中文摘要：

研究交通车辆的高效调度的问题.随着车辆交通复杂程度的增加,调度过程中车辆的可调度流量特征变得复杂,呈现了非线性变化.传统的车辆调度方法都是以流量特征为基础进行调节,受到交通流量的非线性变化影响,效率偏低.为解决上述问题,在传统的小波神经网络预测交通调度模型中,引入了混沌重构的混沌时间序列预测,并且加入一种基于混沌算法的快速交通信息学习算法,在实际小波神经网络调度模型的建立中,以交通流量混沌时间序列为基础,确定网络模型的输入神经元个数、隐含层个数以及神经元个数,克服非线性的干扰.仿真结果表明,改进模型对车辆的调度精度和改进效果较好.

英文摘要：

The efficient scheduling of traffic vehicle was researched in the paper. With the increase of vehicle traffic complexity, sehedulable flow characteristics of the vehicle become complex, and the process of scheduling presents a nonlinear change. Without considering the chaos characteristics in traffic control, traditional vehicle scheduling method based on flow characteristics is affected by nonlinear changes in traffic flow, and the efficiency is low. To solve this problem, the chaotic time series prediction of chaos reconstruction was introduced in the traditional traffic scheduling model based on wavelet neural network prediction, and a rapid traffic information learning algorithm based on chaos algorithm was added. In the establishment of actual wavelet neural network scheduling model, on the basis of traffic flow chaos time series, we determined the number of input neurons, the numbers of hidden layers and number of neurons in the network model. The simulation experiment results show that the improved model is better in the scheduling precision and can improve the effect of vehicles.