A no-tardiness job shop scheduling problem with overtime consideration and the solution approaches

In make-to-order manufacturing environments, overtime work is one of the effective and commonly used re-sources for expanding production capacity to ensure orders on-time delivery. However, if overtime work is not used reasonably and optimally, not only it cannot expedite the order completion, but also may lead to an increase in manufacturing costs. In order to use overtime work optimally, this paper presents a no-tardiness job shop scheduling problem with overtime work consideration (NTJSSP-OW) to minimize the total earliness inventory and overtime work costs simultaneously. A mathematical model is formulated and a hybrid genetic algorithm with simulated annealing (GASA) is proposed to solve it. Nine algorithms are also selected for performance comparisons. Unlike the traditional job shop scheduling problem, when solving NTJSSP-OW by heuristics and meta-heuristics, no-tardiness constraint is more likely to lead to infeasible solutions. So a multi-stage decoding scheme with a reconstructing rule is developed to ensure feasible solution. In order to extend the search space, a dispatching rule-based population initialization procedure and a repairing mechanism are provided. Compre-hensive experiments are conducted on 14 modified benchmark problems, and non-parametric statistical tests like the Friedman test and post-hoc Nemenyi test are performed for the experimental results. Further systematic analyses indicate that GASA has significantly faster convergence on 90% of all test instances, and its global search ability outperforms other competing algorithms for 12 out of 14 instances.