Thermal displacement prediction model of SVR high-speed motorized spindle based on SA-PSO optimization

Abstract

In view of the problem that a lot of heat is generated inside the motorized spindle when it is working, which causes thermal errors and affects the processing quality, this paper optimizes the Support Vector Regression through the particle swarm algorithm to establish a thermal displacement model of the motorized spindle to predict the thermal elongation change, To thermally compensate the motorized spindle. The sensors are arranged to collect the temperature rise data and thermal displacement data of the motorized spindle at different speeds according to the temperature field distribution of the motorized spindle's steady-state temperature simulation analysis results. Taking the temperature data as the training set and the thermal displacement data as the feature set, the support vector regression machine based on improved particle swarm optimization of the simulated annealing algorithm (SA-PSO-SVR) is used to establish the thermal displacement model of the motorized spindle. The results show that the SA-PSO-SVR model can predict the thermal elongation change, clarify the thermal error system real-time motorized spindle thermal displacement change, compensate for the thermal error, and improve the machining accuracy of the motorized spindle.

Keywords

• High-speed motorized spindle
• Particle swarm optimization
• Support vector regression machine
• Thermal displacement modeling