Article: Fault location method for AC/DC distribution network based on wavelet transform and two-level artificial neural network Journal: International Journal of Wireless and Mobile Computing (IJWMC) 2025 Vol.29 No.3 pp.205 - 212 Abstract: In view of the increasingly complex distribution network structure in new power systems, the limitations of traditional distribution line fault point troubleshooting technology have become more prominent. This paper proposes a fault location method for AC/DC distribution networks based on wavelet transform and two-level artificial neural network. Firstly, a series of distinguishable features are extracted from the fault signals recorded by the relays in order to make the faults in the distribution network understandable by the neural network. A secondary component extraction algorithm of fault information based on wavelet transform is proposed. Then, a distribution network fault identification and location model based on a two-level artificial neural network is constructed and used to achieve accurate estimation of fault range, fault location and fault resistance. Finally, the standard IEEE 15-bus system is used to carry out case analysis. The results show that the proposed method has good identification performance for faults at different angles, different locations and different resistances. Inderscience Publishers - linking academia, business and industry through research

Title: Fault location method for AC/DC distribution network based on wavelet transform and two-level artificial neural network

Authors: Cong Liu; Ming Zhang; Rongliang Zhu; Shuang Ji; Lei Wang

Addresses: State Grid Jilin Electric Power Co., Ltd., Siping Power Supply Company, Siping, Jilin, China ' State Grid Jilin Electric Power Co., Ltd., Siping Power Supply Company, Siping, Jilin, China ' State Grid Jilin Electric Power Co., Ltd., Siping Power Supply Company, Siping, Jilin, China ' State Grid Jilin Electric Power Co., Ltd., Siping Power Supply Company, Siping, Jilin, China ' State Grid Jilin Electric Power Co., Ltd., Siping Power Supply Company, Siping, Jilin, China

Abstract: In view of the increasingly complex distribution network structure in new power systems, the limitations of traditional distribution line fault point troubleshooting technology have become more prominent. This paper proposes a fault location method for AC/DC distribution networks based on wavelet transform and two-level artificial neural network. Firstly, a series of distinguishable features are extracted from the fault signals recorded by the relays in order to make the faults in the distribution network understandable by the neural network. A secondary component extraction algorithm of fault information based on wavelet transform is proposed. Then, a distribution network fault identification and location model based on a two-level artificial neural network is constructed and used to achieve accurate estimation of fault range, fault location and fault resistance. Finally, the standard IEEE 15-bus system is used to carry out case analysis. The results show that the proposed method has good identification performance for faults at different angles, different locations and different resistances.

Keywords: wavelet transform; artificial neural networks; AC/DC distribution network; fault localisation; fault identification; fault resistance.

DOI: 10.1504/IJWMC.2025.148590

International Journal of Wireless and Mobile Computing, 2025 Vol.29 No.3, pp.205 - 212

Received: 16 Dec 2024
Accepted: 01 Mar 2025
Published online: 14 Sep 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Fault location method for AC/DC distribution network based on wavelet transform and two-level artificial neural network

Keep up-to-date