부산대학교 도서관

Unexpected failures in the electrical power transmission line can occur for several different, unpredictable reasons. Power failures on transmission lines can destroy the present power grid if faults aren't quickly detected and corrected. For consistent performance, it is essential to have a system in place for identifying and categorizing power system faults. Several academics have developed automated approaches for fault identification and classification; however, typical fault detection techniques depend on human feature extraction with previous understanding. It is crucial to detect transmission line faults to guarantee safety. Preventing costly damage to the network is one of the key advantages of earlier fault detection in a transmission line. Autonomous and efficient fault diagnosis in the power system remains a major problem in the area of intelligent fault diagnosis. Recent years have seen a surge in interest in the development of intelligent fault diagnosis techniques that make use of Machine Learning (ML). Different ML techniques for fault classification are presented in this research. Kaggle data is used after being cleaned and integrated. Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest (RF) are the ML models used. Using the metrics of evaluation, the optimal model is found. Results from experiments demonstrate that the NB will outperform other methods for fault detection in power transmission lines, with an accuracy rate of 97.77 % , recall of 97.09 % , the precision of 98.64%, and Fl-score of 97.86%.