Low carbon flexible job shop scheduling problem considering worker learning using a memetic algorithm

Green low carbon flexible job shop problems have been extensively studied in recent decades, while most of them ignore the influence of workers. In this paper, we take workers into account and consider the effects of their learning abilities on the processing time and energy consumption. And then a new low carbon flexible job shop scheduling problem considering worker learning (LFJSP-WL) is investigated. To reduce carbon emission (CE), a novel CE assessment of machines is presented which combines the production scheduling strategies based on worker learning. A memetic algorithm (MA) is tailored to solve the LFJSP-WL with objectives of minimizing the makespan, total CE and total cost of workers. In LFJSP-WL, a three-layer chromosome encoding method is adopted and several approaches considering the problem characteristics are designed in population initialization, crossover and mutation. Besides, four effective neighborhood structures are developed to enhance the exploitation and exploration capacities, and the elite pool strategy is presented to reserve elite solutions along each iteration. The Taguchi method of DOE is used to obtain the best combination of the key parameters used in MA. Computational experiments conducted show that the MA is able to easily obtain better solutions for most of the tested 22 challenging problem instances compared to two other well-known algorithms, demonstrating its superior performance for the proposed LFJSP-WL.