this paper uses dynamic cognitive networks (dcn) as an intelligent tool for supervisory control. the dcns are an evolution of fuzzy cognitive maps (fcm). intelligent systems and tools use expert knowledge to build models with inference and / or decision taking abilities. a supervisory control architecture for an alcoholic fermentation process is developed from the acquisition of empirical knowledge from an expert. the objective of the supervisor is to operate the process in normal and critical situations. for this, we propose the use of a dcn model with new types of concepts and relationships that not only represent cause-effect as in fcm models. simulation results are presented to validate the architecture developed.