Estimation of laser hybrid welded joint strength by using genetic algorithm approach

Abstract

The genetic algorithm approach is extended to the prediction of welding strength of the 6K21-T4 aluminum alloy materials. The welding strength of joint parts can be improved by selecting suitable welding parameters. It is affected by many parameters, such as wire type, shielding gas, laser energy, laser focus, traveling speed, wire feed rate. The model is based on dependence of the six welding parameters on the welded joint strength. The present paper describes the use of the stochastic search process based on genetic algorithms (GA), in estimating the strength value of the welded parts. Non-linear estimation models were developed using GAs. The genetic algorithm laser welding strength estimation model (GALWSEM) was developed to estimate the mechanical properties of the welded joint for alloy materials. The effects of six welding design parameters on the strength value using the GALWSEM have been examined. The good quality welded joints can be obtained by using the results produced by the GALWSEM. The results indicate that the better quality joint may be obtained by selecting the wire type of 5356, the laser focus of -1 mm, the wire type of ER 4043 and the laser focus of 0 mm. © 2008 Elsevier Ltd. All rights reserved.