This paper focuses on intelligent attributes of railway intelligent transportation system (RITS) to use agent-oriented G-net approach to construct the model about stations and trains in the simulation system based on multi-agent, which is called agent-oriented G-net train operation model (AGNTOM). The model integrates object-oriented approach, multi-agent technique and Petri nets analysis method, so it embodies the object-oriented concepts including class, inheritance, encapsulation, and utilizes existed Petri nets analysis tools to ensure the design of the simulation system. Furthermore, we use Petri nets theory in agent structure design and analysis phases to make multi-agent simulation system developing efficiently. Compared with existed models, AGNTOM has some prominent features including asynchronous message-passing, better description for the frame of the system, better autonomous decision-making and self-adjustment abilities.