Study on the wire feed speed prediction of double-wire-pulsed MIG welding based on support vector machine regression

Abstract

Obtaining the wire feed speed which can properly match the process parameters is difficult in double-wire-pulsed metal inert gas (MIG) welding. This work analyzed ten factors which affect the wire feed speed in reality and conducted corresponding correlation analysis. Then, four significant correlation factors, which were duty ratio, frequency, average current of leading wire, and average current of trailing wire, are selected as independent variables for establishing a double-wire feed speed prediction model. The model established by support vector machine regression used two evaluation criterions, which were the mean square error (MSE) and squared correlation coefficient (SCC), and then obtained the optimal model parameters by mesh optimization. Finally, the proposed model was validated by actual double-wire-pulsed welding experiments. This study can optimize the double-wire welding technological designing process and improve the intelligent double-wire welding industry.