Authors: Jian Han Liping Wang Ningbo Cheng Haitong Wang
Publish Date: 2011/09/15
Volume: 60, Issue: 5-8, Pages: 463-472
Abstract
Thermal deformation in machine tools is one of the most significant causes of machining errors A new approach to predict the thermal error of machine tool is proposed The temperature variables and the thermal errors are measured using the Pt100 thermal resistances and eddy current sensors respectively Fuzzy cmeans clustering method is conducted to identify the temperatures and the representative as an independent variable are selected meanwhile it eliminates the coupling among the variables The learning and prediction of the thermal errors is achieved using minimalresource allocating networks by treating the issue as functional mapping between the thermal shifts and the temperature variables The network is made to predict the error map of a machining center A traditional radial basis function model is introduced for comparison The experiment result shows that the fuzzy cmeans clustering method and minimalresource allocating networks combination is a fast and accurate method for thermal error compensation in machine tools
Keywords: