The thermal error optimization models for CNC machine tools

Abstract

Thermal error compensation is becoming a cost-effective way to improve accuracy of machine tools especially with the increasing demand for machining accuracy in recent years. The compensation effectiveness mainly depends on the accuracy of the thermal error model. In order to explore the robustness, versatility, and prediction accuracy of the thermal error modeling, linear regression (LR) model, backpropagation (BP) network model, and radial basis function (RBF) network model are developed, analyzed, and compared. Experimental validation on a high precision four-axes machining center demonstrates that LR model has high prediction accuracy yet it has low robustness because the estimation of the regression coefficients and thermal key points are strongly correlated to the measurement data and their noise level. The neural network model is more adaptive to the case of different feed rates, rotational speeds, and ambient temperatures and has certain versatility on machine tools of the same type. The fitting accuracy and the prediction correctness of the BP network usually vary according to the hidden neurons, thresholds, and weights and cannot achieve the peak performance simultaneously. Experimental results show that the thermal error in Z axial direction could be reduced to as less as 25% of the original thermal error with compensation using the RBF model under the machining conditions of various feed rates and rotational speeds. It is also demonstrated that RBF model could improve the thermal precision in Z axle of the machine tool by about 65% under the distinct environmental temperature conditions.