Numerical control machine tool thermal error modeling method based on optimized fuzzy neural network

Abstract

The invention discloses a numerical control machine tool thermal error modeling method based on an optimized fuzzy neural network. The numerical control machine tool thermal error modeling method comprises the steps that n key temperature sensitive points affecting the thermal error are determined on a to-be-modeled numerical control machine tool, the numerical control machine tool operates in a no-load state, and the temperature x1, x2,...x<n> of all the key temperature sensitive points in the warm-up process of the numerical control machine tool and the actual error value y are collectedin real time; and then the T-S type fuzzy neural network is used for modeling the thermal error of the numerical control machine tool. The numerical control machine tool thermal error modeling methodis characterized in that before modeling, the value range of the center c<ij> and the width sigma<ij> of a subordinating degree function of the T-S type fuzzy neural network and the value range of thelink weight P<ji><1> of a consequent network and a predictor network are determined through a BP algorithm firstly, then a parameter individual is randomly taken from the range to serve as an initialpopulation individual of a GA, codes of the initial population individual are optimized to finally obtain the optimal optimized individual, namely, the optimal network parameters of fuzzy neural network. The numerical control machine tool thermal error modeling method has the advantage that the robustness and prediction accuracy of a model can be improved.

Description

technical field [0001] The invention relates to the technical field of thermal error compensation of machine tools, in particular to a thermal error modeling method of a numerically controlled machine tool based on an optimized fuzzy neural network. Background technique [0002] The history of thermal error compensation of CNC machine tools can be traced back to the 1950s. After half a century of development, thermal error compensation technology has made some progress, and some technologies have been applied to the actual production of CNC machine tools, but thermal error compensation There is still a lot of room for development in technology, and the main difficulty lies in error identification, that is, thermal error modeling. Since the thermal error of the machine tool depends to a large extent on the processing conditions and the processing environment and other factors, and the thermal error of the machine tool presents nonlinear and interactive effects, it is quite di...

AI Technical Summary

Problems solved by technology

However, the randomness of the membership function parameters in the network leads to the shortcomings of the robustness, extrapolation and real-time performance of the model.

Images