基于光谱技术和SIMCA方法的润滑油鉴别

采用可见-近红外反射光谱结合独立软模式法(SIMCA)建立了不同品牌种类的发动机润滑油鉴别模型。研究在对光谱曲线进行预处理和聚类分析后,选取7个主成分作为SIMCA的最佳主成分,随机采用20×7个样本作为建模样本,其余的10×7个样本作为预测样本,应用SIMCA进行分类,在显著性水平为5%下,其预测分辨率为98.75%。根据变量建模能力值,找到敏感波段420~425 nm、492~518 nm和796~816 nm,并将相应波段的光谱值作为SIMCA的输入,进行建模预测,结果发现,预测分辨率达95.71%,能快速正确区分7类不同品种的发动机润滑油。

Fast Catalogue of Lubricating Oil by Vis/NIR Spectroscopy and SIMCA

The feasibility of visible and short-wave near-infrared spectroscopy(Vis/NIR) techniques with soft independent modeling of class analogy(SIMCA) as means for the nondestructive and fast detection model of lubricating oils was evaluated.And selected sensitive bands were found validated.In this study,seven kinds of lubricating oils were employed.20×7 lubricating oil samples were randomly selected for the calibration set,while the remaining 10×7 samples for the prediction set.SIMCA was applied to make the model.Seven frontal principal components(PCS) of each catalogue were applied as the best PC of SIMCA,and with a significance level of 0.05,recognition ratio of 98.75% was obtained.According to the modeling power of each spectra datum in SIMCA,some possible sensitive bands 420~425 nm,492~518 nm,796~816 nm were found.Then these spectrum data were used as the input of SIMCA.Finally,recognition ratio of 95.71% was obtained.The prediction results indicated that the selected wavelengths reflected the main characteristics of lubricating oils based on Vis/NIR spectroscopy,which proposed a new way to accelerate the research on cataloguing lubricating oils.