基于NIRS技术的食用醋品牌溯源研究

发布时间：2018-04-28 14:02

本文选题：近红外光谱 + 食用醋　；参考：《光谱学与光谱分析》2014年09期

【摘要】：以四种品牌152组食用醋样品为研究对象,采用漫反射与透射两种近红外光谱采集模式分别进行光谱数据采集,并以此建立了食用醋品牌溯源模型,重点考察光谱采集模式、光谱预处理方法等对溯源模型精度的影响。结果表明,选取114组样品为训练集,原始光谱数据经过多元散射校正、二阶求导预处理后,采用偏最小二乘判别分析法(PLS1-DA)建立的食用醋NIRS品牌溯源模型,对38组测试集样品进行预测,透射光谱模型的决定系数(R2)、校准均方根误差(root-mean-square error of calibration,RMSEC)、预测均方根误差(root-mean-square error of prediction,RMSEP)分别为0.92,0.113,0.127,正确识别率为76.32%;漫反射光谱模型R2,RMSEC,RMSEP分别为0.97,0.102,0.119,正确识别率为86.84%。由此说明,近红外光谱结合PLS1-DA可以用来建立食用醋品牌溯源模型,且漫反射光谱模型预测效果更好。
[Abstract]:Taking 152 groups of edible vinegar samples of four brands as the research object, the spectral data were collected by diffuse reflection and transmission near infrared spectrum, and the tracing model of edible vinegar brand was established, and the spectral acquisition model was investigated. The effect of spectral pretreatment methods on the accuracy of traceability model. The results showed that 114 groups of samples were selected as training set, the original spectral data was corrected by multiple scattering, the second order derivative pretreatment was used to establish the NIRS brand traceability model of edible vinegar by partial least squares discriminant analysis (PLS1-DA). The determination coefficient of the transmission spectrum model is R2N, the root-mean-square error of calibration RMSECs, the root-mean-square error of prediction RMSEPs are 0.92n0.1130.127and the correct recognition rate is 76.322.The diffuse reflectance spectral model R2RMSECEPs are 0.970.102n0.119, and the correct RMSEPs are 86.84kgs. The results show that the RMSEPs of the R2GMS model are 0.970.102a 0.19, and the RMSEPs of the RMSECs are 0.970.102a 0.1190.The root-mean-square error of prediction RMSEPs are 0.921030.127.The RMSEP of the diffuse reflectance spectrum model is 0.970.102n0.119. It is concluded that the near infrared spectroscopy combined with PLS1-DA can be used to establish the traceability model of edible vinegar brand, and the diffuse reflectance spectrum model is more effective.
【作者单位】：光明乳业股份有限公司乳业生物技术国家重点实验室;上海理工大学医疗器械与食品学院;上海海事大学信息工程学院;上海市食品药品检验所;
【基金】：国家自然科学基金项目(31101348)资助
【分类号】：O657.33

【相似文献】