Rotating electrical machines are critical assets in industrial systems, where unexpected failures can lead to costly downtime and safety risks. This review presents a comprehensive and up-to-date analysis of artificial intelligence (AI) techniques for fault diagnosis in electric machines. It categorizes and evaluates supervised, unsupervised, deep learning, and hybrid/ensemble approaches in terms of diagnostic accuracy, adaptability, and implementation complexity. A comparative analysis highlights the strengths and limitations of each method, while emerging trends such as explainable AI, self-supervised learning, and digital twin integration are discussed as enablers of next-generation diagnostic systems. To support practical deployment, the article proposes a modular implementation framework and offers actionable recommendations for practitioners. This work serves as both a reference and a guide for researchers and engineers aiming to develop scalable, interpretable, and robust AI-driven fault diagnosis solutions for rotating electrical machines.
Zachariades et al. (Mon,) studied this question.