Research on fault identification method of submarine cable based on seafloor observation network

Since the seafloor observation network (SON) is located at the bottom of the ocean, in order to ensure the reliable operation of the SON system and achieve long-term stable seafloor observation tasks, reliable branch unit(BU) systems and fault identification methods are needed to isolate faults and fault identification.In view of this situation, this paper proposes a method of submarine cable protection for SON, which realizes fault isolation and fault identification of power transmission system through the designed BU and HPO-CatBoost recognition algorithm. In this paper, the BU of the SON is designed according to the actual demand, and the BU is connected to the main cable and branch cable node of the transmission submarine cable. The BU is mainly composed of the switch device and the controller part, and the main cable is used to power the controller. Then, an uninterrupted power supply scheme is proposed, and a meshed SON topology is designed. Different types of submarine cable faults are designed on this topology model. The HPO algorithm is used to find the optimal hyper-parameter combination to achieve CatBoost 's high-precision submarine cable fault identification. Finally, the leakage current of each node of the SON is calculated, and the fault location of the SON is determined according to the relationship between the leakage current and the resistance value of the submarine cable. Finally, the leakage current of each node of the SON is calculated, and the fault location of the SON is determined according to the relationship between the leakage current and the resistance value of the submarine cable. The experimental results show that the branch unit designed in this paper can accurately disconnect the fault submarine cable. The accuracy of submarine cable fault identification based on HPO-CatBoost model can reach 97.5 %. The positioning error of submarine cable fault location based on node leakage current is within 5 %, which proves the feasibility of the submarine cable fault isolation system.

Authors

Institutions

Publication Details

Journal
Alexandria Engineering Journal
Published
2025-11-28
DOI
https://doi.org/10.1016/j.aej.2025.11.045
Primary Topic
Electrical Fault Detection and Protection
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Research on fault identification method of submarine cable based on seafloor observation network

Qi Liu, Letian Fu, Weidong Wang, Xu Chu et al.
Alexandria Engineering Journal
Electrical Fault Detection and Protection
article

Research on fault identification method of submarine cable based on seafloor observation network

Qi Liu, Letian Fu, Weidong Wang, Xu Chu, Shaoshuai Yu
article en

Abstract

Since the seafloor observation network (SON) is located at the bottom of the ocean, in order to ensure the reliable operation of the SON system and achieve long-term stable seafloor observation tasks, reliable branch unit(BU) systems and fault identification methods are needed to isolate faults and fault identification.In view of this situation, this paper proposes a method of submarine cable protection for SON, which realizes fault isolation and fault identification of power transmission system through the designed BU and HPO-CatBoost recognition algorithm. In this paper, the BU of the SON is designed according to the actual demand, and the BU is connected to the main cable and branch cable node of the transmission submarine cable. The BU is mainly composed of the switch device and the controller part, and the main cable is used to power the controller. Then, an uninterrupted power supply scheme is proposed, and a meshed SON topology is designed. Different types of submarine cable faults are designed on this topology model. The HPO algorithm is used to find the optimal hyper-parameter combination to achieve CatBoost 's high-precision submarine cable fault identification. Finally, the leakage current of each node of the SON is calculated, and the fault location of the SON is determined according to the relationship between the leakage current and the resistance value of the submarine cable. Finally, the leakage current of each node of the SON is calculated, and the fault location of the SON is determined according to the relationship between the leakage current and the resistance value of the submarine cable. The experimental results show that the branch unit designed in this paper can accurately disconnect the fault submarine cable. The accuracy of submarine cable fault identification based on HPO-CatBoost model can reach 97.5 %. The positioning error of submarine cable fault location based on node leakage current is within 5 %, which proves the feasibility of the submarine cable fault isolation system.

Alexandria Engineering JournalVol. 133
Hunan University (CN)
Openalex Percentile: Top 63%
Electrical Fault Detection and Protection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.