神经网络具有识别复杂非线性系统的特性,比较适合于交通领域应用。BP神经网络是一种典型的人工神经网络,BP算法依梯度下降搜索法可以保证在有限次搜索后快速找到全局最优;而遗传算法的全局寻优能力,可防止陷入局部极小点。本文将二者结合起来,建立遗传-神经网络,建立了结合实时交通信息的动态交通流量预测模型。 Neural networks have the characteristics of identifying complex nonlinear systems and are more suitable for traffic applications. BP neural network is a typical artificial neural network. According to the gradient descent search method, BP algorithm can guarantee to find the global optimum quickly after a finite number of searches. However, the global optimization ability of genetic algorithm can prevent it from falling into a local minimum. In this paper, the two are combined to establish a genetic-neural network and establish a dynamic traffic flow prediction model combined with real-time traffic information.