To predict aircraft taxiing estimated time of arrival（ETA）， reduce conflicts， and improve the efficiency of the airport， this paper uses the Kalman filter algorithm to preprocess historical trajectory data of an airport. In order to measure the distance between trajectory samples， three kinds of features are synthesized for clustering of airport historical trajectory data， including the aircraft taxiing period and the number of surface aircraft. In addition ，we refer to the dynamic time warp （DTW） algorithm to extract the difference features of the trajectory. The Euclidean distance of two sample features is taken as their similarity. Initial clustering center is determined based on the divided difference maximum principle. The K-means algorithm is used to cluster samples， and the cluster with the highest matching degree is selected according to the time period of the aircraft to be planned and the number of aircraft operating on the surface. The trajectory sequence of the cluster’s center sample and the static path planned by the tower are combined to predict the aircraft taxiing ETA. By comparing and analyzing the actual trajectory data with the predicted taxiing ETA， the good performance of predicting the aircraft taxiing ETA in this paper is verified.