TY - JOUR
T1 - A Q-Learning Based Hybrid Meta-Heuristic for Integrated Scheduling of Disassembly and Reprocessing Processes Considering Product Structures and Stochasticity
AU - Wang, Fuquan
AU - Fu, Yaping
AU - Gao, Kaizhou
AU - Wu, Yaoxin
AU - Gao, Song
N1 - Publisher Copyright:
© The author(s) 2024.
PY - 2024/6
Y1 - 2024/6
N2 - Remanufacturing is regarded as a sustainable manufacturing paradigm of energy conservation and environment protection. To improve the efficiency of the remanufacturing process, this work investigates an integrated scheduling problem for disassembly and reprocessing in a remanufacturing process, where product structures and uncertainty are taken into account. First, a stochastic programming model is developed to minimize the maximum completion time (makespan). Second, a Q-learning based hybrid meta-heuristic (Q-HMH) is specially devised. In each iteration, a Q-learning method is employed to adaptively choose a premium algorithm from four candidate ones, including genetic algorithm (GA), artificial bee colony (ABC), shuffled frog-leaping algorithm (SFLA), and simulated annealing (SA) methods. At last, simulation experiments are carried out by using sixteen instances with different scales, and three state-of-the-art algorithms in literature and an exact solver CPLEX are chosen for comparisons. By analyzing the results with the average relative percentage deviation (RPD) metric, we find that Q-HMH outperforms its rivals by 9.79%−26.76%. The results and comparisons verify the excellent competitiveness of Q-HMH for solving the concerned problems.
AB - Remanufacturing is regarded as a sustainable manufacturing paradigm of energy conservation and environment protection. To improve the efficiency of the remanufacturing process, this work investigates an integrated scheduling problem for disassembly and reprocessing in a remanufacturing process, where product structures and uncertainty are taken into account. First, a stochastic programming model is developed to minimize the maximum completion time (makespan). Second, a Q-learning based hybrid meta-heuristic (Q-HMH) is specially devised. In each iteration, a Q-learning method is employed to adaptively choose a premium algorithm from four candidate ones, including genetic algorithm (GA), artificial bee colony (ABC), shuffled frog-leaping algorithm (SFLA), and simulated annealing (SA) methods. At last, simulation experiments are carried out by using sixteen instances with different scales, and three state-of-the-art algorithms in literature and an exact solver CPLEX are chosen for comparisons. By analyzing the results with the average relative percentage deviation (RPD) metric, we find that Q-HMH outperforms its rivals by 9.79%−26.76%. The results and comparisons verify the excellent competitiveness of Q-HMH for solving the concerned problems.
KW - disassembly
KW - meta-heuristic
KW - Q-learning
KW - remanufacturing scheduling
KW - reprocessing
UR - http://www.scopus.com/inward/record.url?scp=85201516447&partnerID=8YFLogxK
U2 - 10.23919/CSMS.2024.0007
DO - 10.23919/CSMS.2024.0007
M3 - Article
AN - SCOPUS:85201516447
SN - 2096-9929
VL - 4
SP - 184
EP - 209
JO - Complex System Modeling and Simulation
JF - Complex System Modeling and Simulation
IS - 2
ER -