AI-DRIVEN FAULT DETECTION AND PREDICTIVE MAINTENANCE IN ELECTRICAL POWER SYSTEMS: A SYSTEMATIC REVIEW OF DATA-DRIVEN APPROACHES, DIGITAL TWINS, AND SELF-HEALING GRIDS

Abstract

The increasing complexity of electrical power systems necessitates advanced fault detection and predictive maintenance strategies to enhance operational efficiency and grid reliability. Traditional maintenance approaches, such as reactive and preventive maintenance, have proven insufficient in mitigating unplanned outages and optimizing asset utilization. Recent advancements in artificial intelligence (AI) have introduced data-driven solutions that significantly improve fault classification, failure prediction, and automated recovery processes. This study conducts a systematic review of 180 high-quality peer-reviewed articles, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to ensure a rigorous and transparent research methodology. The findings reveal that AI-driven predictive maintenance methods, including machine learning, deep learning, digital twin technology, IoT-enabled sensor networks, and self-healing grids, have outperformed traditional fault detection techniques in terms of accuracy, adaptability, and cost-effectiveness. AI-based fault detection models achieve an average accuracy of 85% to 95%, reducing false alarms by 50% and minimizing power restoration times by up to 60%. The integration of IoT sensors with real-time analytics has improved anomaly detection rates by 28%, while digital twin technology has enhanced predictive maintenance efficiency, reducing unplanned outages by 35%. Additionally, self-healing grid mechanisms, powered by reinforcement learning algorithms, have demonstrated the ability to autonomously isolate faults and reconfigure energy distribution, preventing nearly 45% of potential service disruptions. Despite these advancements, challenges such as the black-box nature of deep learning models, cybersecurity vulnerabilities, and interoperability with legacy systems continue to pose barriers to large-scale AI adoption. The study highlights the need for explainable AI frameworks, standardized data governance policies, and enhanced cybersecurity measures to ensure the sustainable deployment of AI in power grid management. The findings provide valuable insights for researchers, utility companies, and policymakers seeking to enhance the resilience and efficiency of modern electrical power systems through AI-driven fault detection and predictive maintenance strategies.