A Novel Hybrid Platform Based on Deep Learning for Fault Detection and Localization in a Smart Distribution Grid

The reliability of smart transmission systems critically depends on the rapid and accurate detection and localization of faults. However, existing approaches face inherent limitations; thus, traveling‐wave (TW) methods offer high localization accuracy but require stringent measurement conditions, while data‐driven models provide robustness but may suffer from reduced precision under certain scenarios. To address these challenges, this paper proposes a hybrid fault detection and localization methodology that combines physics‐based and deep learning approaches within a unified and modular framework. The proposed method integrates a TW analytical module and a one‐dimensional convolutional neural network (1D‐CNN) model, designed to exploit their complementary strengths. A key contribution of this work lies in the development of an adaptive decision fusion strategy, which combines the outputs of both modules based on confidence levels to produce a more accurate and reliable fault location estimate. The entire approach is implemented within a modular platform architecture, enabling clear separation between data acquisition, preprocessing, individual localization modules, and decision‐making. To ensure a rigorous evaluation, a large dataset of fault scenarios is generated using high‐fidelity electromagnetic transient simulations (PSCAD/EMTDC) of the Song Loulou–Logbaba 225‐kV transmission line in Cameroon, covering a wide range of fault types, locations, resistances, and operating conditions. The performance of each module and the hybrid approach is systematically assessed using standard detection and localization metrics. The results demonstrate that the TW module achieves high localization precision, while the 1D‐CNN model ensures robust detection and fault classification under varying conditions. The proposed hybrid approach significantly improves overall performance, achieving a 100% detection rate and reducing the average localization error to 0.017 km, outperforming individual methods. These findings confirm that the proposed hybrid methodology enhances both accuracy and robustness, making it a promising solution for advanced fault monitoring and protection in modern power grids.