Aiming at the problems of complex energy consumption of industrial robots, strong dynamics and unpredictable real-time power, based on the energy consumption analysis of permanent magnet synchronous motors, servo drives and other functional components in the robot system, an equivalent power model for industrial robots was proposed. The model established a mapping relationship between the robot's loss power, motor torque, and motor angular velocity through high-order polynomials. The coefficients in the model were solved by least squares, and power prediction could be performed under unknown robot motor parameters. The results show that the root mean square relative error between the theoretical calculation value and the experimental measurement value based on the power model is 8.11%, which proves the correctness of the power model and identification parameters.