Artificial Intelligence-Based Condition Monitoring and Predictive Maintenance of Medium Voltage Cables : An Integrated System Development Approach

Abstract

In order to minimize power supply outages in electrical distribution systems, the reliable operation of medium-voltage (MV) cables is of paramount importance. These cables may experience unplanned downtime and failures, which can result in large financial losses and interruption of the processes. This study investigates the use of artificial intelligence (AI) in developing a system for condition monitoring and predictive maintenance of Medium Voltage (MV) cables. It uses historical data to train models for predicting potential cable failures, with the goal of increasing reliability and decreasing downtime. The study also investigates the effectiveness of machine learning (ML) algorithms in forecasting maintenance needs under various environmental conditions and factors. The findings suggest that ML can optimize MV cable maintenance strategies, resulting in increased efficiency and cost-effectiveness in electrical infrastructure management. Using cutting-edge technologies like sensors, data analytics, and ML, this paper proposes an integrated monitoring system development approach for MV cable predictive maintenance. The purpose of the proposed system is to improve the reliability of MV cable network by facilitating proactive maintenance strategies through timely insights into cable condition. This research provides useful insights for industry professionals, researchers, and policymakers who want to optimize maintenance strategies and ensure continuous power supply in modern electrical infrastructure.