Mechanical property prediction of friction stir welding joint based on support vector machine
ZHANG Li-guo;HE Jun;GAO Shuang-sheng;General Affair office,Liaoning General Aviation Academy;Faculty of Aerospace Engineering, Shenyang Aerospace University;Faculty of Materials Science and Engineering, Shenyang Aerospace University;
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.