Unique NSGA-II and MOPSO algorithms for improved dynamic cellular manufacturing systems considering human factors

In this study, we present a new mathematical model of a multi-objective dynamic cellular manufacturing system (MDCMS) that considers human factors. Human factors are incorporated into the proposed model in terms of human reliability and decision-making processes. Three objective functions are considered simultaneously. The first objective minimizes the total cost of the MDCMS. The second objective function minimizes inconsistency in the decision-making style of operators in the common manufacturing cells. The third objective function balances the workload of cells with respect to the efficiency of operators, which is calculated based on human reliability analysis. Various studies have been conducted in the field of MDCMS, but human factors have not received sufficient attention as important elements. Due to the NP-hardness of the MDCMS problem, two innovative meta-heuristic algorithms are developed, i.e., a non-dominated sorting genetic algorithm (NSGA-II) and a multi-objective particle swarm optimization method. The results obtained by the algorithms were compared and analyzed using different criteria. Several test problems were considered to verify and validate the proposed model and solution methods. To the best of our knowledge, this is the first study to consider human reliability and decision-making styles in a large MDCMS in an actual production setting.