Sustainable reconfigurable manufacturing system design using adapted multi-objective evolutionary-based approaches

Abstract

Nowadays, manufacturing systems should be cost-effective and environmentally harmless to cope with various challenges in today's competitive markets. In this paper, we aim to solve an environmental oriented multiobjective reconfigurable manufacturing system design (ie., sustainable reconfigurable machines and tools selection) in the case of a single unit process plan generation. A non-linear multi-objective integer program (NL-MOIP) is presented first, where four objectives are minimised respectively, the total production cost, the total production time, the amount of the greenhouse gases emitted by machines and the hazardous liquid wastes. Second, to solve the problem, we propose four adapted versions of evolutionary approaches, namely two versions of the well known non-dominated sorting genetic algorithm (NSGA-II and NSGA-III), weighted genetic algorithms (WGA) and random weighted genetic algorithms (RWGA). To illustrate the efficiency of the four approaches, several instances of the problem are experimented and the obtained results are analysed using three metrics respectively hypervolume, spacing metric and cardinality of the mixed Pareto fronts.Moreover, the influences of the probabilities of genetic operators on the convergence of the adapted NSGA-III are analysed and TOPSIS method is used to help the decision maker ranking and selecting the best process plans.

Effects of Different Mold Materials and Coolant Media on the Cooling Performance of Epoxy-Based Injection Molds

“…In addition, helium gas [32] or hydrogen [33] can also be applied as cooling media in gas-cooled nuclear reactors since its low tendency to absorb neutrons. Sulfur hexafluoride [34,35] is also widely applied to cool some high-voltage power systems, such as circuit breakers, transformer, or switches. These issues are currently being investigated and the results will be presented in a later study.…”

Considering Sustainability in Reconfigurable Manufacturing Systems Research – A Literature Review

“…Frequently, models with predetermined objectives, e.g. Khettabi et al [42], are presented as a solution for including a sustainability perspective in RMS research.…”

“…that it is foremost related to research aiming at minimization through adding it as a factor in models and programs (e.g. [41,42]). For instance, Khettabi et al [42] developed a non-linear multi-objective program where four objective were minimized; total production cost, total production time, waste (incl.…”

“…[41,42]). For instance, Khettabi et al [42] developed a non-linear multi-objective program where four objective were minimized; total production cost, total production time, waste (incl. oils, water, industrial waste disposal etc.)…”

The Configuration Design of Electronic Products Based on improved NSGA-III with Information Feedback Models

“…Several studies have proposed some improved NSGA-Ш algorithms, and Sang [34] proposed an improved genetic algorithm NSGA-III-APEV to solve a multi-objective shop floor scheduling model. Khettabi [35] designed a multi-objective reconfigurable manufacturing system model, experimentally compared four genetic algorithms, and analyzed the effect of genetic operators on the convergence of NSGA-III. Liu [36] proposed the NSGA-III-GKM algorithm using genetic K-mean clustering algorithm for clustering reference points, which has better diversity and convergence.…”