Train station classification for passenger dedicated line

China has busy rail networks with highly complex patterns of train service. Train station is the basic element not only of passenger dedicated line but also of transport process from beginning to end. On busy congested rail, train stations play an important role. This paper presents an objective method for classifying train stations in terms of passenger information and local infrastructure. The aim of the method is to improve the performance of China Railway networks. In the present study, we propose a method for the classification of train stations based on influence factors data and the use of Self-Organizing Map (SOM). SOM is one of the most well-known neural networks with unsupervised learning rules. The SOM application classifies the train station into three clusters showing distinguishable levels. Finally, we choose a representative sample of these stations in North China to do simulation experiment. Simulation results verify the effectiveness of the proposed method.