I. Introduction
As a very critical part in modern mechanical and electrical industrial systems, rotating machinery has been widely utilized in different application scenarios [1]. However, failures (e.g. rotor imbalance and misalignment, outer/inner race defects of bearings) inevitably occur especially under harsh operating environments, which are very prone to cause performance degradation, or even worse, economic loss and severe casualty [2], [3]. To prevent these and take measures in the initial phase, it is of great importance to develop effective and efficient methods for early fault diagnosis and build health condition monitoring systems of rotating machinery.