To ensure the stability of precision of the motorized spindle for five-axis machining center, the thermal error of five-axis machining center was investigated, and the temperature rise-thermal deformation model of a thin-wall ring type rotary elastomer was built on the basis of thermo-elastic property. Thus, a model of radial thermal error was con-structed. The relationship between radial error and axial error was also investigated in this paper and the total radial errors were gotten. In addition, the thermal error of the motorized spindle of five-axis machining center was measured by the ball bar in the experiment of thermal error. The motorized spindle total radial error was achieved by this experiment and radial total error analytical model. Finally, a BP neural network algorithm was introduced for thermal error prediction of five-axis machining center, and the precision of prediction of these models was compared and analyzed. The analysis shows that this method is practical and effective.