In view of the problem that the dredging supervision is difficult to cover all ships all day and cannot achieve real-time monitoring,we analyze the high frequency data of AIS(automatic identification system)of a cutter suction dredger,including the dynamic longitude,latitude,speed,heading direction,etc.,and study the identification and prediction of ship construction trajectory by using the DBSCAN(density-based spatial clustering of applications with noise)clustering algorithm to roughly identify the construction area,using the LOF(local outlier factor)algorithm to remove the non-construction trajectory in the trajectory,and using the time series ARIMA model to predict the ship construction trajectory.The results show that DBSCAN clustering algorithm combined with the LOF algorithm is reasonable and feasible,and ARIMA(autoregressive integrated moving average)model is characterized by high accuracy,real-time and easy realization.