The establishment of traffic model suitable for ITS is an important aspect to promote the rapid development of urban traffic. The paper develops an urban traffic particle model based on practical observation of traffic flow, in which intersection is regarded as elementary granular unit and there are decoupled relations among them. Then the exercise mechanism of traffic flow is introduced, and a correlative model and its decoupled method are argued between units. Finally the paper takes practical data of two adjacent intersections for example. Signal cycle, traffic flows of each phase are used to analyze stability of elementary unit as time scale, state variables. Through computer simulation and analysis, modeling distributed traffic particle flow is feasible; the model provides theories basis for distributed architecture of intelligent transport system of cities.

Identifying and predicting the situation of traffic flow play an important role in traveler information broadcast and real-time traffic control. In this paper, to pick up the effective characteristic parameters of traffic, the features and the transition between different situations in traffic are studied and analyzed, A hybrid Elman neural network and Fuzzy techniques are good at working out the non-linear problem and identifying the state of system, so they can apply to predict and distinguish the traffic situation in short term. As a result, it proves that there are some advantages, e.g. simple configuration, good prediction and exact identification. So it is fit to online predict and identify the traffic flow in urban expressway.