An Adaptive Machine Learning Approach for Electrical Fault Detection and Minimization

In the field of electrical power systems, effective fault detection, and minimization are crucial for maintaining system reliability and operational efficiency. This paper introduces machine learning based Adaptive Fault Reduction Algorithm (AFRA), a novel performance optimization approach designed to reduce fault occurrences significantly of electrical power systems. We used a binary classification dataset with a total of 12,001 data samples for this research. Random Forest (RF) model was used for fault detection and compared its performance against the Artificial Neural Network (ANN) model. RF model demonstrated accuracy, precision, and recall, with scores of 99.79%, 99.64%, and 99.91 % respectively, compared to the ANN's 99.54%, 99.54%, and 99.45%. By integrating AFRA, we reduced the number of fault events from 5,496 to just 6, achieving a 99.89% reduction. Our approach highlights the importance of optimization in fault detection and minimization methodologies, offering a robust framework for improving system reliability. The promising results achieved by AFRA suggest significant potential for its application in real-time monitoring and dynamic fault detection and minimization in power systems.