基于近红外光谱的橄榄油品质鉴别方法研究

摘要

Currently on the market,the sale of olive oil is mainly divided into extra virgin olive oil and common virgin olive oil. In order to identify the qualities of two different olive oils,a new method to identify the quality of olive oil with siPLS-IRIV-PCA algorithm is developed.Based on the near infrared spectral data of olive oil,the efficient spectral subintervals are selected with a synergy interval partial least squares (siPLS).The performance of the model is evaluated by using the root mean square error of cross-validation (RMSECV).The characteristic wavelengths are selected from the efficient spectral subintervals by iteratively retains informative variables (IRIV)algorithm.Principal component analysis (PCA)model is constructed based on the selected characteristic wavelengths.The samples of 90 groups of extra virgin olive oil and 90 groups of common olive oil are identified. PCA uses 1 427 wavelength variables as input variables and the contribution rates of the first two principal components are 51.891 8% and 26.473 2% respectively.siPLS-PCA uses 408 wavelength variables as input variables and the contribution rates of the first two principal components are 56.039 1% and 36.2355%.siPLS-IRIV-PCA uses 6 wavelength variables as input vari-ables and the contribution rates of the first two principal components are 66.347 6% and 32.3043%.The result shows that, compared with PCA and siPLS-PCA,siPLS-IRIV-PCA has the best identification performance.The method is simple and con-venient and has a high identification degree which offers a new approach to identify the quality of olive oil.%目前市面上销售的橄榄油主要分为特级初榨橄榄油和普通初榨橄榄油两类,为了鉴别两种不同品质的橄榄油,提出了一种应用 siPLS-IRIV-PCA算法的橄榄油品质鉴别的新方法。基于橄榄油的近红外光谱数据,应用联合区间偏最小二乘法(siPLS)对橄榄油的近红外光谱进行了波长区间优选,使用交叉验证均方根误差(RMSECV)评估模型的性能并选择最优波长区间,通过迭代保留信息变量(IRIV)算法从最优波长区间中选择特征波长,根据选择的特征波长构建主成分分析(PCA)模型。对90组特级初榨橄榄油和90组普通橄榄油样本进行了判别鉴定。PCA将1427个波长变量作为输入变量,前两个主成分贡献率为51.8918%和26.4732%；siPLS-PCA将408个波长变量作为输入变量,前两个主成分贡献率为56.0391%和36.2355%；siPLS-IRIV-PCA将6个波长变量作为输入变量,前两个主成分贡献率为66.3476%和32.3043%。结果表明,与PCA和 siPLS-PCA鉴别方法相比,siPLS-IRIV-PCA具有最佳的鉴别性能。