Publisher : The Korean Welding and Joining Society
DOI : 10.5781/JWJ.2016.34.2.67
Title & Authors
Prediction of Tensile Strength for Plasma-MIG Hybrid Welding Using Statistical Regression Model and Neural Network Algorithm Jung, Jin Soo; Lee, Hee Keun; Park, Young Whan;
Aluminum alloy is one of light weight material and it is used to make LNG tank and ship. However, in order to weld aluminum alloy high density heat source is needed. In this paper, I-butt welding of Al 5083 with 6mm thickness using Plasma-MIG welding was carried out. The experiment was performed to investigate the influence of plasma-MIG welding parameters such as plasma current, wire feeding rate, MIG-welding voltage and welding speed on the tensile strength of weld. In addition we suggested 3 strength estimation models which are second order polynomial regression model, multiple nonlinear regression model and neural network model. The estimation performance of 3 models was evaluated in terms of average error rate (AER) and their values were 0.125, 0.238, and 0.021 respectively. Neural network model which has training concept and reflects non -linearity was best estimation performance.