To deal with the difficulties in the amplitude-sensitive characteristics prediction，a novel fast prediction model for the dynamic characteristics of the hydraulic mount considering decoupler membrane’s stiffness variation was proposed． Firstly，the working principles and characteristics of the hydraulic mount were clarified，and the nonlinear contact force between the decoupler membrane and its metallic cage was introduced to build a lumped pa-rameter model for the hydraulic mount． Secondly，a fluid-structure-interaction finite element analysis on the decou-pler membrane was carried out，and the relationship between the equivalent displacement and the nonlinear reaction force was described with a piecewise function． Moreover，the influences of the thickness，diameter of the decoupler membrane and the gap between the decoupler and its metallic cage on the stiffness variation characteristics were in-vestigated． The BP neural networks was employed to establish the prediction model for the stiffness of decoupler membrane． Finally，the dynamic characteristics of a typical hydraulic mount with a fixed decoupler was numerically simulated，and the simulation results were compared with the measured results． The comparison results show that
the proposed prediction model is more accurate，and it can largely reduce the time needed to calculate the dynamic characteristics of the hydraulic mount．