International Journal of Scientific Research and Engineering Development

The high voltage (HV) equipment is an important element in transmission and distribution of electrical power over grids. To properly ensure the reliability of its systems it is vital to prepare its operation integrity to prevent expensive failure. Detection and diagnostic (FDD) methods are sometimes ineffective in traditional fault detection and diagnostic (FDD) when it comes to accuracy, scalability, and real time monitoring. Artificial Intelligence (AI) has come into the fore as a potent instrument of improving FDD procedures in high voltage settings in recent years. This paper will undertake an in-depth discussion of AIbased solutions to fault detection and fault diagnosis in HV equipment. It explains the nature of errors in such systems, explains the use of machine learning (ML) and deep learning (DL), and assesses performance using experimental data. The outcomes confirm that AI models, especially convolutional neural networks (CNNs) and long short-term memory (LSTM) networks, can detect and diagnose faults with the highest degree of accuracy and minimum false positives. The paper ends with useful information on real-world implementation and provides the way forward research which will enable more optimization of AI in the management of HV equipment.