Estimation of Thermal Deformation of Machine Tool by Applying Neural Network. Improvement of Estimation Accuracy by Utilizing Time-Series Data of Temperature on Machine Surfaces.

Abstract

Neural network models are constructed to estimate thermal deformation of a vertical machining center by employing time-series data of temperature measured near the heat sources. The relative displacement between the rotating tool and the workpiece caused by the heat generated due to spindle rotation was estimated by utilizing several neural network models. It is shown through the experiments that the points of temperature measurement can be reduced without sacrificing the estimation accuracy by utilizing the time-series data of temperature.