Application of Python-based Machine Learning for Transformer Performance and Transmission Line Fault Prediction

In recent years, the application of machine learning has significantly expanded across core engineering domains. It is essential for engineering students to develop the ability to apply machine learning to fundamental applications. This paper addresses the identification and location of faults in transmission lines under abnormal conditions. Additionally, it explores how Python-based machine learning can be utilized to predict voltage regulation and transformer efficiency under various load conditions. For transmission line fault classification and prediction, the Random Forest Classifier algorithm achieved 100% accuracy, while the Random Forest Regression model used for fault location prediction resulted in an error of 0.0626. For predicting voltage regulation and transformer efficiency, the Random Forest Regression model produced an error of 0.00133 and 0.358 respectively. Furthermore, this work aims to enhance conventional lab experiments, enabling engineering students to integrate recent trends in machine learning into their traditional methodologies, thereby fostering a deeper understanding of modern approaches to electrical engineering challenges.