Optimization of turning process is a non-linear optimization with constrains and it is difficult for theconventional optimization algorithms to solve this problem. The purpose of present study is todemonstrate the potential of Imperialist Competitive Algorithm (ICA) for optimization of multipassturning process. This algorithm is inspired by competition mechanism among imperialists andcolonies, in contrast to evolutionary algorithmsthat perform the exploration and exploitation in thesolution space aiming to efficiently find near optimal solutions using a finite sequence ofinstructions. To validate the proposed approach, the results of ICA were finally compared withGenetic Algorithm (GA).Based on the results; ICA has demonstrated excellent capabilities such assimplicity, accuracy, faster convergence and better global optimum achievement. The outcomeshows the success of ICA in optimizing the machining process indicating that data analysis methoddeveloped in this work can be effectively applied to optimize machining processes. تفاصيل المقالة

A properly designed machining procedure can significantly affect the efficiency of the production lines. To minimize the cost of machining process as well as increasing the quality of products, cutting parameters must permit the reduction of cutting time and cost to the lowest possible levels. To achieve this, cutting parameters must be kept in the optimal range. This is a non-linear optimization with constrains and it is difficult for theconventional optimization algorithms to solve this problem. This paper presents Colonial Competitive Algorithm (CCA) approach to determine the optimal cutting parameters required to minimize the cutting time while maintaining an acceptable quality level.CCA is inspired by competition mechanism among imperialists and colonies, in contrast to evolutionary algorithms that perform the exploration and exploitation in the solution space aiming to efficiently find near optimal solutions using a finite sequence of instructions. Therefore, a case study from literature was considered and optimized using of CCA. To validate the proposed approach, the results of CCA were finally compared with the Genetic Algorithm (GA). Based on the results, CCA has demonstrated excellent capabilities such as accuracy, faster convergence and better global optimum achievement. تفاصيل المقالة