基于支持向量机的电火花加工TC4的盲孔深度预测模型

A Blind Hole Depth Prediction Model for Electrical Discharge Machining(EDM) TC4 Based on Support Vector Machine

在使用电火花加工技术对难加工金属进行加工时,因为加工过程的复杂性,单纯通过电火花加工实验方法研究各种放电参数及非电参数对盲孔深度的影响不但耗费大量时间,而且实验成本较高。因此文章提出了基于支持向量机在电火花加工工程中盲孔深度的预测模型。以电火花加工TC4为例,设计正交实验。实验结果表明,支持向量机模型可以精确的反映加工参数与实验结果的非线性关系,具有较准确的预测精度。

Because of the complexity of machining process, the effect of discharge parameters and non-electrical parameters on the depth of blind hole is not only time-consuming to study simply by electrical discharge machining（EDM） experiment method when EDM technology is used to process difficult-to-machine metal. Moreover, the cost of the experiment is high. Therefore, a prediction model of blind hole depth based on support vector machine（SVM） in EDM engineering is proposed in this paper. Taking electrical discharge machining TC4 as an example, the orthogonal experiment was designed. The experimental results show that the SVM model can accurately reflect the nonlinear relationship between the machining parameters and the real results, and has a more accurate prediction accuracy.