Research on Machining Error Control Method Driven by Digital-twin Model of Dynamic Characteristics of Machining System

Abstract

The position of each component structure in the machining space of the machining system directly affects the machining quality of the workpiece. In this paper, RBF neural network is used to study the spatial dynamic characteristics of the translational axes of five-axis CNC machine tools. It is the basis for building an evolvable knowledge base. Process evaluation, information feedback, and iterative optimization of thin-wall parts were carried out using digital-twin technology. Firstly, the model simulation of the translational machining space of a three-dimensional five-axis CNC machine tool is carried out by using the finite element method. The RBF neural network predicts the natural frequency of a translational machining space dynamic characteristics. It is further used to construct the dynamic characteristic spectrum of the translational space of CNC machine tools. Secondly, the machine tool flush space cutting process is built with a digital-twin system to optimize the iterative mechanism for machining process optimization. Finally, the method’s effectiveness was verified by experiments on milling thin-walled parts on a dual-turntable five-axis CNC machine and by contouring error measurement experiments. The results show that the average error of the optimized thin-wall contour is reduced by 26.9%. The iterative mechanism can continuously optimize the machining error and improve the machining accuracy. The iterative mechanism can continuously optimize the machining error and improve the machining accuracy.