摘要
针对神经网络方法在切削力预测方面存在的缺陷,提出了一种新的基于支持向量回归机的切削力智能预测方法。分析了以往切削力预测模型中输入参数和输出参数的选择问题,在此基础上选择轴向切深、进给量、主轴转速和曲面半径四个关键指标作为预测模型的输入,选择XY平面上的切削力合力和轴向切削力作为预测模型的输出,进一步建立了基于支持向量回归机的切削力预测模型。仿真实例的预测结果表明,建立的智能切削力预测模型合理有效。
In view of the defects of the neural network method in the prediction of cutting force, a new intelligent prediction method based on support vector regression is proposed. The selection problem of input and output parameters in past prediction model of cutting force is analyzed, based on which this paper selected of axial depth of cut, feed rate, spindle speed and the radius of curved surface and four key indicators as input for the prediction model, select the XY plane of the cutting force and axial cutting force as the output prediction model to further establish the cutting force prediction model based on the support vector regression machine. The simulation results show that the intelligent cutting force prediction model is reasonable and effective.
出处
《工具技术》
北大核心
2016年第10期32-35,共4页
Tool Engineering
基金
国家自然科学基金(61102120)
关键词
切削力
预测
支持向量机
支持向量回归机
cutting force
prediction
support vector machine
support vector regression
