A hybrid genetic algorithm based on a two-level hypervolume contribution measure selection strategy for bi-objective flexible job shop problem

Abstract

This study addresses the bi-objective flexible job shop problem (BOFJSP) with respect to minimization of the maximum completion time (makespan) and total tardiness. This study aims to propose an algorithm called Bi-objective Hybrid Genetic Algorithm – hypervolume contribution measure (BOHGA-HCM) that integrates GA with a multi-search algorithm and uses hypervolume contribution measure (Δs) in its two-level selection strategy. The initial population is created by randomly assigning operations to the available machines via dispatching rules to find better areas in the search space and enhance diversity to avoid premature convergence. The algorithm handles the objective functions simultaneously with the Pareto Optimality approach. The effectiveness and performance of the proposed algorithm are benchmarked and compared with other algorithms by using well-known data sets presented in the literature. © 2022 Elsevier Ltd