The thermal behaviour of a CNC machining center was modelled by both Multiple Regression Analysis and Artificial Neural Network techniques. To this end, the indirect approach, in which the thermal deformations of the machine structure are related to temperature measurements at representative points, was used. Temperature was monitored using 27 thermocouples positioned in different points of the machine structure, whilst the thermal expansion of the Y-axis ball screw was measured using a proximity transducer. The data base to build the predictive models of the thermal deformation was obtained by imposing to the machining center different working cycles. The thermal expansion of the Y-axis ball screw has been successfully predicted.
Thermal error prediction in a machining center using statistical and neural network–based models
SIMONCINI, MICHELA
2004-01-01
Abstract
The thermal behaviour of a CNC machining center was modelled by both Multiple Regression Analysis and Artificial Neural Network techniques. To this end, the indirect approach, in which the thermal deformations of the machine structure are related to temperature measurements at representative points, was used. Temperature was monitored using 27 thermocouples positioned in different points of the machine structure, whilst the thermal expansion of the Y-axis ball screw was measured using a proximity transducer. The data base to build the predictive models of the thermal deformation was obtained by imposing to the machining center different working cycles. The thermal expansion of the Y-axis ball screw has been successfully predicted.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
