针对智能交通系统的开发,提出一种基于灰色GM(1,1)模型和RBF网络非线性组合的短时交通流预测方法.该方法采用三层结构的RBF网络将两种单一预测方法(灰色GM(1,1)模型和RBF网络)进行了非线性组合.利用实测数据对组合方法进行了仿真实验,结果表明:非线性组合模型的预测准确性高于单独的RBF网络预测的准确性;组合模型发挥了两种单一方法各自的优势,是短时交通流预测的有效方法. Aimed at the development of ITS, a short-term traffic flow prediction method based on gray GM (1,1) model and non-linear combination of RBF networks is proposed. This method uses three-layer RBF network to compare two single prediction methods GM (1, 1) model and RBF network), and the simulation results show that the prediction accuracy of nonlinear model is higher than that of RBF neural network alone. The combined model exerts the respective advantages of the two single methods and is an effective method for short-term traffic flow prediction.