A Reinforcing-Learning-Driven Artificial Bee Colony Algorithm for Scheduling Jobs and Flexible Maintenance under Learning and Deteriorating Effects

In the last decades, availability constraint as well learning and deteriorating effects were introduced into production scheduling theory to simulate real-world case studies overcome limitation of classical models. To best our knowledge, this paper is first in literature address permutation flowshop problem (PFSP) with flexible maintenance under deterioration minimize makespan. Firstly, we PFSP effects. Then, effect also considered. Adaptive artificial bee colony algorithms (ABC) enhanced Q-learning are proposed, which Nawaz–Enscore–Ham (NEH) heuristic modified NEH heuristics hybridized a insertion construct potential integrated initial solutions. Furthermore, (QL)-based neighborhood selection applied employed bees phase improve quality search space Computational experiments performed on Taillard’s well-known benchmarks, augmented both prognostic health management (PHM) data, demonstrate effectiveness proposed QL-driven ABC algorithms.