Combined vibration and thermal analysis for the condition monitoring of rotating machinery

Abstract

Traditional practice in vibration-based condition monitoring of rotating machines with a multiple bearing system, such as turbo-generator sets, is data intensive. Since a number of sensors are required at each bearing location, the task of diagnosing faults on these systems may be daunting for even an experienced analyst. Hence, this study seeks to develop a simplified fault diagnosis method that uses just a single vibration and a single temperature sensor on each bearing. Experiments were done on a laboratory rig with two dissimilar length rotors supported through four ball bearings. Commonly encountered rotor-related faults were independently simulated and compared to a baseline condition. For reference, conventional vibration spectrum analysis was done first. Overall vibration analysis was then conducted and combined with temperature data in two diagnosis approaches. Learning from the first combined approach, which had some limitations, was used to propose a principal component analysis–based approach that was demonstrated with and without temperature data. Results of the proposed principal component analysis–based method suggest that supplementing vibration data with temperature measurements gives improved fault diagnosis when compared to fault diagnosis using vibration data alone. The experimental rig, measurements done, description of both combined approaches and results obtained are presented in this article.