@article{Zhou2026, 
author = {Miaomiao Zhou and Mengshi Li and Haiting Shan and Q. H. Wu},
title = {Distribution Network Fault Diagnosis Based on Hybrid Model and Data-driven Approach with Grey Wolf Hunting and Spatial Contraction Strategy},
year = {2026},
journal = {CSEE Journal of Power and Energy Systems},
volume = {12},
number = {3},
pages = {1448-1457},
keywords = {Distribution network, fault classification, fault diagnosis, fault location, grey wolf optimisation},
url = {https://www.sciopen.com/article/10.17775/CSEEJPES.2024.03930},
doi = {10.17775/CSEEJPES.2024.03930},
abstract = {Swift and precise fault location in distribution networks is paramount for minimising outage losses and expediting power restoration. This paper proposes a hybrid fault location technique based on data and model fusion, which formulates the fault localization task as an optimization problem. The technique tackles three key problems: fault classification, line identification and precise location in distribution networks. The technique hinges on the Grey Wolf Hunting (GWH) algorithm, which has significant advantages in exploring and exploiting capabilities, and the spatial contraction strategy (SCS), which significantly curtails computational expense. Simulation results demonstrate the proposed technique’s commendable performance in recognition accuracy and location precision, alongside robust noise immunity. Meanwhile, this hybird data and model fusion driven technique can be flexibly applied to different distribution networks.}
}