Effect of spectrum preprocessing methods on the rapid detection of ash content in flour by the portable NIR spectrometer
-
摘要: 为了实现便携式近红外光谱仪现场快速分析小麦粉中灰分的含量,对125个小麦粉样本扫描并进行多种预处理后,建立了基于偏最小二乘（PLS）的定量分析模型。探讨了基线校正（Baseline）、矢量归一化（Normalize）、SavitskyGolay卷积平滑法、导数、标准正态变量变换（Standard Normal Variate Correction,SNV）以及多元散射校正（Multiplicative Scatter Correction,MSC）这六种预处理方法及其组合方式对建模的影响。结果表明:矢量归一化+Savitsky-Golay滤波平滑法是最佳预处理方法,相应建立的小麦粉灰分含量最佳模型的校正决定系数Rc2为0.947,交叉验证决定系数R2v为0.896,校正均方根误差（RMSEC）为0.026,交叉验证均方根误差（RMSECV）为0.037,预测均方根误差（RMSEP）为0.026。无预处理模型的校正决定系数为0.873,交叉验证决定系数为0.832,校正均方根误差为0.044,交叉验证均方根误差0.051,预测均方根误差为0.056;相较于无预处理模型,最佳模型的预测精度和稳健性有了很大的提高。
-
关键词:
- 便携式近红外光谱仪 /
- 偏最小二乘 /
- 灰分 /
- 矢量归一化 /
- Savitsky-Golay卷积平滑法
Abstract: In order to carry out the spot rapid analysis of ash content in flour which based on the portable NIR spectrometer, 125 samples of flour was scanned and some quantitative analytical modelswas built which based on the partial least squares ( PLS) analysis after various spectrum preprocessing methods. The experiment discussed the effect of six spectrum preprocessing methods including baseline, normalize, Savitsky-Golay convolution smoothing method, derivation, standard normal variate correction and multiplicative scatter correction and their combination on modeling, and analyzed various influencing factors in the process of experiment.The results showed that the best spectrum preprocessing method was the combination of normalize and Savitsky-Golay convolution smoothing method. The correlation coefficient of calibration ( Rc2) of the best corresponding model was 0.947.The Cross validation coefficient R2 vwas 0.896. The root mean square error RMSEC was 0.026. The root mean square error RMSECV was 0.037.The root mean square error of prediction set model RMSEP was 0.026. The correlation coefficient of calibration ( Rc2) of the model without spectrum preprocessing method was 0.873.The Cross validation coefficient R2 vwas 0.832.The root mean square error RMSEC was 0.044.The root mean square error RMSECV was 0.051.The root mean square error of prediction set model RMSEP was 0.056.Compared with the model without spectrum preprocessing methods, the best model strongly improves the prediction accuracy and the robustness of the model. -
[1] 许合金, 张百赟, 吴丹, 等.不同因素对面粉品质的影响[J].饲料与畜牧:新饲料, 2015 (5) :34-37. [2] 闫李慧.基于近红外光谱技术的面粉品质研究[D].郑州:河南工业大学, 2012:1-90. [3] 窦颖, 孙晓荣, 刘翠玲, 等.基于模拟退火算法优化波长的面粉品质检测[J].食品科学, 2016, 37 (12) :208-211. [4] 金华丽, 王金水.近红外光谱法检测小麦粉中灰分含量的研究[J].河南工业大学学报 (自然科学版) , 2010, 31 (1) :14-17. [5] 蒋衍恩.如何使用近红外仪实现小麦粉生产的过程控制[J].现代小麦粉工业, 2010, 24 (6) :18-20. [6] 李树高.小麦粉灰分含量对面制品的影响[J].粮食与食品工业, 2008, 15 (5) :11. [7] 王伟明, 董大明, 郑文刚, 等.梨果糖浓度近红外漫反射光谱检测的预处理方法研究[J].光谱学与光谱分析, 2013, 33 (2) :359-362. [8] 尼珍, 胡昌勤, 冯芳.近红外光谱分析中光谱预处理方法的作用及其发展[J].药物分析杂志, 2008 (5) :824-829. [9] 孙晓荣, 刘翠玲, 吴静珠, 等.基于近红外光谱无损快速检测小麦粉品质的研究[J].北京工商大学学报 (自然科学版) , 2011, 29 (4) :68-70. [10] 金华丽, 卞科.近红外光谱法检测小麦粉中的水分含量[J].中国粮油学报, 2010, 25 (8) :109-112. [11] 吴静珠, 李慧, 王克栋, 等.光谱预处理在农产品近红外模型优化中的应用研究[J].农机化研究, 2011 (3) :178-181. [12] 中国国家标准化管理委员会.GB/T 5505-2008粮油检验灰分测定法[S].北京:中国标准出版社, 2008. [13] 徐一茹, 刘翠玲, 孙晓荣, 等.基于近红外和中红外光谱技术的小麦粉品质检测及掺杂鉴别方法[J].食品科学, 2014, 12:128-132. [14] 李河, 林勤保, 郭捷, 等.近红外光谱技术及其在液态食品上应用的研究进展[J].食品工业科技, 2013, 34 (11) :376-383. [15] Daiki Ono, Takeshi Bamba, Yuichi Oku, et al.Application of Fourier transform near-infrared spectroscopy to optimizationof green tea steaming process conditions[J].Journal of Bioscience and Bioengineering, 2011, 112 (3) :247-251.
[16] FGuy, SPrache, AThomas, et al.Prediction of lamb meat fatty acid composition using near-infrared reflectance spectroscopy (NIRS) [J].Food Chemistry, 2011, 127 (3) :1280-1286.
[17] 金伟, 赵红霞, 高芝.基于PLS建模在近红外光谱分析中的应用展望[J].现代农业科学, 2008 (11) :10-11. [18] 周照艳, 岳勇, 王涛, 等.PLS因子数对定量模型性能稳定性的影响分析[J].计算机工程与设计, 2014 (5) :1788-1791. [19] 国家标准化管理委员会.GB 5009.4-2010食品中灰分的测定[S].北京:中国标准出版社, 2010.
计量
- 文章访问数: 204
- HTML全文浏览量: 20
- PDF下载量: 323
下载:
