Abstract: The running time of pigs in submarine pipelines is an important reference for pig receiving operation. In order to identify the factors that influence the running time of pigs, the correlation degree of pipeline mileage, pipeline inlet/outlet pressure difference, gas transport capacity, pipeline inlet/outlet temperature difference, amount of interference, pig quality, oil transport capacity and water cut was calculated with the grey incidence analysis method. Meanwhile, the incidence between the influencing factors and the running time of pigs was also analyzed, and on this basis, a BP neural network prediction model of pig running time in the network structure of (8, 11, 1) was established. Then, the running time of pig in submarine pipeline was predicted and verified based on the data record of pigging operation in a submarine pipeline of the Bohai Oilfield. It is indicated that the running time of pigs predicted by the BP prediction model has an average error of 8 min and an average relative error of 12.5%. In general, the research results could provide reference for the preparation of a reasonable plan for pig receiving operation in the submarine pipelines.