Sistema de monitoramento de máquinas a partir de um sistema supervisório para auxílio da manutenção preventiva e preditiva

The use of operational data from industrial machines can support the identification of abnormalities and maintenance planning. This study aims to propose a monitoring architecture that integrates data from supervisory systems with the Grafana platform, with the possibility of incorporating complementary sensors, to support preventive and predictive maintenance. The methodology consists of bibliographic and documentary research with a qualitative and exploratory approach, based on a comparative analysis of five case studies on industrial equipment monitoring. The monitored variables, data acquisition and storage methods, visualization resources, and contributions to maintenance were examined. The analysis indicated that monitoring variables such as temperature, vibration, and electric current can facilitate the identification of abnormal behavior, historical failure analysis, and decision support. Based on these findings, the centralization of operational information in Grafana dashboards is proposed to enhance the use of data available in supervisory systems. It is concluded that this integration has the potential to support better-informed maintenance interventions, although the application and benefits of the proposed architecture still require implementation and experimental validation.