论文部分内容阅读
在对城市高速公路交通流模型深入研究的基础上 ,针对在不同环境以及时变系统中对复杂非线性大系统的控制 ,提出了一种改进的快速 RBF神经网络算法对交通流进行建模 ,克服了传统的数学模型对交通非线性大系统建模时泛化能力差的缺陷 .该算法是采用 APC- 单路径聚类算法确定 RBF神经网络结构参数的一种快速 RBF神经网络算法 ,网络训练速度快 ,效果良好 ,对实现交通流的在线建模与控制有重要意义 .文中进行了计算机仿真研究 ,结果表明了方法的有效性
On the basis of thorough research on traffic flow model of urban expressway, aiming at the control of complex nonlinear large-scale system in different environments and time-varying systems, an improved rapid RBF neural network algorithm is proposed to model traffic flow, It overcomes the defect that the traditional mathematics model has poor generalization ability for modeling nonlinear traffic large system.It is a fast RBF neural network algorithm which uses APC-single path clustering algorithm to determine the structural parameters of RBF neural network, Speed and good effect, it is of great significance to realize the on-line modeling and control of traffic flow.In this paper, computer simulation is carried out and the results show the effectiveness of the method