A hybrid optimization approach integrating genetic algorithm and Monte Carlo tree search for multi-machine scheduling in manufacturing irregular solid wood furniture parts

The scheduling of irregular solid wood furniture components poses unique challenges due to complex geometries, multi-machine routing, and high human involvement in semi-automated production. To address these challenges, this study innovatively proposed a hybrid optimization approach that integrates Genetic algorithm (GA) and Monte Carlo tree search (MCTS). The GA performs global scheduling to generate initial solutions, while the MCTS component adaptively refines machine assignments by considering setup times and human-in-the-loop factors. Experimental validation using real-world production data demonstrates that the proposed GA-MCTS method significantly reduces makespan, improves machine utilization, and balances line workload more effectively than traditional heuristics or standalone GA/MCTS models. Furthermore, the proposed model is computationally lightweight, making it well-suited for deployment in small-to-medium-sized enterprises (SMEs) where data collection and automation are limited. The findings provide a practical and adaptive scheduling framework for smart manufacturing, bridging the gap between advanced optimization techniques and the operational realities of the wood furniture industry.