Artificial intelligence-based optimization applications techniques in Kanban Systems: Literature review and methodological approaches

In this study, technological advancements have led to fundamental transformations in the methods and tools used in lean production processes. Kanban cards, one of the primary tools of pull systems, have evolved in this transformation process from being merely a physical signaling tool to being reshaped with digital and artificial intelligence-based solutions. Especially in complex and dynamic production environments, the integration of AI-based optimization techniques into Kanban systems is increasingly important for accelerating decision-making processes, balancing inventory levels, and optimizing production flow. This study systematically reviews the literature on AI-based optimization applications in Kanban systems. Within the scope of the study, the use, problem types addressed, and contributions of methods such as genetic algorithms, tabu search, simulated annealing, ant colony optimization, and particle swarm optimization were evaluated. The analysis revealed that these techniques are particularly effective in accelerating decision-making processes and enhancing the adaptive capacity of the system under variable production conditions. To the best of our knowledge, this study represents the first systematic review in the literature to examine AI-based optimization methods in Kanban systems from a comprehensive perspective. Consequently, it provides a broad framework that will guide future research for both academic and industrial applications.