基于RBF神经网络的复杂系统的建模与优化

针对BP神经网络算法在用于函数逼近时,存在着收敛速度慢、易陷入局部极小的不足,提出基于RBF(径向基函数,Radail Basis Function)神经网络的建模与优化方法,并以典型复杂系统联合制碱工业过程为例,利用神经网络算法的强大学习能力建立RBF神经网络模型,并进行优化研究。以联合制碱工业过程中的煅烧工段为例进行了仿真研究,仿真结果显示RBF神经网络的优越性,效果令人满意。

Modeling and optimization of complex systems based on RBF neural network

The BP neural network algorithm used in approximation of function has two shortcomings which are slow convergence rate and easily falling into the local. In order to solve the problems, a new method is proposed in this paper and is complicated on a typical complex system-the synthetic ammonia decarbornization industrial process. The main issue of the proposed approach is on modelling and optimization of the RBF （Radial Basis Function） neural network. The learning capability of RBF neural network on processing nonlinear system is used, and the modelling and optimization of RBF neural network is present. Furthermore, some simulation studies with calcinations section have been done. The simulation result shows the superiority of the RBF neural network.