Permutation Flowshop Scheduling Problem Considering Learning, Deteriorating Effects and Flexible Maintenance

Availability constraints, machine condition as well as human behavior phenomena were recently introduced in the study of scheduling problems in order to get closer to the industrial reality. In this context, the permutation flowshop scheduling problem (PFSP) under flexible maintenance planning is investigated by incorporating machine deteriorating and human learning effects. The objective is to minimise the expected makespan by optimising simultaneously job sequence and maintenance decisions. To study the different problem configurations with respect to machine and human related effects, two studies are carried out. In the former study, the learning effect (human effect) is applied on maintenance activities, where durations are assumed to be time varying. While in the later, besides applying the learning effect on maintenance operations, time-dependent deteriorating jobs are also considered. Given the NP-completeness of the PFSP, an artificial bees colony algorithm (ABC) based metaheuristic is proposed, complemented with a maintenance insertion heuristic and adaptive local search procedures, to provide good solutions with reasonable CPU time. To prove the effectiveness of our proposed algorithm, intense computational experiments are carried out on Taillard's well-known benchmarks, expanded with flexible maintenance data.