混沌-支持向量机在加工误差预测中的应用

Prediction Method for Machining Errors Basedon Chaos Theory and Support Vector Machine

提出将混沌-支持向量机模型方法应用于加工误差数据预测。利用互信息法和曹氏方法进行相空间重构,并运用小数据量法计算最大Lyapunov指数,对加工误差时间序列进行混沌识别。通过最小二乘支持向量机对历史样本的学习建立预测模型,并将其预测结果与RBF神经网络预测结果进行仿真对比。结果表明,在较少的加工误差数据条件下,该模型能够有效地描述和预测加工误差的变化,具有较高的预测精度。

A model based on chaos theory and support vector machine was presented to apply to the prediction of machining error. Phase-space was reconstructed by using the mutual information and Cao method. The largest Lyapunov exponent was calculated by small data sets algorithm. The machining error time series were identified by its chaos feature. The simulated prediction model was built based on the least squares supper vector machine, and the prediction result was compared with that of RBF neural network, The compared result shows that the prediction accuracy of this model was higher than that of the RBF neural network using the less data samples.