荧光光谱法和ABC-RBF神经网络在多环芳烃浓度检测中的应用

发布时间：2018-06-10 06:42

本文选题：多环芳烃 + 荧光光谱　；参考：《发光学报》2017年06期

【摘要】：多环芳烃(polycyclic aromatic hydrocarbon,PAHs)具有强致癌性,极大威胁着人类身体健康。因此,寻找一种高效、精确的多环芳烃浓度检测方法十分必要。采用FS920荧光光谱仪分析了苯并(k)荧蒽(BkF)、苯并(b)荧蒽(BbF)、苯并(a)芘(BaP)混合溶液的荧光光谱特性。发现在激发波长260~400 nm、发射波长300~500 nm范围内,混合溶液的荧光光谱重叠严重。当混合物浓度配比不同时,荧光特性也存在很大差异。针对光谱图不能直接反映混合物各组分浓度的特点,将人工蜂群(ABC)算法优化的径向基函数(RBF)神经网络应用于浓度检测中,对比分析普通RBF和ABC-RBF神经网络模型。结果表明,ABC-RBF神经网络模型预测误差相对较小,训练到95次时,均方差精度达到10~(-3)。BkF、BbF和BaP的回收率平均值分别为99.20%、99.12%和99.23%,证明此网络适用于检测多环芳烃溶液,为检测多环芳烃浓度提供了一种快速、有效的新方法。
[Abstract]:Polycyclic aromatic hydrocarbon (PAHs) has a strong carcinogenicity and a great threat to human health. Therefore, it is necessary to find an efficient and accurate method for detecting the concentration of polycyclic aromatic hydrocarbons. The FS920 fluorescence spectrometer is used to analyze the fluorescence light of benzo (k) fluoranthene (BkF), benzo (b) fluoranthene (BbF), benzo (a) pyrene (BaP) mixed solution. It is found that in the range of excitation wavelength 260~400 nm and emission wavelength 300~500 nm, the fluorescence spectrum of the mixed solution overlaps seriously. When the mixture concentration is different, the fluorescence characteristics are also very different. The radial basis function optimized by artificial bee colony (ABC) algorithm can not directly reflect the characteristics of the mixture concentration of the mixture. (RBF) the neural network is applied to the concentration detection, comparing and analyzing the common RBF and ABC-RBF neural network models. The results show that the prediction error of the ABC-RBF neural network model is relatively small. When the training to 95 times, the mean square deviation precision reaches 10~ (-3).BkF, BbF and BaP are 99.20%, 99.12% and 99.23% respectively. It is proved that this network is suitable for detection. Polycyclic aromatic hydrocarbons (PAHs) solutions provide a fast and effective method for detecting PAHs concentration.
【作者单位】：燕山大学河北省燕山大学测控技术与仪器重点实验室;
【基金】：国家自然科学基金(61201110)资助项目~~
【分类号】：O657.3;TP183

【相似文献】