| Abstract: |
This research addresses the problem of faults in modern electrical grids, which cause power outages, reduced system stability, and financial losses. With the increasing sophistication of power systems due to their integration with artificial intelligence technologies, fault detection methods have become more efficient and effective. This paper proposes intelligent fault detection methods based on supervised deep learning techniques. These methods involve collecting existing electrical gauges from the power system, preprocessing the data, and applying a classification model to differentiate between normal and fault states. The model is trained using classified voltage and current datasets to enhance detection accuracy. Experimental results demonstrate that the proposed method achieves higher accuracy and faster fault detection compared to traditional methods. Its adoption enables efficient handling of large datasets, providing a scalable solution that can be integrated with other technologies to make real-time fault monitoring in smart grids more effective. Overall, this study highlights the importance of using intelligent technologies to improve the performance and safety of modern power systems.
|
