二进制蜻蜓算法-直接校正算法优选标样集在小麦粉蛋白质近红外模型传递中的应用  

Application of BDA-DS Method to Optimize the Selection of Transfer Set in Near Infrared Model Transfer of Wheat Flour Protein

作　　者：王红鸿 陈琴 陈勇 熊智新 吴彩娥 谢德红 WANG Honghong;CHEN Qin;CHEN Yong;XIONG Zhixin;WU Cai’e;XIE Dehong(College of Light Industry and Food Engineering,Nanjing Forestry University,Nanjing 210037;College of Information Science and Technology,Nanjing Forestry University,Nanjing 210037)

机构地区：[1]南京林业大学轻工与食品学院,江苏南京210037 [2]南京林业大学信息科学技术学院,江苏南京210037

出　　处：《分析科学学报》2023年第3期267-274,共8页Journal of Analytical Science

基　　金：“十三五”国家重点研发计划重点专项(2019YFD1002300)。

摘　　要：为了实现小麦粉蛋白质含量近红外分析模型的传递,探究二进制蜻蜓算法(Binary Dragonfly Algorithm,BDA)与直接校正算法(Direct Standardization,DS)相结合构成的BDA-DS算法挑选标样集对模型传递结果的影响。以棱光S450光栅型近红外光谱仪为主机,NeoSpectra Micro傅里叶变换型近红外光谱仪为从机,采集了126个小麦粉的近红外光谱,用偏最小二乘回归法建立了主机近红外光谱与小麦粉蛋白质的关联模型。经BDA-DS算法模型传递后,主机模型对从机样品预测决定系数为0.9812,预测标准偏差为0.1838,从机与主机的光谱集合平均马氏距离由22.34下降到1.40,均接近于主机模型精度水平。该研究同时与采用Kennard/Stone(K/S)挑选标样集再结合DS构成的传统K/S-DS算法进行了对比,结果表明:相对于K/S-DS算法,BDA-DS算法挑选出较少的标样集就能表征仪器的差异,有效地提高了主机模型对从机样品的预测精度,为近红外模型传递提供了一种更加有效的标样集选择方法。To improve the accuracy of near-infrared(NIR)calibration model transfer for wheat flour protein content,the BDA-DS algorithm,which integrated Binary Dragonfly Algorithm(BDA)and Direct Standardization(DS),was proposed to select the transfer subset.In this experiment,Lengguang S450 grating scanning spectrometer was defined as the master instrument while NeoSpectra Micro Fourier transform(FT)NIR spectrometer was the target instrument.Both of them were adopted to collect the spectra of 126 samples respectively,then the correlation model between NIR spectra and wheat flour protein by Partial Least Squares Regression(PLSR)method was established.After the model transfer of BDA-DS,the master model had a significant predictive performance on the target prediction set.The prediction determination coefficient was 0.9812,the root mean square errors of prediction was 0.1838,and the average Mahalanobis distance between the master and target spectra decreased from 22.34 to 1.40,all of which were close to the accuracy of the master instrument.The conventional K/S-DS method was also employed for comparative investigation,and the results showed that the transfer set selected by the BDA-DS method not only could better characterize the differences between the master and target instruments with fewer transfer sets but also improved the prediction accuracy of the transferred analytical model.The proposed method can provide a more effective selection strategy to optimize the standardization samples for NIR calibration model transfer.

关 键 词：二进制蜻蜓算法 直接校正算法 近红外光谱 模型传递 小麦粉蛋白质 

分 类 号：O657.33[理学—分析化学]