Smart grid technology Condition monitoring Fault detection System degradation Preventive maintenance Corrective maintenance

Electrical power transmission lines are critical components of the power system, ensuring the delivery of electricity from generation to end-users. However, these systems are highly vulnerable to degradation caused by environmental conditions, mechanical stress, thermal effects, and aging infrastructure, which can lead to failures, outages, and safety risks. Traditional maintenance approaches—corrective, preventive, and predictive—have been widely used, but they are often limited in efficiency, cost-effectiveness, and reliability. In recent years, Artificial Intelligence (AI) and Machine Learning (ML) have emerged as transformative technologies for predictive maintenance in electrical power transmission systems. This study explores the application of AI and ML techniques in enhancing predictive maintenance of transmission lines. It examines how advanced algorithms such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Support Vector Machines (SVMs), combined with data from Internet of Things (IoT) sensors, drones, and thermal imaging systems, can be used to detect early warning signs of faults such as overheating, insulation breakdown, and overcurrent conditions. The study also highlights the benefits of AI-driven predictive maintenance, including reduced downtime, lower operational costs, improved system reliability, enhanced asset lifespan, and greater energy efficiency. Despite these advantages, the study identifies challenges such as data quality issues, high implementation costs, and technical complexities in integrating AI systems into existing power infrastructure. The research concludes that AI and ML-based predictive maintenance represents a significant advancement over traditional maintenance approaches and is essential for modernizing electrical power transmission systems. It recommends increased investment in smart grid technologies and capacity building to support the adoption of intelligent maintenance systems for sustainable and reliable power delivery.