Induction motors (IMs) are the backbone of modern industry. Despite their robustness and reliability, they are prone to a range of problems that can result in periods of inactivity, diminished operational efficiency, and potential safety risks. Rapid identification and assessment of faults is important to maintain efficient motors operation and avoid serious malfunctions. The paper offers a comprehensive analysis of the existing body of knowledge in IMs’ faults detection, highlighting areas of deficiency and obstacles. Our review is built according to the IMs diagnosis process, presenting for each step of this process several approaches. Finally, we discuss the effectiveness of each fault classification approach in addressing data-driven challenges such as high-dimensionality, class imbalance, nonlinearity, noise, and overfitting. This paper highlights the rising transition to data-driven strategies, with deep learning increasingly taking center stage in tackling the complex challenges of fault diagnosis. It underscores the significant impact of these advancements on the field, actively facilitating future research into intelligent, real-time condition monitoring systems.

In this paper, advanced sensorless control methods of an induction machine (IM) with the use of a model reference adaptive system (MRAS) estimator are presented, specifically an MRAS using reactive power (Q-MRAS) with an implemented feedforward artificial neural network. Advantages of the proposed solution in comparison with the conventional Q-MRAS include better robustness, less dependence on the IM parameters, and stable operation in the regenerative mode. The simulations were performed in the MATLAB Simulink interface to validate the proposed approach. The algorithm was implemented in a single-core TMS320F28335 real-time Digital Signal Controller with a LabVIEW control panel. The experimental results were obtained on a three-phase experimental induction motor drive with a nominal power of 2.2 kW.