Aiming at energy consumption calculation in radial tire die micro-milling,taking spindle speed,feed per tooth and cutting depth as variables,an energy consumption experiment for tire die micro-milling was designed.A prediction model for energy consumption in micro-milling based on BP neural network was built according to the experimental data.By improving the activation function of the prediction model,the prediction accuracy of the energy consumption in micro-milling was improved.The results show that the proposed prediction model is effective and can be used to predict energy consumption under different combinations of milling parameters.