The Application of Multi-objective Genetic Algorithm in the Modeling of Thermal Error of NC Lathe

Abstract

A modeling method based on multi-objective genetic algrithm (MOGA) for thermal error of NC lathe is proposed in this paper. Firstly, a coupling analysis method on component thermal deformation of the machine tool is used to determine the positions of equivalent temperature measurement points and establish a estimation model of thermal errors according to the physical characteristics of each component. Then one objective function is formulated based on this estimation model while the other one is determined by the testing data of the thermal error experiments. At last MO-GA is applied and a thermal error model with high robustness is obtained.