乙基橙偶氮苯聚合物的全光开关特性曲线拟合中的应用

Application of neural network in the curve fitting of all optical switching of amorphous copolymer containing azobenzence groups

BP神经网络通过调节连接权重可以实现以任意精度逼近非线性函数,利用这一特点可以对非线性函数关系进行拟合。偶氮苯聚合物的全开关特性曲线是非线性,很难用数学函数表达式来描述。因而本文首先介绍神经网络的基本原理和BP算法神经网络,然后BP神经网络应用于的全光开关特性曲线拟合,在MATLAB环境下,利用实验数据进行了实验测试,结果表明该方法处理数据精度高,拟合效果好。

BP neural network can implement approximating nolinear functions by arbityary accuracy through regulating variable weight connection, this character can fit nolinear function relations. But all optical switching proeries of azobenzene groups is nolinear function, and it is very difficultly to describe with mathematics function expression. Thus the basic principle of the artificial neural network in introduced at first. The back propagation algorithm neural network is described in detail and the application of BP neural network in fitting the curves of all optical switching properies of azobenzene groups. Through training and testing using the data of experiment under MATLAB, The result shows this method has the high precision of processing result,good effect fitting.