Abstract: On the basis of network training, neural network computing models of maximum fluctuation of water surface in ship lift chamber with tumble gate operating (NNCM-MFWS-SLC-TGO) were built through the principle of artificial neural networks. The characteristics of the models were tested according to the experiment data from Yantan Ship Lift and Three Gorges Ship Lift. And the result indicates that the models may be applied to forecast maximum water level fluctuation in ship lift chamber with tumble gate operating. Furthermore, a new way and method about the study on ship lift chamber hydrodynamics were provided.