This article focuses on the analysis and non-invasive online diagnostics of the operating condition of bearings integrated in three-phase squirrel cage induction motors, an electric machine that, due to its constructive and operational characteristics, has a significant presence in the industry.

The proposed signal-processing analysis tool is based on the non-invasive monitoring of stator electrical currents. To improve robustness in the diagnosis of bearing faults over the state-of-the-art, a hybrid approach is employed. The Short-Time Fourier Transform (STFT) and Park's Vector Approach (PVA) are combined and applied to the stator currents. The hybridisation allows benefits of both methods to be combined: i) a proper evaluation of time-varying phenomena; and ii) the possibility to distinguish the type of fault affecting the bearing.

To demonstrate the feasibility of the approach, comparisons are made between the proposed hybrid technique and both the STFT and the Extended Park's Vector Approach (EPVA), which have been previously considered in the diagnosis of these and other induction motor faults.

The validation of the proposed solutions is conducted through computational simulations and laboratory tests, ultimately aiming at generating a database of results that will initiate future research in this area. To emulate bearing failures in an experimental context, artificial damage to bearing components is introduced.