苹果擦伤拉曼光谱无损检测虚拟系统研究

Non-destructive apple bruise detection with Raman spectroscopy and its virtual instrumentation

为检测苹果品质并依据擦伤进行分级,研发了一个基于拉曼光谱的实时无损自动检测分类虚拟仪器分级系统样机。采用一台Nicolet傅氏变换拉曼光谱仪进行苹果擦伤光谱检测。测试集和训练集的苹果光谱用WinDAS的典型变量分析(CVA)和主成分分析法(PCA)进行分类处理。分析得出的模型经UNEQ分类检验,'马氏平方图'和χ2检验结果该分类模型。其次,应用LabVIEW设计苹果虚拟仪器分级控制系统,并制作了样机。试验结果表明拉曼光谱分析能用于苹果擦伤无损检测和类别确定;虚拟仪器分级系统能对苹果进行准确分级处理。

A prototype automated inspection system was developed to classify apples based on bruising in real time. A Nicolet FT-Raman Spectroscope was employed to obtain apple spectra. The spectroscope utilized OMNIC E. S. P. 5.1 software. The unbruised and bruised spectra were analyzed and classified by WinDAS using canonical variate analysis (CVA) and principal component analysis (PCA) models, on both the training and testing sets. The PCA and CVA model analysis satisfactorily classified the apples by bruise, then the UNEQ class modeling was used and the square of Mahalanobis distance passed X2 test. Besides, LabWIEW was applied to develop apple grading control system, and prototype of virtual instrumental system was fabricated. The experiments show that the Raman spectroscope permits non-destructive bruise determination with good results and the virtual instrument grading system has a good accuracy.