Thermal error prediction and compensation method of CNC machine tool based on parallel deep learning network

Abstract

The invention discloses a method for predicting and compensating the thermal error of a numerical control machine tool based on a parallel deep learning network. The thermal error value of the spindle at the time point is used as sample data; B. Establish a deep learning thermal error prediction model based on a parallel deep belief network; C. Train the deep learning thermal error prediction model with the collected sample data; D. Real-time detection of heat sources of CNC machine tools Measure the temperature value of the point, and input the deep learning thermal error prediction model after training, and predict the thermal error value in real time; E, use the predicted thermal error value as the compensation translation of the origin of the coordinate system of the CNC machine tool, and realize it by offsetting the origin of the coordinate system Thermal errors are compensated in real time. The invention has the advantages of being able to accurately represent the complex mapping relationship between the monitoring temperature signal and the thermal error under the condition of large data, and is beneficial to improving the accuracy of thermal error prediction and compensation.

Description

technical field [0001] The invention relates to the technical field of precision control in the CNC machine tool industry, in particular to a method for predicting and compensating thermal errors of a CNC machine tool based on a parallel deep learning network. Background technique [0002] According to statistics, in the process of precision machining, the machining error caused by the thermal deformation of the process system accounts for 40%-70% of the total machining error, among which the thermal deformation error of CNC machine tools accounts for a large proportion, even accounting for more than 50% of the entire workpiece machining error . Reasonable and effective thermal error control is an important guarantee for improving the machining accuracy of CNC machine tools. The error compensation method is one of the most commonly used and effective methods. The premise of thermal error compensation is to establish the mapping relationship between the thermal error and te...

AI Technical Summary

Problems solved by technology

However, in addition to the problems of compensation accuracy and robustness, the thermal error mathematical model established by the traditional method has two major defects: first, it needs to master a large number of signal processing technologies combined with rich engineering practice experience to extract signal features; It is difficult to characterize the complex mapping relationship between monitoring signals and thermal errors in the case of large data using shallow models

Images