Co-simulation based Digital Twin for Thermal Characteristics of Motorized Spindle

Abstract

To improve the accuracy of thermal characteristics analysis of motorized spindle, an on-line correction model of thermal boundary conditions is proposed based on BP neural network (BPNN), the experimental data and simulation results are used to build the BPNN model to correct the thermal boundary conditions of motorized spindle. A digital twin system for thermal characteristics is developed based on the co-simulation of Ansys, Matlab, and LabVIEW to accurately predict the temperature field and thermal deformation of motorized spindle under different working conditions. The experimental results show that the prediction accuracy of temperature field accuracy of the motorized spindle is 98.62%, and the prediction accuracy of thermal deformation is 96.06%, which effectively improves the simulation accuracy of thermal characteristics, and provides the basis for the error compensation and thermal optimization design.