基于支持向量机的机床切削比能预测方法

针对建立数控机床切削比能预测模型时实验样本数量少,预测量数值变化波动大的问题,提出了一种基于支持向量机理论的数控机床切削比能预测方法。应用正交试验法设计实验方案,进行了不同参数组合条件下的铣削实验;利用MATLAB软件及其结合加载的LIBSVM工具箱编写程序对模型中的各参数进行寻优处理,预测不同加工参数下的机床切削比能;以数控铣床加工45号钢为例,将预测值与实验值进行对比,模型的均方误差达0. 0094,相关系数达到93. 5%,证明了该模型在切削比能预测方面的可行性。该研究对数控机床节能加工和工艺优化具有重要意义。

A Prediction Method of Cutting Specific Energy of Machine Tool Based on SVM

Aiming at the problem of the small number of experimental samples and the large variation of the predictive value when establishing the specific energy prediction model of numerical control machine tools,a prediction method of cutting specific energy of CNC machine tools based on the theory of support vector machines is proposed.Orthogonal experimental method was used to design the experimental scheme and the milling experiment was carried out under the condition of different parameters.MATLAB software and the LIBSVM toolbox combined with the program were used to write the program to optimize the parameters of the model and predict the different processing parameters.The machine tool cutting specific energy;using CNC milling machine processing 45 steel as an example,the predicted value and the experimental value comparison,the model of the mean squared error of 0.0094,the correlation coefficient of 93.5%,proved that the model is feasible in the cutting specific energy prediction Sex.This study is of great importance for energy-saving machining and process optimization of CNC machine tools.