论文部分内容阅读
文章介绍了基于RBF神经网络的短时段交通量预测模型,给出了模型的具体计算流程,利用计算软件Matlab7.0编制模型算法程序,并分别利用该模型与常用的BP神经网络针对高速公路所采集的数据进行了仿真预测比较,对预测结果进行了比较分析。预测结果表明RBF神经网络预测方法较BP网络方法有较大改进,网络具有在线预测、训练速度快、预测精度高等特点,能够满足路网调度对短时段交通流预测的需求。
This paper introduces a short-term traffic prediction model based on RBF neural network, and gives the specific calculation flow of the model. Using the calculation software Matlab7.0 to compile the model algorithm program, and using the model and the commonly used BP neural network for expressway The collected data are simulated and compared, and the predicted results are compared and analyzed. The prediction results show that the RBF neural network prediction method has a greater improvement than the BP network method. The network has the characteristics of online prediction, fast training speed and high prediction accuracy, and can meet the demand of short-period traffic flow prediction by the network scheduling.