Scheduling a cellular manufacturing system with GA

Abstract

The flexible manufacturing cell scheduling problem is considered with a multi-objective approach, pursuing together makespan minimisation and the in process job wait minimisation. The formulation of the scheduling problem is discussed, analysing how to generate well suited sequences, like generalised permutation sequences, and the proper construction of a JIT timing of activities. An evolutionary sequencing algorithm based on both classic genetic operators and hybrid operators is then proposed. The hybrid operators have been introduced to construct highly fit initial population, to perform periodically a local search on the population and to maintain enough genetical diversity in the actual population. Simulation runs on a large number of randomly generated problems, showed the high performance of the proposed evolutionary hybrid algorithm, in front of a modified NEH algorithm, in the determination of schedules minimising makespan and in process job wait together.