Detecção de anomalias em ventiladores industriais via sinais de vibração
Keywords: Anomaly detection, condition monitoring, pelletizing furnace, industrial fans, Fisher discriminant analysis, vibration
AbstractPelletizing furnaces require the use of high power fans to circulate the air in the different regions of the furnace, ensuring the efficiency of the pellet burning process and the use of energy. The failure of one of these fans results in a stop of the production process and economic losses. This work presents a contribution to support predictive maintenance routinely performed on this equipment. Vibration signals in rotating machinery are sensitive to many faults and are therefore widely used in diagnostic systems. From the speed and torque information of the fans and the vibration signals in the bearings collected at low sampling rates, it is possible to generate alarms that guide investigative actions, specifically in the equipment that exhibit anomalous behavior. Graphs with sliding windows allow checking trends in vibration increase, and are used to predict alarms in advance. The monitoring of two fans for four months, compared to inspection reports carried out in the same period showed the contribution that the proposed system can bring to reduce downtime and more rationally use the work of the maintenance teams.