Application of response surface methodology and genetic algorithm in the prediction and optimization of the ductile properties of mild steel weld

Abstract

Welding has been identified as an excellent joining process which guarantees, good ductile joints devoured of failure. However determining the right parameters, and weld process is key to obtaining a quality joint. This study is performed to evaluate the effect of the input process parameters on the responses (tensile strength, percentage elongation, and bending strength), and to optimize the ductile properties of the weld variables using response surface methodology (RSM), and genetic algorithm (GA) techniques. Analysis carried out using the two different techniques showed the suitability of the techniques in obtaining the optimum weld parameters and their significant differences in results. The GA, performed more efficiently with its results recording a less than 6% error. However, the suitability of the RSM, is displayed in its ability to reveal the parameters with the most significant effect. The result shows that the weld current and arc voltage are the parameters with the most significant effect on the ductility of the welded joint, haven recorded p values less than 0.005 in the ANOVA analysis. But for the microscopic images obtained from both the RSM and GA welds, the study shows that the GA parameters obtained are capable of producing a more durable welds.

Keywords:

• Modeling
• genetic algorithm
• welding
• gas tungsten arc welding

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

The data supporting the findings of this study are available within the article.