OPERATIONAL DECISION IN INDUSTRIAL PROCESSES: A SYSTEMATIC MAPPING OF HUMAN OPERATOR, SUPPORT SYSTEMS AND PROCESS VARIABILITY

Industrial processes involve variability, operational uncertainty, and the continuous need to interpret real operating conditions. Even in automated environments, operational decision-making remains relevant in the face of abnormal situations, transient states, alarms, quality deviations, and adjustments not fully captured by control systems. In this context, understanding how the literature addresses the relationship between human operators, decision-support systems, computational modeling, and sociotechnical factors is essential to guide research in Operations Research and Production Engineering. This paper aims to map and analyze the scientific literature on operational decision-making in industrial processes, identifying approaches, analytical dimensions, and research gaps. To this end, a systematic mapping of the literature was conducted in the IEEE Xplore, Scopus, and Web of Science databases, considering publications from 2015 to 2026. The initial search resulted in 543 records, which were subsequently subjected to duplicate removal, inclusion and exclusion criteria, title and abstract screening, and full-text reading. The final portfolio consisted of 22 articles, 12 classified as core studies and 10 as complementary studies. The studies were organized into five analytical axes: abnormal conditions and uncertainty; cognition and situational awareness; decision-support systems; modeling, prediction, and artificial intelligence; and sociotechnical dimension and autonomy. The results indicate that operational decision-making is addressed as a technical, cognitive, informational, and sociotechnical phenomenon, although still in a fragmented way. A greater concentration of recent publications was observed, especially from 2022 onward, associated with industrial digitalization, data-driven models, artificial intelligence, dashboards, and human-in-the-loop architectures. Despite these advances, few studies simultaneously integrate process variability, human judgment, tacit knowledge, cognitive load, trust in systems, and practical operational constraints. It is concluded that operational decision-making should not be treated only as an automatic response from systems or as an external variable in optimization models, but as part of the production system itself. As a contribution, the study structures existing knowledge and identifies opportunities for empirical research, human-in-the-loop models, and approaches capable of integrating human decision-making, support systems, operational learning, and process variability.