Modeling Determinants of Production Management using Distributed Intelligence

Abstract This article presents a decision-making model to support production management, developed with the application of distributed intelligence (DI). A systematic literature review (SLR) identified a significant gap in the integration of distributed decision-making methods with existing production systems. The proposed model incorporates dynamic selection of resources – workstations and employees – for production tasks, taking into account their competencies, availability, and technological constraints. The optimization process is performed using a particle swarm optimization (PSO) algorithm, implemented in the MATLAB environment. The model was validated through a case study conducted in a metalworking company. Empirical findings confirm the hypothesis that introducing elements of distributed intelligence into the production decision-making process enhances the quality of outcomes. Furthermore, the reorganization of the organizational structure was shown to reduce the time required to access information, enabling flexible adaptation of the production workflow to the company’s evolving operational conditions. This research contributes to the development of decision support systems and outlines future directions for predictive and autonomous production planning.