NSGA-II vs NSGA-III for the Sustainable Multi-Objective Process Plan Generation in a Reconfigurable Manufacturing Environment
Imen Khettabi, Mohamed Amine Boutiche, Lyès Benyoucef
Abstract
Since global economic competition, a new generation of manufacturing systems has been developed for changing market needs while minimizing harmful environmental impacts. Reconfigurable manufacturing system (RMS) can increase the system sustainability and reactivity to satisfy the market needs. In this paper, we consider an environmental oriented multi-objective problem for a sustainable reconfigurable manufacturing system (S-RMS). First, in the case of a single unit process plan generation, a non-linear multi-objective integer program (NL-MOIP) is presented, where four objectives are optimized respectively, the total production cost, the total production time, the amount of the greenhouse gases emitted from energy consumption and the hazardous liquid wastes. Second, to solve the problem, adapted versions of the well-known non-dominated sorting genetic algorithm respectively NSGA-II and NSGA-III are presented. Finally, to illustrate the comparisons between both meta-heuristics, some experimental results are presented and analyzed.