航空铝合金三维端铣表面粗糙度的LS-SVM控制研究  

The Research on the Control of Surface Roughness Based on LS-SVM for Three Dimensional End Milling of Aviation Aluminum Alloy

作　　者：李灵光[1] 王爱民[1] 王小龙[1] 

机构地区：[1]北京理工大学机械与车辆学院,北京100081

出　　处：《机械设计与制造》2015年第3期256-259,共4页Machinery Design & Manufacture

基　　金：航天二院质量与技术基础项目

摘　　要：为提高加工工件的表面质量,需要有效控制加工工件表面粗糙度,因此有必要建立精度高、泛化能力强的表面粗糙度预测模型。首先基于具有位错动力学物理基础的Z-A材料本构模型,建立航空铝合金7050材料的三维端面铣削有限元仿真模型,并设计正交试验验证有限元模型的可靠性;其次建立最小二乘支持向量机(LS-SVM)预测模型,以仿真所提供的样本数据为输入,拟合铣削参数与表面粗糙度的复杂非线性关系,实现了表面粗糙度的预测,结果表明LS-SVM模型预测的相对误差不超过6%;最后基于LS-SVM表面粗糙度预测模型得出各铣削参数对表面粗糙度的影响,为生产实际提供指导。In order to improve the surface quality of workpiece, it needs to effectively control surface roughness of the workpiece. It is necessary to establish a prediction model of high precision, strong generalization ability for surface roughness. Firstly, it simulates the 3D end milling using FEM for the 7050 materials of aviation aluminum alloy based on the Z-A material constitutive model of the dislocation dynamics physics, and verifies the authenticity of the finite element model using orthogonal experiment design; Then, it establishes the prediction LS-SVM model of surface roughness. The sample data provided by the FEM simulation imports LS-SVM model, fitting the complex nonlinear relationship of milling parameters and surface roughness. It therefore realizes the prediction of surface roughness and the results show that the relative error of the LS- SVM prediction model is ruJt more than 6%; Finally, it gets the relationship between the surface roughness and the milling parameters based on the LS-SVM prediction model for surface roughness, and it provides guidance for the actual production.

关 键 词：表面粗糙度 端面铣削 有限元仿真 航空铝合金 最小二乘支持向量机 

分 类 号：TH16[机械工程—机械制造及自动化]