1. Modified Multi-Crossover Operator NSGA-III for Solving Low Carbon Flexible Job Shop Scheduling Problem
- Author
-
Hongwei Kang, Ye Wang, Yong Shen, Da Wang, Xingping Sun, and Qingyi Chen
- Subjects
0209 industrial biotechnology ,Mathematical optimization ,Computer science ,Population ,Crossover ,Evolutionary algorithm ,Bioengineering ,Context (language use) ,02 engineering and technology ,co-evolution ,lcsh:Chemical technology ,Multi-objective optimization ,multi-crossover operator ,low carbon ,lcsh:Chemistry ,020901 industrial engineering & automation ,Local optimum ,Genetic algorithm ,0202 electrical engineering, electronic engineering, information engineering ,genetic algorithm ,Chemical Engineering (miscellaneous) ,flexible job shop scheduling problem ,lcsh:TP1-1185 ,education ,education.field_of_study ,Process Chemistry and Technology ,Pareto principle ,multi-objective optimization ,lcsh:QD1-999 ,020201 artificial intelligence & image processing - Abstract
Low carbon manufacturing has received increasingly more attention in the context of global warming. The flexible job shop scheduling problem (FJSP) widely exists in various manufacturing processes. Researchers have always emphasized manufacturing efficiency and economic benefits while ignoring environmental impacts. In this paper, considering carbon emissions, a multi-objective flexible job shop scheduling problem (MO-FJSP) mathematical model with minimum completion time, carbon emission, and machine load is established. To solve this problem, we study six variants of the non-dominated sorting genetic algorithm-III (NSGA-III). We find that some variants have better search capability in the MO-FJSP decision space. When the solution set is close to the Pareto frontier, the development ability of the NSGA-III variant in the decision space shows a difference. According to the research, we combine Pareto dominance with indicator-based thought. By utilizing three existing crossover operators, a modified NSGA-III (co-evolutionary NSGA-III (NSGA-III-COE) incorporated with the multi-group co-evolution and the natural selection is proposed. By comparing with three NSGA-III variants and five multi-objective evolutionary algorithms (MOEAs) on 27 well-known FJSP benchmark instances, it is found that the NSGA-III-COE greatly improves the speed of convergence and the ability to jump out of local optimum while maintaining the diversity of the population. From the experimental results, it can be concluded that the NSGA-III-COE has significant advantages in solving the low carbon MO-FJSP.
- Published
- 2021