A multi-objective fuzzy genetic algorithm for job-shop scheduling problems

Purpose: Many uncertain factors in job shop scheduling problems are critical for the scheduling procedures. There are not genetic algorithms to solve this problem drastically. A new genetic algorithm is proposed for fuzzy job shop scheduling problems. Design/methodology/approach: The imprecise processing times are modeled as triangular fuzzy numbers (TFNs) and the due dates are modeled as trapezium fuzzy numbers in this paper. A multi-objective genetic algorithm is proposed to solve fuzzy job shop scheduling problems, in which the objective functions are conflicting. Agreement index (AI) is used to show the satisfaction of client which is defined as value of the area of processing time membership function intersection divided by the area of the due date membership function. The multi-objective function is composed of maximize both the minimum agreement and maximize the average agreement index. Findings: Two benchmark problems were used to show the effectiveness of the proposed approach. Experimental results demonstrate that the multi-objective genetic algorithm does not get stuck at a local optimum easily, and it can solve job-shop scheduling problems with fuzzy processing time and fuzzy due date effectively. Research limitations/implications: In this paper only two objective functions of genetic algorithm are taken into consideration. Many other objective functions are not applied to this genetic algorithm. Originality/value: A new multi-objective fuzzy genetic algorithm is proposed for fuzzy genetic algorithm. The genetic operations can search the optimization circularly.