The Optimization of Multi-objective FJSP Based on the Hybrid Algorithm

Abstract

The flexible job-shop scheduling problem (FJSP) is a critical model in manufacturing systems that assigns operations from different jobs to various machines. However, optimizing multiple targets during the production scheduling process is always necessary. While the non-dominated sorting genetic algorithm (NSGA-II) is an effective method to solve the multi-objective FJSP, it can have the main drawbacks of converging too early and falling into local optimization. To address these issues, this research proposes a hybrid algorithm that combines NSGA-II and multi-objective simulated annealing using a pareto-domination based acceptance criterion (PDMOSA). The PDMOSA has a powerful search performance that can overcome the limitations of NSGA-II. The hybrid algorithm also includes original modification methods such as a deletion criterion, duplicated solution deletion, and new individual adding. Additionally, a plug-in decoding method is introduced. The proposed hybrid algorithm is compared with several improved ways based on NSGA-II in various experiments. The results demonstrate that the performance of the hybrid algorithm is better than the others in multi-objective FJSP.