基于PARAFAC和ART算法的油类污染物荧光检测

Fluorescence Detection of Oil Pollutants Based on PARAFAC and ART Algorithms

采用平行因子分析(PARAFAC)和交替残差三线性(ART)算法,对石油类污染物进行测量与识别,重点对比分析了两种算法对油种鉴别的差异。在实验中,将以CCl4为溶剂的95号汽油、0号柴油与普通煤油溶液作为研究对象,以不同浓度的石油类物质混合液作为实验样本,利用F-7000荧光分光光度计对样本进行检测,以得到各样本的三维荧光数据。测量样本的组分数估计值预设为3时,采用PARAFAC算法得到的柴油、汽油和煤油样品的回收率分别为(95.60±3.60)%、(94.67±3.66)%和(95.49±4.49)%;ART算法无需预设组分数,其测量得到的柴油、汽油和煤油样本的回收率分别为(96.58±2.17)%、(95.17±9.17)%和(95.90±8.90)%。结果表明:两种算法都可用于三组分石油类污染物的识别与测量,均能得到较高的回收率;ART算法因无需预先设定组分数而更具优势。

Parallel factor analysis （PARAFAC） and alternating residual tri-linearization （ART） algorithms are used to measure and identify petroleum pollutants. The differences between the two algorithms in oil identification are emphatically compared and analyzed. The CC14 solutions of No. 95 gasoline, No. 0 diesel and kerosene are used as the research objects. We take petroleum mixed solutions with different concentrations as samples to measure the three-dimensional fluorescence data of each sample by F-7000 fluorescence spectrometer. When PARAFAC algorithm is applied and the component number is set to 3, the recovery rates of diesel, gasoline and kerosene are （95.60±3.60） %, （94.67±3.66） % and （95.49±4.49） %, respectively. ART algorithm does not require a preset component number, and the recovery rates of diesel, gasoline and kerosene are （96.58±2.17）%, （95.17± 9.17）% and （95.90±8.90）%, respectively. The results show that the two algorithms can be used for the measurement and identification of three kinds of petroleum pollutants, and high recovery rates can be obtained. ART algorithm does not require presetting component number, so it has more advantages.