基于支持向量机的搅拌摩擦焊接头力学性能预测

Mechanical property prediction of friction stir welding joint based on support vector machine

对6005A-T6铝合金板搅拌摩擦焊焊接接头进行拉伸试验,将测得的抗拉强度和延伸率作为支持向量机训练和预测所需数据,结合Matlab编程建立了一种相对较新的基于支持向量机的搅拌摩擦焊接头力学性能的预测模型。利用模型对测试数据进行了预测,结果表明,将支持向量机用于搅拌摩擦焊接头力学性能的预测是可行的。该方法可以在样本数量较少的情况下建立较理想的预测模型的同时具有较高的预测精度,有一定的应用推广价值。

The 6005A-T6 aluminum alloy plates were welded by FSW（ Friction Stir Welding）. The tensile strength and elongation of FSW joints were tested. By using the test data,a mechanical properties prediction model of friction stir welding joint based on SVM（ Support Vector Machine） was established with MATLAB programming. The model was used to make a prediction about the test data. Results showthat it is feasible to predict the mechanical properties of friction stir welding joint using SVM. An ideal model with high prediction accuracy can be established with small sample. Therefore,the method is worth generalizing.