Display omitted •A refined neural network model of hydro-turbine is established and verified.•An accurate quantitative evaluation of system damping is proposed.•The effect of operating condition on the hydraulic-mechanical damping is studied.•The relation between the control stability and damping is revealed.•The hydraulic-mechanical damping is decomposed. Hydropower is a renewable energy source with flexible and rapid regulation. Its efficient utilization is of significance in improving the stability of the electric power grid and its ability to absorb renewable energy. The current day power grid is facing security challenges due to its composition and structural changes. To understand the damping mechanism of the hydropower unit on the power grid, a new quantitative evaluation method is proposed for the analysis of the damping characteristics of the hydropower unit under full operating conditions and control parameters. In order to improve the simulation accuracy, firstly a hydro-turbine regulation system simulation platform for quantitative analysis is built and a refined hydro-turbine model using a polynomial correction neural network is proposed. Secondly, to realize the damping analysis of the hydropower unit, an accurate quantitative evaluation method based on gradient-descent algorithm is proposed. Finally, taking a large hydropower station in China as an example, damping of the hydropower unit under full operating conditions (FOC) and control parameters is computed and analyzed considering two control modes. The results show that the damping of the hydropower unit on the power grid changes from −1.1415 to 0.4402 with a certain regularity under FOC and increases with the increase of control parameters. The damping under power control mode is generally better than that under opening control mode. Conclusions drawn from an in-depth analysis of the damping mechanism of hydropower units can provide necessary theoretical guidance and application value for optimizing the operation mode of the units.