Linear servo system thermal error modeling method and compensation system based on energy balance

Abstract

The invention discloses a linear servo system thermal error modeling method based on energy balance. The method comprises the following steps of 1) constructing an LSTM neural network model according to an energy balance equation of a linear servo system; 2) collecting original operation data of the linear servo system, and performing wavelet threshold denoising on armature current in the original operation data; 3) generating an input data vector from the original operation data subjected to wavelet threshold denoising processing, and generating a data file in an npy format from the input data vector for model training; 4) training the LSTM neural network model to obtain a linear servo system thermal error model; and 5) predicting the thermal error delta L tau+1 of the linear servo system by using the thermal error model of the linear servo system. The invention further provides a linear servo system thermal error compensation system based on energy balance. The linear servo system thermal error compensation system comprises a data acquisition system, a data processing system, a thermal error prediction system, a CNC control system and a servo control system.

Description

technical field [0001] The invention belongs to the technical field of mechanical error analysis, in particular to an energy balance-based linear servo system thermal error modeling method and compensation system. Background technique [0002] The thermal expansion of the shaft system has a hysteresis effect, and the hysteresis effect is significant for the shaft system. Hysteresis effects are important for robust modeling of thermal errors, which lead to time-varying, nonlinear and non-steady-state behavior of thermal expansion temperature behavior. The hysteresis effect means that the current thermal error not only depends on the current input, but also has memory characteristics for the historical thermal effect and is significantly affected by the historical thermal effect. Therefore, the influence of historical thermal information on the current thermal error should be considered in the thermal error modeling of the shaft system. Traditional thermal error models canno...

AI Technical Summary

Problems solved by technology

Traditional thermal error models cannot apply past thermal information, resulting in poor predictive performance and poor robustness

Images