Milling parameter optimization method for thin-walled workpiece

Abstract

The invention discloses a milling parameter optimization method for a thin-walled workpiece. The method comprises the steps that firstly, creating a BP neural network to complete establishment of a workpiece maximum machining deformation prediction model; establishing a multi-objective optimization model of milling parameter optimization by taking a machine tool, a cutter and machining deformationas constraints, taking machining time and cutting energy consumption as optimization objectives and taking a cutting speed, a feed rate of each tooth, an axial cutting depth and a radial cutting width as optimization variables; converting the milling parameter optimized multi-objective optimization model into a single-objective optimization model by using a weighted summation method so as to realize multi-objective integration; and using a genetic algorithm as an optimization algorithm to carry out optimization solution on the optimization target model to optimize milling parameters. The influence of machining deformation of the thin-walled workpiece on an optimization result is considered while the machining time and the cutting energy consumption are taken as optimization objectives tooptimize the cutting parameters, so that the optimization result is more accurate, the problem of conservative milling machining parameters of the thin-walled workpiece at present is solved, and machining efficiency of the workpiece is improved.

Description

technical field [0001] The invention relates to a method for optimizing machining parameters, in particular to a method for optimizing parameters for milling of thin-walled parts, involves genetic algorithms and BP neural network prediction, and belongs to the technical field of numerical control machining. Background technique [0002] With the continuous development of material science and numerical control technology, thin-walled parts have been widely used in aerospace, automotive molds and other fields. However, thin-walled parts have common characteristics such as variable specifications and sizes, complex shapes and structures, and weak rigidity. They are easy to deform during processing and difficult to process. [0003] At present, when domestic manufacturing units process thin-walled parts with high precision requirements, they often adopt conservative cutting parameters and increase the grinding process, which generally has the problems of low processing efficienc...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem of low efficiency of thin-walled parts in the process of CNC milling, and propose a method for optimizing the parameters of thin-walled parts milling. performance parameters to establish cutting parameter optimization model

At the same time, the present invention considers the influence of processing deformation, uses BP neural network to establish the maximum deformation prediction model of the workpiece, and uses genetic algorithm as a constraint function to optimize the processing parameters, which can improve the current thin-walled parts processing parameters that are too conservative and the processing quality is difficult to guarantee problems, to achieve efficient production of thin-walled parts

Images