Nonlinear autoregressive neural network machine tool thermal error modeling method with external input

Abstract

The invention discloses a numerical control machine tool thermal error modeling method. The method comprises the steps of 1, testing machine tool temperature and thermal error data; 2, selecting a keytemperature measuring point as the input of a thermal error model by adopting an information entropy algorithm; 3, training an NARX model; and 4, calculating a real-time thermal error compensation value of the machine tool through the model. According to the method provided by the invention, a temperature measurement point which is most relevant to a thermal error can be found by adopting a relative information entropy algorithm; the NARX model can overcome the hysteresis characteristic of a temperature-thermal error, and has the advantages of high prediction precision and high adaptability.

Description

technical field

[0001] The invention belongs to the technical field of thermal error compensation of precision numerical control machine tools, and relates to a thermal error modeling method of a machine tool with an external input nonlinear autoregressive neural network NARX (Nonlinear AutoRegressive with eXternal input neural network). Background technique

[0002] During the working process of the machine tool, due to factors such as spindle heating, frictional heat generation of moving parts, cutting heat and environmental temperature changes, various components of the machine tool will be thermally deformed, resulting in changes in the ideal position of the cutting tool and the workpiece, resulting in machining errors. At present, due to the improvement of machining and manufacturing technology, the geometric error of precision machine tools is small, and thermal error has become the most important factor affecting its accuracy. Relevant studies have shown that thermal ...

Images