Analyzing faults in distribution networks is essential for maintaining a reliable and efficient electrical supply. The study employs advanced signal processing techniques and deep learning algorithms to accurately identify, classify, and locate different fault types such as symmetrical, unsymmetrical, and high impedance faults (HIFs). The proposed method is validated through extensive simulations and diverse fault scenarios with varying fault resistance values, demonstrating its effectiveness in improving fault management in contemporary Distribution Networks. Furthermore, this research introduces a novel approach for the rapid detection and localization of HIFs in distribution networks. HIFs are difficult to detect in power distribution systems due to their intermittent nature and low fault currents.