BP神经网络在磷酸盐溶液紫外吸收光谱中的应用  

Application of BP Neural Network Algorithm in the UV Absorption Spectrum of the Phosphate Solution

作　　者：王睿[1] 余震虹[1] 鱼瑛[1] 

机构地区：[1]江南大学通信与控制工程学院通信研究所

出　　处：《光谱实验室》2009年第4期822-826,共5页Chinese Journal of Spectroscopy Laboratory

摘　　要：利用紫外分光光度法测定磷酸盐溶液的光谱,经过转换得到吸光度与溶液浓度的非线性关系,使用BP神经网络算法处理此非线性问题。Matlab语言中的神经网络工具箱提供了许多有关神经网络设计、训练和仿真的函数来实现BP网络,使应用BP网络来解决此类问题变得方便和有效。实验证明Levenberg-Marquardt法网络收敛速度最快,量化共轭梯度法最慢。本文还运用Matlab中的数据拟合法与BP神经网络法进行比较,前者虽然得到拟合曲线关系式,但较为复杂,工作量大。因此,BP神经网络法更适合于解决此类问题。The ultraviolet spectrophotometric non-linear relationship between absorbance and the concentration of solution was treated by the BP neural network with the neural network toolbox in Matlab,which provides many of the neural network design,training and simulation functions,and is convenient and effective that bestowing the BP network to solve the problem. The results show that the network convergence rate of the Levenberg-Marquardt method is the fastest,and the rate of the quantized conjugate gradient method is the slowest. The BP neural network is more suitable to resolve this issue.

关 键 词：磷酸盐溶液 紫外分光光度法 BP神经网络 MATLAB语言 

分 类 号：O657.32[理学—分析化学]