析化学, 2020, 48(4):536-542.
4. [4]
  SCHOOT M, KAPPER C, VAN KOLLENBURG G H, POSTMA G J, VAN KESSEL G, BUYDENS L M C, JANSEN J J. Chemom. Intell. Lab. Syst., 2020, 204:104105.SCHOOT M, KAPPER C, VAN KOLLENBURG G H, POSTMA G J, VAN KESSEL G, BUYDENS L M C, JANSEN J J. Chemom. Intell. Lab. Syst., 2020, 204:104105.
5. [5]
  ZHANG J, CUI X Y, CAI W S, SHAO X G. Sci. China:Chem., 2019, 62(2):271-279.ZHANG J, CUI X Y, CAI W S, SHAO X G. Sci. China:Chem., 2019, 62(2):271-279.
6. [6]
  ZHANG J, CUI X Y, CAI W S, SHAO X G. J. Chemometr., 2018, 32(11):e2971.ZHANG J, CUI X Y, CAI W S, SHAO X G. J. Chemometr., 2018, 32(11):e2971.
7. [7]
  ZHANG J, GUO C, CAI W S, SHAO X G. Chemom. Intell. Lab. Syst., 2021, 210:104244.ZHANG J, GUO C, CAI W S, SHAO X G. Chemom. Intell. Lab. Syst., 2021, 210:104244.
8. [8]
  ZHANG Jin, HU Yun, ZHOU Luo-Xiong, LI Bo-Yan. J. Instrum. Anal., 2020, 39(10):1196-1203. 张进, 胡芸, 周罗雄, 李博岩. 分析测试学报, 2020, 39(10):1196-1203.
9. [9]
  ZHANG Jin, CAI Wen-Sheng, SHAO Xue-Guang. Prog. Chem., 2017, 29(8):902-910. 张进, 蔡文生, 邵学广. 化学进展, 2017, 29(8):902-910.
10. [10]
  WANG Y D, VELTKAMP D J, KOWALSKI B R. Anal. Chem., 2002, 63(23):2750-2756.WANG Y D, VELTKAMP D J, KOWALSKI B R. Anal. Chem., 2002, 63(23):2750-2756.
11. [11]
  DU W, CHEN Z P, ZHONG L J, WANG S X, YU R Q, NORDON A, LITTLEJOHN D, HOLDEN M. Anal. Chim. Acta, 2011, 690(1):64-70.DU W, CHEN Z P, ZHONG L J, WANG S X, YU R Q, NORDON A, LITTLEJOHN D, HOLDEN M. Anal. Chim. Acta, 2011, 690(1):64-70.
12. [12]
  LIU Y, CAI W S, SHAO X G. Anal. Chim. Acta, 2014, 836:18-23.LIU Y, CAI W S, SHAO X G. Anal. Chim. Acta, 2014, 836:18-23.
13. [13]
  ZHANG J, GUO C, CUI X Y, CAI W S, SHAO X G. Anal. Chim. Acta, 2019, 1050:25-31.ZHANG J, GUO C, CUI X Y, CAI W S, SHAO X G. Anal. Chim. Acta, 2019, 1050:25-31.
14. [14]
  ZHANG J, LI B Y, HU Y, ZHOU L X, WANG G Z, GUO G, ZHANG Q H, LEI S C, ZHANG A H. Anal. Chim. Acta, 2021, 1142:169-178.ZHANG J, LI B Y, HU Y, ZHOU L X, WANG G Z, GUO G, ZHANG Q H, LEI S C, ZHANG A H. Anal. Chim. Acta, 2021, 1142:169-178.
15. [15]
  MISHRA P. Anal. Chim. Acta, 2021, 1187:339154.MISHRA P. Anal. Chim. Acta, 2021, 1187:339154.
16. [16]
  MISHRA P, WOLTERING E. Anal. Chim. Acta, 2021, 1177:338771.MISHRA P, WOLTERING E. Anal. Chim. Acta, 2021, 1177:338771.
17. [17]
  MISHRA P. Chemom. Intell. Lab. Syst., 2021, 214:104338.MISHRA P. Chemom. Intell. Lab. Syst., 2021, 214:104338.
18. [18]
  NY/T 1121.6-2016. Soli Testing. Part 6:Method for Determination of Soil Organic Matter. Agricultural Standard of the People's Republic of China. 中华人民共和国农业行业标准.土壤检测第6部分:土壤有机质的测定. NY/T 1121.6-2016.
19. [19]
  LI X Y, CAI W S, SHAO X G. J. Near Infrared Spectrosc., 2015, 23(5):285-291.LI X Y, CAI W S, SHAO X G. J. Near Infrared Spectrosc., 2015, 23(5):285-291.
20. [20]
  ZOU X B, ZHAO J W, MALCOLM P, MEL H, MAO H P. Anal. Chim. Acta, 2010, 667(1-2):14-32.ZOU X B, ZHAO J W, MALCOLM P, MEL H, MAO H P. Anal. Chim. Acta, 2010, 667(1-2):14-32.

扫一扫看文章

计量

PDF下载量: 13
文章访问数: 580
HTML全文浏览量: 46

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

连续小波变换结合无参数模型增强框架对时序漂移的近红外光谱建模

通讯作者: 徐兴阳,E-mail:yy_xxy@sina.com

English

Continuous Wavelet Transform Combined with Parametric-Free Calibration Enhancement Framework for Calibration of Time-shift Near-infrared Spectra

Corresponding author: XU Xing-Yang, yy_xxy@sina.com

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

连续小波变换结合无参数模型增强框架对时序漂移的近红外光谱建模

通讯作者: 徐兴阳,E-mail:yy_xxy@sina.com

English

Continuous Wavelet Transform Combined with Parametric-Free Calibration Enhancement Framework for Calibration of Time-shift Near-infrared Spectra

Corresponding author: XU Xing-Yang, yy_xxy@sina.com

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南： 你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

文章相关

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs