Abstract: The main intersection signal setting standard and basis are obtained through the establishment of microscopic traffic model, but the complexity of model calibration and calculation result in poor reliability of the data information, so it does not apply to the actual situation. Therefore, this paper directly using the data of the actual collection, the FCM( Fuzzy C-Means) clustering method is adopted to identify the roundabouts traffic state according to the headway changes inner and outer ring road traffic flow to provide the time basis of signal control for traffic managers. Finally, the method is verified on the VISSIM platform. The results show that the method can accurately distinguish the running state of the intersection traffic, provide reliable signal control basis for traffic management.