汽车保有量预测对城市交通的发展方向有直接的参考意义,通过分析影响城市汽车保有量的因素,找出了城市人口、GDP、公共交通服务水平等九个主要的因素,并对这些因素进行分析。同时建立了预测城市汽车保有量的BP神经网络模型。为了保证模型的收敛,在进行实例分析的时候引入主成分分析法将九个因素减少为五个因素,并进行了预测,预测精度比较高。 Prediction of car ownership has direct reference meaning to the development direction of urban traffic. By analyzing the factors that affect the car ownership in urban areas, we find out nine main factors such as urban population, GDP and public transportation service level, and make these factors analysis. At the same time, a BP neural network model for predicting the car ownership in cities is established. In order to ensure the convergence of the model, the principal component analysis is introduced to reduce the nine factors into five factors when performing the case analysis. The prediction is made and the prediction accuracy is relatively high.