Optimizing multi-objective scheduling problem of hybrid flow shop with limited buffer

Buffer zones in a production company are set before and after each processing equipment based on various factors such as workshop space in the hybrid-flow workshop, transportation capacity of the carrying equipment, ease of handling of the machine, machine productivity at various stages, and production cycle time. The objective of this paper was to optimizing the multi-objective scheduling problem in hybrid flow shop with limited buffer. As there was limited space (capacity) at front and rear buffers of each machine, transportation of workpieces in batches, limited carrying capacity of carrier equipment, differences in workability between parallel machines, and process determination, etc., were considered as resource limiting factors, and based upon these factors two-objective scheduling model was established with the goal of minimizing completion time and minimizing material transportation time. The two-objective scheduling model was added with minimization parallel machine front buffer space occupancy rate equilibrium index as a new goal, and established a three-objective scheduling model. In this article, NSGA-II and NSGA-III algorithms were used to solve the three-objective scheduling model, and the crossover and mutation parts of the algorithm were redesigned according to the model established. The actual production data of a marine pipe production enterprise was taken as an example and optimization results were compared with the actual production data. Thus the effectiveness of the algorithm was verified, and the difference between the two algorithms when processing the three-target scheduling model was compared, and it is concluded that NSGA-III has better convergence effect when processing the three-objective model. To explore the impact of different buffer volumes on production, target values ​​under different buffer volumes were compared, and finally optimal buffer volume for each target was found out; then the two-objective model and the three-objective model were compared under different buffer volumes. The optimization results of these indicators prove the practical importance of adding the minimization of the parallel machine front buffer space occupancy rate balance index.