基于LS-SVM的机床加工误差预测模型探讨

Prediction method for machining errors based on LS-SVM

提出一种基于最小二乘支持向量机(LS-SVM)的机床加工误差回归模型和预测方法,给出了相应的步骤和算法。通过与BP神经网络和RBF神经网络预测方法比较,仿真结果表明,在较少的误差数据条件下,该模型能够有效的描述和预测加工误差的变化,且模型预测误差比神经网络模型小60%左右;应用该预测模型预测机床加工误差有更高的预测精度,对其实施补偿和控制,将有效提高机床的加工精度。

A new machining error prediction approach,which is based on the least squares support vector machine（LS-SVM）.In the same condition,the results show that the prediction accuracy of LS-SVM is 60% higher than that of the predictor method of BPNN and RBFNN.Compared with other more modeling approaches,the prediction effect indicates that the proposed method is more accurate and can be realized more easily.It provides a better way for on-line quality monitoring and controlling of dynamic machining.