Thermal error in machine tools is one of the most significant causes of machining errors.This paper presents a new modeling method for machine tool error.Minimal-resource allocating networks (M-RAN) are used to establish the relationships between the temperature variables and thermal errors.Pt-100 thermal resistances and eddy current sensors are used to measure the temperature variables and the thermal errors respectively.A machining center is used to experiment.The test results show that method with minimal-resource allocating networks can predict the thermal errors of the machine accurately.
展开▼
