The invention belongs to the technical field related to numerical control, and discloses a feed speed optimization method based on main shaft data simulation. The feed speed optimization method basedon the main shaft data simulation comprises the following steps: (1) a numerical control system interpreter processes a G code of a part line by line to obtain a data block and an interpolation pointfile with a line number, and then calculates and obtains the cutting depth; (2) the obtained process parameters are used as an input, and a measured main shaft power corresponding to the process parameters is used as an output, so as to construct a main shaft power neural network prediction model; and meanwhile, a multi-objective optimization model is constructed; and (3) an optimal feed speed solution set of the multi-objective optimization model is solved based on the main shaft power neural network prediction model, the process parameters, and the interpolation point file, and the optimal feed speed is then selected in the optimal feed speed solution set according to actual processing requirements. The feed speed optimization method based on the main shaft data simulation has good applicability and good flexibility; the precision is improved; and the feed speed optimization method based on the main shaft data simulation is simple and easy to implement.