Application of Imperialist Competitive Algorithm to Optimization Problems Arising in Welding Process
- H. Towsyfyan, S. A. Adnani Salehi, R. Rashidian
The Imperialist Competitive Algorithm (ICA) that was recently introduced has shown its good performance in optimization problems. This algorithm is inspired by competition mechanism among Imperialists and colonies, in contrast to evolutionary algorithms. This paper presents the mathematical modeling and optimization of bead geometry in submerged arc welding using of regression analysis and ICA. Generally, in welding process, weld bead geometry and weld quality are, in most parts, depend on welding parameters, thus the weld quality is usually measured in terms of weld bead geometry which that includes weld height, width and penetration. Therefore, in this study, an attempt was made to minimize the weld area, after satisfying the condition of maximum bead penetration using of Imperialist Competitive Algorithm. ICA has demonstrated excellent capabilities such as simplicity, accuracy, faster convergence and better global optimum achievement. The results of ICA were finally compared with the Genetic Algorithm (GA). The outcome shows the success of ICA in optimizing the weld bead geometry.