Machine tool thermal error modeling method based on multi-element projection pursuit clustering

Abstract

The invention relates to a data processing method in the technical field of precision processing technologies, and specifically relates to a machine tool thermal error modeling method based on a multi-element projection pursuit clustering algorithm. The method comprises the steps of: (1) carrying out a detection experiment of a machine tool temperature field and thermal deformation; (2) establishing a multi-element projection pursuit clustering model and carrying out parameter calculation; (3) designing and developing a thermal error compensation system; and (4) testing prediction performance of the model. The method provided by the invention has the advantages of high prediction precision, simple calculation and high robustness. The thermal deformation of a main shaft of the machine tool is effectively controlled, and the machining precision of the machine tool is further improved.

Description

technical field [0001] The invention relates to a data processing method in the technical field of precision machining, in particular to a numerically controlled machine tool thermal error modeling method based on multivariate projection tracking clustering. Background technique [0002] The thermal deformation caused by the uneven temperature rise of various parts of the machine tool leads to changes in the relative position between the tool and the workpiece to be processed, and the resulting thermal error is the largest error source of the machine tool, accounting for 70% of the total error of the machine tool. With the continuous development of modern manufacturing technology, the effect of eliminating thermal deformation by controlling the main heat source or changing the structure of the machine tool is no longer obvious, and the implementation of thermal error compensation for machine tools is developing rapidly with lower manufacturing costs and significant economic b...

AI Technical Summary

Problems solved by technology

The regression orthogonal modeling method combines the traditional modeling theory with engineering judgment, increases the modeling constraints, reduces the sensitivity to the temperature sensor position, and improves the robustness of thermal error modeling. However, once the measurement error occurs , the accuracy of the model is difficult to guarantee

Using stepwise regression and partial least squares regression, the mapping relationship between the temperature field of the machine tool and the thermal error can be established, and the modeling accuracy is high, but the model is limited to a specific machine tool, and the robustness is poor

Neural network is another effective way to establish a machine tool thermal error model, but there are many heat sources in the machine tool, and this method is difficult to solve the coupling problem between various temperature variables

Images