Artificial Intelligence Application in Production Scheduling Problem Systematic Literature Review: Bibliometric Analysis, Research Trend, and Knowledge Taxonomy

Due to increasing industrialization and globalization, using artificial intelligence (AI) to solve the production scheduling problem has attracted a lot of interest. To improve the overall performance and efficiency of production scheduling, the use of AI technologies has become essential. To better understand how AI may be used to solve the production scheduling problem (PSP), this research will look at worldwide trends, knowledge structures, and knowledge gaps. By evaluating the available literature and utilizing both quantitative and qualitative methodologies, it will provide an in-depth understanding of this topic (through a review). Gaining a clearer grasp of the evolution and organization of knowledge in this area and locating any research gaps are the aims of this study. Using the scientific mapping method, 63 key papers that were released between 1987 and 2023 were compiled and synthesized. Bibliographic analysis was done using visualized data on journal publishing years, attribution and co-citations, international collaboration between nations and institutions, influential publications, concomitant keywords, and groups of historical study subjects. As a result, five categories of AI applications in production scheduling problems were classified and thematically discussed: (i) job shop scheduling problems; (ii) flow shop scheduling; (iii) distribution scheduling and transportation scheduling; (iv) production scheduling; and (v) production scheduling. Finally, suggestions for upcoming study directions and knowledge gaps were provided. The findings contribute to providing a rigorous intellectual outlook for AI applications in PSP subfields and academic limits of AI application in the PSP study.