ABSTRACT
In this review paper, we examine the role of Artificial Intelligence (AI) in predictive maintenance of converter-driven renewable energy systems. With the rise of renewable energy integration, the reliability of power electronic converters becomes essential. Traditional maintenance strategies, such as scheduled and reactive maintenance, are insufficient considering the increasing complexity of the systems and the cost of unexpected downtimes. AI-based predictive maintenance enables early detection of anomalies, reduces maintenance cost and increases system lifetime. This paper discussed the fundamentals of predictive maintenance in converter systems, types of AI techniques used and the challenges faced. By comparing machine learning (ML), deep learning (DL) and hybrid methods, we also present how they perform for various converter faults. This review also highlights various case studies, datasets used, feature extraction methods, and presents future possible trends in this rapidly expanding research area.
KEYWORDS: - Artificial Intelligence, Predictive Maintenance, Converter-Driven Systems, Renewable Energy, Machine Learning, Deep Learning, Fault Detection, Prognostics
Full Issue
| View or download the full issue | PDF 127-141 |