最小二乘支持向量机在对羟基苯甲酸甲酯钠荧光检测中的应用
发布时间：2019-05-30 03:19
【摘要】：对羟基苯甲酸甲酯钠是一种常见的食品添加剂,如果长时间食用或者超量食用会对人体造成一定的危害。采用FS920荧光光谱仪对对羟基苯甲酸甲酯钠橙汁溶液和水溶液进行检测,实验结果表明两者的特征峰发生了明显的变化。经分析得出,对羟基苯甲酸甲酯钠橙汁溶液的荧光光谱受到橙汁荧光特性干扰,一定浓度范围的溶液光谱图存在较大差距,对羟基苯甲酸甲酯钠浓度与荧光强度之间的关系复杂。为了精确地检测橙汁中对羟基苯甲酸甲酯钠的浓度,结合荧光光谱法与最小二乘支持向量机,建立了橙汁溶液中对羟基苯甲酸甲酯钠的检测模型,使用改进的粒子群优化算法得到影响模型性能的正则化参数和核函数。实验得到了较为理想的结果,与普通反向传播(BP)神经网络、基本粒子群寻参的最小二乘支持向量机等方法相比,该方法性能最优,得到的平均回收率为97.05%,平均相对误差为2.71%,均方根误差为3.04%,模型输出与真实值之间的相关系数是0.9999。该方案可以做为橙汁中对羟基苯甲酸甲酯钠浓度的精确检测方法。
[Abstract]:Sodium p-hydroxybenzoate is a common food additive, if eaten for a long time or excessive consumption will cause certain harm to the human body. FS920 fluorescence spectrometer was used to detect the orange juice solution and aqueous solution of sodium p-hydroxybenzoate. The experimental results show that the characteristic peaks of the two solutions have changed obviously. The results show that the fluorescence spectrum of sodium p-hydroxybenzoate orange juice solution is interfered by the fluorescence characteristics of orange juice, and there is a big gap in the solution spectrum in a certain concentration range. The relationship between the concentration of sodium p-hydroxybenzoate and fluorescence intensity is complex. In order to accurately detect the concentration of sodium p-hydroxybenzoate in orange juice, a model for the determination of sodium p-hydroxybenzoate in orange juice solution was established by combining fluorescence spectroscopy and least square support vector machine. The regularization parameters and kernel functions that affect the performance of the model are obtained by using the improved particle swarm optimization algorithm. The experimental results are satisfactory. Compared with the ordinary back propagation (BP) neural network and the least square support vector machine for basic particle swarm optimization, this method has the best performance, and the average recovery is 97.05%. The average relative error is 2.71%, the root mean square error is 3.04%, and the correlation coefficient between the output of the model and the true value is 0.999 9. This method can be used as an accurate method for the determination of sodium p-hydroxybenzoate in orange juice.
【作者单位】： 燕山大学电气工程学院;
【基金】：国家自然科学基金(61471312) 河北省自然科学基金(F2015203240)
【分类号】：TP18;TS207.3
本文编号：2488472
[Abstract]:Sodium p-hydroxybenzoate is a common food additive, if eaten for a long time or excessive consumption will cause certain harm to the human body. FS920 fluorescence spectrometer was used to detect the orange juice solution and aqueous solution of sodium p-hydroxybenzoate. The experimental results show that the characteristic peaks of the two solutions have changed obviously. The results show that the fluorescence spectrum of sodium p-hydroxybenzoate orange juice solution is interfered by the fluorescence characteristics of orange juice, and there is a big gap in the solution spectrum in a certain concentration range. The relationship between the concentration of sodium p-hydroxybenzoate and fluorescence intensity is complex. In order to accurately detect the concentration of sodium p-hydroxybenzoate in orange juice, a model for the determination of sodium p-hydroxybenzoate in orange juice solution was established by combining fluorescence spectroscopy and least square support vector machine. The regularization parameters and kernel functions that affect the performance of the model are obtained by using the improved particle swarm optimization algorithm. The experimental results are satisfactory. Compared with the ordinary back propagation (BP) neural network and the least square support vector machine for basic particle swarm optimization, this method has the best performance, and the average recovery is 97.05%. The average relative error is 2.71%, the root mean square error is 3.04%, and the correlation coefficient between the output of the model and the true value is 0.999 9. This method can be used as an accurate method for the determination of sodium p-hydroxybenzoate in orange juice.
【作者单位】： 燕山大学电气工程学院;
【基金】：国家自然科学基金(61471312) 河北省自然科学基金(F2015203240)
【分类号】：TP18;TS207.3
【相似文献】
相关期刊论文 前3条
1 戴丽,顾建刚;最小二乘圆法及其在原木定心中的应用[J];木材加工机械;2002年02期
2 杨延荣;杨仁杰;董桂梅;杜艳红;单慧勇;张伟玉;;红外光谱结合最小二乘支持向量机掺杂牛奶判别方法研究[J];光散射学报;2014年02期
3 李世勇;王芳;邵学广;;最小二乘支持向量回归与偏最小二乘回归建立烟草总糖NIR预测模型比较[J];烟草科技;2006年11期
，本文编号：2488472
本文链接：https://www.wllwen.com/kejilunwen/zidonghuakongzhilunwen/2488472.html
