Prediction of temperature field in the whole process of instantaneous and steady state of high-speed motorized spindle

The temperature rise of the high-speed motorized spindle directly affects the machining accuracy of the machine tool, making it crucial to accurately understand the dynamic changes in temperature during spindle operation in order to improve machining accuracy. This paper proposes a prediction model for the temperature field of the high-speed motorized spindle, considering both the instantaneous and steady-state phases, to accurately predict the dynamic changes in temperature rise during spindle operation. Initially, the steady-state heat transfer coefficients and the instantaneous heat generation at random moments during spindle operation are optimized using the Grey Wolf Optimization algorithm. Subsequently, a prediction model is established based on the identified instantaneous heat generation, using a BP neural network, to enable full-cycle prediction of the heat generation of the motorized spindle. Finally, experimental verification demonstrates that the proposed prediction model achieves a prediction accuracy of 98%.