基于近红外光谱的腌制期咸鸭蛋理化指标无损检测

Non-Destructive Detection of Physical and Chemical Indicators of Salted Duck Eggs during Salting Using Near-Infrared Spectroscopy

以高邮麻鸭蛋为研究对象,采集整个腌制期咸鸭蛋近红外光谱数据,对比测定其理化指标值,建立咸鸭蛋关键品质指标(蛋黄含水率、蛋黄氯化钠浓度和咸蛋黄指数)的无损快速检测模型。为尽可能削弱外部其他因素对样本光谱采集过程的影响,使用多元散射校正、归一化等预处理方法,结合竞争性自适应重加权算法(competitive adaptive reweighted sampling,CARS)、连续投影算法(successive projections algorithm,SPA)和非信息变量剔除(uninformative variables elimination,UVE)3种特征选择算法建立偏最小二乘回归模型,并在一次特征波段选取基础上提取二次特征波长,再建立偏最小二乘回归模型。结果表明,蛋黄含水率、蛋黄氯化钠浓度和咸蛋黄指数的最优波长选择方法均是二次特征波段提取法UVE+SPA,发现二次特征波段选择综合表现最优。经对比分析,蛋黄含水率、蛋黄氯化钠浓度、咸蛋黄指数最优模型结构分别是标准化-UVE+SPA-PLSR、卷积平滑-UVE+SPA-PLSR、均值中心化-UVE+SPA-PLSR,训练集相关系数分别为0.9334、0.8978和0.9286,预测集相关系数分别为0.9276、0.9085和0.9163。本研究建立的光谱模型能实现对腌制期咸鸭蛋理化指标的无损检测。

The near-infrared spectral data of salted duck eggs,prepared from Gaoyou Ma duck eggs,were collected during the whole curing period and based on them,a model for nondestructive and rapid detection of the key quality indicators of salted duck eggs(yolk moisture content,yolk sodium chloride concentration and salted egg yolk index).In order to reduce the influence of other external factors on spectrum acquisition,various spectral preprocessing methods such as multiplicative scatter correction and normalization combined with three feature selection algorithms including competitive adaptive reweighted sampling(CARS),successive projections algorithm(SPA)and uninformative variables elimination(UVE)were used to establish partial least squares regression(PLSR)models.Furthermore,CARS or UVE combined with SPA was used to establish a more robust model.It was found that the optimal band selection method for the three quality indicators of salted duck eggs was UVE combined with SPA,which had the best overall performance.Comparative analysis showed that the optimal model structures for egg yolk moisture content,egg yolk sodium chloride concentration,and salted egg yolk index were standardization-UVE+SPA-PLSR,Savitzky-Golay-UVE+SPA-PLSR,and mean centering-UVE+SPA-PLSR,respectively.The correlation coefficients were 0.9334,0.8978 and 0.9286 for the training set(R_(c)),and 0.9276,0.9085 and 0.9163 for the prediction set(R_(p)),respectively.The spectral model established in this study can allow the non-destructive detection of the physical and chemical indicators of salted duck eggs during the salting period.