Video vibration identification system using motion magnification

Abstract

Predictive maintenance is the most suitable for industries, as it monitors the health of machines and reduces downtime on the production line. One of the monitored signals is the vibration level of the machines. The instruments most used for this measurement are sensors, which mostly need physical contact with the monitored equipment. However, these instruments depend on wires and can be defective, generating erroneous measurements. Solutions that measure the level of vibration without contact are expensive. That's why we developed the Video Vibration Identification System using Motion Magnification (SIVVAM) as a low-cost, non-contact alternative solution for vibration monitoring. The main contributions are identification of vibration in non-contact motors, real-time processing, definition of two areas of interest to measure vibration simultaneously, and use of low-cost hardware. The proposed solution can assist in predictive maintenance by alerting when the vibration level is above the indicated standard.