BP神经网络在非线性系统建模中的应用

Application of BP Neural Network in Creating Modeling of Non-liner System

介绍了采用BP神经网络建立系统数据间的非线性关系的数学模型,利用三层BP网络,结合Matlab神经网络工具箱,模拟肼与过氧化氢的反应过程,将预测的结果和实验数据作比较,结果表明该模型的预测值和试验值吻合的很好,是一种可行的数据处理方法。

A mathematical model consisted in data of non-Liner system in BP neutral network was introduced. In this paper, three layers BP neural network and Matlab neural network toolbox were used to simulate the reaction of H2O2. Compared with the predicted results and the experimental data, the predicted values of this model can fit the highest real temperature well at various conditions, and this method of data processing was feasible, which were proved.