This paper focuses on traffic flow forecasting approach based on soft computing tools. The soft computing tools used is Particle Swarm Optimization (PSO) with Wavelet Network Model(WNM). The forecast of short-term traffic flow in timely and accurate is one of important contents of intelligent transportation system research. The modelling of traffic characteristics and the prediction of future traffic flow are the first steps to efficient network control and management. The real traffic data is used to demonstrate that the PSO algorithm combined with WNM is effective for traffic flow forecasting. The simulation results demonstrate that the proposed model can improve prediction accuracy and outperforms other compared methods. A new hybrid model between wavelet analysis and a neural network: wavelet network model absorbs some merits of wavelet transform and artificial neural network.