-
从检测水中腐殖质的实际需求出发进行三维荧光光谱检测系统的设计与搭建。结合检测的实际需求,双光栅单色仪工作波长为350~450 nm,光谱仪工作范围为340~650 nm,样品槽使用石英试管以保证紫外光的充分透过,系统的设计与实际组成图见图3。
-
利用优级纯的腐植酸粉末配置浓度分别为20 mg/L、50 mg/L、100 mg/L、150 mg/L和200 mg/L共5个浓度的试剂进行检测,将不同浓度的数据进行归一化处理后导入分析程序中。借助因子数目选择流程完成对因子数目的选择,确定最优模型。因子分析中,因子数量一般不少于2个,不高于5个,腐植酸是的组成较为复杂,因此因子数上限为5。
(1)核心对角矩阵分布
首先获得腐植酸溶液的三维荧光光谱在因子数为2~5时的核心对角矩阵分布图。当选择因子数合适时,核心对角矩阵对角线的元素应该接近于1,其余接近于0。因子数为2~5时核心对角矩阵元素分布如图4所示。
经过分析发现,因子数2~5的核心阵都满足需求,即对角线元素偏向于1,其余偏向于0,当因子数目为4或5时,核心阵元素更偏向于0。需要进一步分析来判断各个因子下模型的优缺点。
(2)核一致函数
计算不同因子数目下模型的核一致函数数值,进一步选择模型。当核一致函数接近于100%时说明因子数目过少,接近于0时则说明因子数目过多,不同因子数目的核一致函数数值如表1所示。
Factor numbers 2 3 4 5 6 Numerical value 84% 73% 56% 51% 24% Table 1. Numerical change of kernel consistent function
由表1可看出:当因子数在4或5个时,核一致函数的数值在50%~60%之间,比较符合分解要求;当因子数为2或3时,核一致函数在70%以上,函数较高,不符合分解要求;当因子数为6个或者更多时,核一致函数数值过少,且降低的幅度过少,不符合残差比较要求,因此,因子数为4和5最为合适。
(3)恒波长残差值
当因子数为4或5时,分析实测图和拟合图在恒波长同步荧光光谱图上的残差来进一步选择模型。因子数为4和5时恒波长残差图如图5所示。
通过仔细比较图5(a)和图5(b)所示的恒波长残差图示,当因子数为4时残差图效果图更优。
(4)综合分析
通过上述因子数目选择流程可以发现,核心对角矩阵法条件相对宽松,可以用来确定因子数目范围,核一致函数条件严苛,可以锁定因子数目,若存在多个因子模型的核一致函数满足要求时,需要进一步分析残差图进行比较,最后若存在多个因子数目的模型满足需求,则使用数目较少的模型以避免因子冗余。
-
不同浓度的腐植酸溶液导出了相同的4个因子,各个因子所在区间如表2所示。
Excitation wavelength/nm Emission wavelength/nm 360-370 450-500 350-360 450-500 365-375 475-525 380-390 475-525 Table 2. Distribution of humic acid factors
经过和标准物质表进行对比,可以发现上述因子分别为两个类腐植酸A类物质,一个类腐植酸C类物质,一个土壤富里酸物质。
-
为了探索溶液浓度对因子贡献率的影响,编写分析算法来分析各个因子的相对贡献率,由于平行因子分析技术关注的样品之间相对强度的差别,因此此处因子的强度并不是绝对强度,而是相对数值,反映的是因子之间的相对差异。图6反映了浓度为20 mg/L、50 mg/L、100 mg/L、150 mg/L、200 mg/L浓度从小到大时4个因子的占比,可见尽管浓度变化,由于其溶液性质并未改变,因子的占比相近不会发生巨大的变化。
Design and verification of improved factor number selection process for parallel factor algorithm
doi: 10.3788/IRLA20210362
- Received Date: 2021-06-02
- Rev Recd Date: 2021-07-05
- Publish Date: 2021-11-02
Abstract: In order to solve the problem that the selection process of the number selection of model factors in the decomposition of three-dimensional fluorescence spectrum by parallel factor algorithm is not clear, an improved factor number selection process composed of core diagonal matrix, kernel uniform function and constant wavelength residual graph was proposed. The improved parallel factor analysis algorithm was developed to verify the accuracy of factor number selection process with humic acid as detection material. The results show that, combined with the above process, when the excitation light and emission light are in 350-450 nm/350-620 nm, respectively, and the factor number is 4, the core diagonal matrix distribution meets the demand, the kernel consistent function is 52%, the residual error of the fitting diagram is the smallest, and the decomposition effect is the best in the standard region. Compared with using a single method, the above combination process is more logical and accurate, and can quickly determine the number of factors in practical application. The four factors are two humic acid factor A located at 360-370 nm/450-500 nm and 350-360 nm/450-500 nm, one humic acid factor C located at 365-375 nm/475-525 nm, and one soil fulvic acid factor located at 380-390 nm/475-525 nm. When the concentration increased from 20 mg/L to 200 mg/L, the composition and contribution rate of the factors has little difference, that is, the change of concentration did not change the properties of the solution.