Real time machine health monitoring and vibrational analysis using FFT approach

Abstract

The most significant role of an industrial machine is its longevity i.e its ability to perform normally and to produce accurate results for extensively long periods of time. To sustain that longevity of the machine, ‘Health Monitoring' is required. Health Monitoring is a promoted and very helpful tool for predictive maintenance techniques. When a machine breaks down, the consequences can range from a personal injury to a public disaster. For this reason, early detection, identification, and rectification of machine faults are required to ensure the safe operation of the machine. When the faults begin to develop in a machine, some of the dynamic properties of the machine change, which influences the machine vibration level and spectral vibration properties. Such changes can act as an indicator for early detection and identification of developing faults. Vibrations are majorly found in the rotating shaft. The rotating shaft vibrates extensively due to improper alignments and imperfect bearings. This paper overviews the generalized health monitoring concept for machines and presents the health monitoring of a rotating machine based on Vibration Data Analysis using an enhanced Fast Fourier Transform Approach. Considering the importance of recent trends of the Industrial Internet of Things (IIoT), remote data analysis is implemented using Python, TCP/IP protocol and Hercules server terminal.