ML driven Fault Diagnosis and Localization in Power Transmission Networks

This study explores a machine learning-based approach to efficiently detect, classify, and locate faults in power transmission lines using voltage and current signal analysis. The method integrates wavelet transform for feature extraction, MATLAB-based transmission line modeling, and supervised with algorithms like Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Decision Tree—for fault classification and distance estimation. A diverse dataset covering various fault scenarios is generated to train and validate the models. The expected outcomes include improved fault detection accuracy, precise fault localization, and a comparative analysis of algorithm performance, with SVM and KNN anticipated delivering the highest accuracy. Experimental validation using simulated data confirms the system’s ability to enhance the reliability and efficiency of power transmission networks. This approach provides a scalable and intelligent solution for modern power system protection.