Abstract: This paper uses the hierarchical structure and the fuzzy neural networks(FNN) theory to solve the real time arterial co-ordinated control problem. The traffic artery is regarded as a large scale system. The subsystems are the intersections in the arterial road and their splits are adjusted on-line by means of the FNN methods. The traffic volume data measured from every intersection are fed to the co-ordinator and these data are used to determine the signal cycle and the offset in the arterial road. The objects of the co-ordinator and subsystems all are to make the average queue in the front of each intersection shortest. The simulation results show that the method proposed by this paper can decrease the average queue length effectively and thus the vehicle delay is reduced.