基于二维相关近红外光谱术的小米含水率检测  

Millet Moisture Content Detection Based on Two-Dimensional Correlation Near Infrared Spectroscopy

作　　者：何国康 袁凯 张志勇[1] 宋海燕[1] 韩小平[1] 杨威 He Guokang;Yuan Kai;Zhang Zhiyong;Song Haiyan;Han Xiaoping;Yang Wei(College of Agricultural Engineering,Shanxi Agricultural University,Jinzhong,Shanxi 030801,China)

机构地区：[1]山西农业大学农业工程学院,山西晋中030801

出　　处：《激光与光电子学进展》2022年第8期549-554,共6页Laser & Optoelectronics Progress

基　　金：山西省自然科学基金面上项目(201701D121103);山西省重点研发计划项目(201803D221027-4)。

摘　　要：小米含水率是衡量小米品质的重要指标,以小米含水率为外扰因素研究了不同含水率样本的二维相关光谱,以实现小米含水率的检测。获取60个样本的近红外光谱,经过4种预处理方法处理后,基于全波段光谱建立样本含水率的偏最小二乘回归(PLSR)模型。经过对比得出不加预处理的模型,其预测效果最好,校正集决定系数(Rc 2)为0.9460,均方根误差(RMSEC)为0.49%,预测集决定系数(Rp 2)为0.9391,均方根误差(RMSEP)为0.63%。以小米含水率为外扰因素,将小米不同含水率梯度的光谱数据进行二维相关光谱分析,通过二维相关同步谱的6个自相关峰对应波长选出1083,951,868,1314,1675,1865 nm作为特征波长。以此建立小米含水率的预测模型,相比于由全光谱数据建立的模型,本文所提模型因波长变量极大地减少,得到了简化,校正集决定系数(Rc 2)为0.952,均方根误差(RMSEC)为0.60%,预测集决定系数(Rp 2)为0.897,均方根误差(RMSEP)为0.63%。结果表明二维相关的近红外光谱分析可以实现小米含水率的预测,同时能够提取特征波长,这为设计基于分立波长元件的小米专用水分检测仪提供了依据。The moisture content of millet is an important indicator to measure the quality of millet.To detect millet moisture content,the twodimensional correlation spectra of samples with different moisture contents are studied with millet moisture content as the external disturbance factor.First,obtain the near infrared spectra of 60 samples,and then,using four different preprocessing methods,create a partial least square regression(PLSR)model of sample moisture content based on the fullband spectra.Following the comparison,it is determined that the model with no preprocessing has the best effect.The calibration set coefficient of determination(Rc 2)is 0.9460,root mean square error(RMSEC)is 0.49%,prediction set coefficient of determination(Rp 2)is 0.9391,and root means square error(RMSEP)is 0.63%.Further,taking the moisture content of millet as the external disturbance factor,the spectral data of different moisture content gradients of millet is analyzed by twodimensional correlation spectroscopy,and the wavelengths of the six autocorrelation peaks of the twodimensional correlation synchronization spectrum are selected,and 1083,951,868,1314,1675,and 1865 nm are selected as the characteristic wavelength.Based on this,a millet moisture content prediction model is developed.The wavelength variable is reduced and the model is simplified when compared to fullspectrum data modeling.The correction set’s coefficient of determination(Rc 2)is 0.952,and the root mean square error(RMSEC)is 0.60%.The prediction set’s coefficient of determination(Rp 2)is 0.897,and the root mean square error(RMSEP)is 0.63%.The results show that twodimensional correlation near infrared spectroscopy can predict millet moisture content and extract the characteristic wavelength,which provides a foundation for the design of a special millet moisture detector based on discrete wavelength components.

关 键 词：光谱学 二维相关光谱 近红外光谱 含水率 小米 

分 类 号：O657.33[理学—分析化学]