论文部分内容阅读
由于齿轮钢淬透性与钢的化学成分和组织结构间存在非常复杂的关系,传统方法难以建立准确的预测模型。针对这一问题,提出了一种多支持向量机的建模方法,将影响淬透性的各因素按其相关性进行分类,根据分类结果确定子模型个数和子模型的输入。同时,为保证模型具有更好的拟合精度和泛化能力,在模型的训练中采用遗传算法对支持向量机进行参数寻优。仿真结果表明,采用多支持向量机建立的钢材淬透性预测模型具有更高的预测精度。
Due to the very complex relationship between the hardenability of gear steel and the chemical composition and microstructure of steel, it is difficult to establish an accurate prediction model by traditional methods. In order to solve this problem, a multi-support vector machine modeling method is proposed, in which the factors influencing the hardenability are classified according to their correlation. According to the classification results, the number of sub-models and the input of sub-models are determined. At the same time, to ensure that the model has better fitting accuracy and generalization ability, genetic algorithm is used to optimize the parameters of SVM. The simulation results show that the prediction model of hardenability of steel based on multi-support vector machine has higher prediction accuracy.