Comparative Analysis of Machine Learning Techniques for Fault Detection

This paper demonstrates the efficient use of machine learning techniques—linear, logistic, polynomial, support vectors—in electrical networks. This work also contains the analysis of the same dataset with Neural Networks in the quest for better efficiency. The study introduces a new method for Electrical Fault Detection using ensemble ML methods. Grid simulation is applied in MATLAB, after collecting voltage and current data, the study demonstrates the effectiveness of neural networks, linear, logistic, polynomial and support vector regression (SVR) models to achieve fault detection and classification accuracy. Findings highlights the tremendous potential of this approach to improve the efficiency and reliability of grid monitoring systems. Ultimately, these developments go a long way in repairing and stabilising the electricity distribution network. This research highlights the combination of advanced machine learning techniques and electrical engineering, highlighting their synergistic potential in solving important challenges in the field. This work aims in making significant progress in the performance and resilience of modern power grids.