提出一种高速公路动态交通系统的神经网络预测控制方法．根据高速公路的实际背景导出其非线性动态模型，利用神经网络及辨识的串并联结构来建立模型的映射，在此基础上给出控制变量带有上下界约束的预测控制算法．根据实测数据进行了仿真研究，结果表明算法是有效的．因而为解决高速公路的动态控制问题提供了一种新的方法． A neural network predictive control method for expressway dynamic traffic system is proposed. According to the actual background of the expressway, the nonlinear dynamic model is derived. The neural network and the identified series-parallel structure are used to establish the mapping of the model. On this basis, a predictive control algorithm with upper and lower bound constraints on the control variables is given. According to the measured data, simulation results show that the algorithm is effective. Therefore, it provides a new method to solve the dynamic control of expressway.