Hydrologic model is a significant tool to simulate the water cycle, while there is great uncertainty depending on single model simulation which makes ensemble hydrologic model simulation become inevitable trend. Three lumped hydrological models were selected to conduct watershed monthly runoff ensemble simulation, and the expectation maximum algorithm was used to estimate the parameters of the BMA in order to obtain BMA mean simulation and 90% uncertainty interval. The result using the observed data of the Wuliehe watershed indicates that the BMA method can not only provide simulation with higher precision through mean simulation, but also provide quantitative evaluation of the model structure through confidence interval which could offer rich information of the runoff simulation.