PHYSICS-BASED, DATA-DRIVEN, AND PHYSICS-BASED DATA-DRIVEN METHODS FOR DIAGNOSTICS OF ROTATING MACHINERY - STATE OF THE ART

As the level of complexity of modern rotating machinery grows, the need for an effective and efficient maintenance process increases as well. In the last decade, researchers all over the world have shown strong aspiration to optimize the diagnostics phase in rotating machinery. This paper highlights some of the latest research on the detection of typical faults in rotating machinery such as mass rotor imbalance, misalignment, rub and looseness, bearing and gear faults. Various technigues for condition monitoring have been researched, and in this paper, they have been classified into three groups: physics-based, data-driven, and physics-based data-driven methods. Although most of the research falls into the first two prior mentioned groups, an intent to introduce a novel method, their symbiosis, has emerged in the last few years. The great potential for future work on physics-based data-driven methods in the field of rotating machinery has been briefly discussed.