A hybrid two-stage algorithm for solving the blocking flow shop scheduling problem with the objective of minimise the makespan

Abstract

Flow shop scheduling is an important tool for a variety of industrial system and it has important applications in manufacturing and engineering. This paper considers the blocking flow shop scheduling problem involving processing times and provides a hybrid approach based on artificial neural network and genetic algorithm technique. The objective of this paper is to focus on to minimise the makespan. In this paper, a multi-layer neural network algorithm is developed to find the initial schedule of jobs and then a genetic algorithm is designed to improve the initial sequence of jobs to obtained the best job schedule that minimise the makespan. A numerical example is illustrated to explain the proposed approach and demonstrate its effectiveness. The performance of our suggested hybrid model is compared with the various existing method in the literature and the results indicate that the proposed model performs significantly better than the other methods in the literature. The computational results that are presented in this paper are very encouraging and have shown that the proposed algorithm is superior.