A novel traveling-wave-based method improved by unsupervised learning for fault location of power cables via sheath current monitoring

Mingzhen Li, Jianming Liu, Tao Zhu, Wenjun Zhou, Chengke Zhou

Research output: Contribution to journalArticle

5 Downloads (Pure)

Abstract

In order to improve the practice in maintenance of power cables, this paper proposes a novel traveling-wave-based fault location method improved by unsupervised learning. The improvement mainly lies in the identification of the arrival time of the traveling wave. The proposed approach consists of four steps: 1) the traveling wave associated with the sheath currents of the cables are grouped in a matrix; 2) the use of dimensionality reduction by t-SNE (t-distributed Stochastic Neighbor Embedding) to reconstruct the matrix features in a low dimension; 3) apply the DBSCAN (density-based spatial clustering of applications with noise) clustering, to cluster the sample points by the closeness of the sample distribution; 4) the arrival time of the traveling wave can be identified by searching for the maximum slope point of the non-noise cluster with the fewest samples. Simulations and calculations have been carried out for both HV (high voltage) and MV (medium voltage) cables. Results indicate that the arrival time of the traveling wave can be identified for both HV cables and MV cables with/without noise, and the method is suitable with few random time errors of the recorded data. A lab based experiment was carried out to validate the proposed method and helped to prove the effectiveness of the clustering and the fault location.
Original languageEnglish
Pages (from-to)2083-2107
Number of pages24
JournalSensors
Volume19
Issue number9
DOIs
Publication statusPublished - 5 May 2019

Fingerprint

Unsupervised learning
Electric fault location
sheaths
traveling waves
cables
learning
Cables
Learning
Cluster Analysis
Monitoring
arrivals
Noise
Electric potential
high voltages
electric potential
matrices
embedding
maintenance
Power (Psychology)
slopes

Keywords

  • circuit faults
  • fault currents
  • fault location
  • power cables
  • sheath currents

Cite this

Li, Mingzhen ; Liu, Jianming ; Zhu, Tao ; Zhou, Wenjun ; Zhou, Chengke. / A novel traveling-wave-based method improved by unsupervised learning for fault location of power cables via sheath current monitoring. In: Sensors. 2019 ; Vol. 19, No. 9. pp. 2083-2107.
@article{41c87101f2fd4bb4a825549162bb0949,
title = "A novel traveling-wave-based method improved by unsupervised learning for fault location of power cables via sheath current monitoring",
abstract = "In order to improve the practice in maintenance of power cables, this paper proposes a novel traveling-wave-based fault location method improved by unsupervised learning. The improvement mainly lies in the identification of the arrival time of the traveling wave. The proposed approach consists of four steps: 1) the traveling wave associated with the sheath currents of the cables are grouped in a matrix; 2) the use of dimensionality reduction by t-SNE (t-distributed Stochastic Neighbor Embedding) to reconstruct the matrix features in a low dimension; 3) apply the DBSCAN (density-based spatial clustering of applications with noise) clustering, to cluster the sample points by the closeness of the sample distribution; 4) the arrival time of the traveling wave can be identified by searching for the maximum slope point of the non-noise cluster with the fewest samples. Simulations and calculations have been carried out for both HV (high voltage) and MV (medium voltage) cables. Results indicate that the arrival time of the traveling wave can be identified for both HV cables and MV cables with/without noise, and the method is suitable with few random time errors of the recorded data. A lab based experiment was carried out to validate the proposed method and helped to prove the effectiveness of the clustering and the fault location.",
keywords = "circuit faults, fault currents, fault location, power cables, sheath currents",
author = "Mingzhen Li and Jianming Liu and Tao Zhu and Wenjun Zhou and Chengke Zhou",
note = "Acceptance in SAN TM 23/05/2019",
year = "2019",
month = "5",
day = "5",
doi = "10.3390/s19092083",
language = "English",
volume = "19",
pages = "2083--2107",
number = "9",

}

A novel traveling-wave-based method improved by unsupervised learning for fault location of power cables via sheath current monitoring. / Li, Mingzhen; Liu, Jianming; Zhu, Tao; Zhou, Wenjun; Zhou, Chengke.

In: Sensors, Vol. 19, No. 9, 05.05.2019, p. 2083-2107.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A novel traveling-wave-based method improved by unsupervised learning for fault location of power cables via sheath current monitoring

AU - Li, Mingzhen

AU - Liu, Jianming

AU - Zhu, Tao

AU - Zhou, Wenjun

AU - Zhou, Chengke

N1 - Acceptance in SAN TM 23/05/2019

PY - 2019/5/5

Y1 - 2019/5/5

N2 - In order to improve the practice in maintenance of power cables, this paper proposes a novel traveling-wave-based fault location method improved by unsupervised learning. The improvement mainly lies in the identification of the arrival time of the traveling wave. The proposed approach consists of four steps: 1) the traveling wave associated with the sheath currents of the cables are grouped in a matrix; 2) the use of dimensionality reduction by t-SNE (t-distributed Stochastic Neighbor Embedding) to reconstruct the matrix features in a low dimension; 3) apply the DBSCAN (density-based spatial clustering of applications with noise) clustering, to cluster the sample points by the closeness of the sample distribution; 4) the arrival time of the traveling wave can be identified by searching for the maximum slope point of the non-noise cluster with the fewest samples. Simulations and calculations have been carried out for both HV (high voltage) and MV (medium voltage) cables. Results indicate that the arrival time of the traveling wave can be identified for both HV cables and MV cables with/without noise, and the method is suitable with few random time errors of the recorded data. A lab based experiment was carried out to validate the proposed method and helped to prove the effectiveness of the clustering and the fault location.

AB - In order to improve the practice in maintenance of power cables, this paper proposes a novel traveling-wave-based fault location method improved by unsupervised learning. The improvement mainly lies in the identification of the arrival time of the traveling wave. The proposed approach consists of four steps: 1) the traveling wave associated with the sheath currents of the cables are grouped in a matrix; 2) the use of dimensionality reduction by t-SNE (t-distributed Stochastic Neighbor Embedding) to reconstruct the matrix features in a low dimension; 3) apply the DBSCAN (density-based spatial clustering of applications with noise) clustering, to cluster the sample points by the closeness of the sample distribution; 4) the arrival time of the traveling wave can be identified by searching for the maximum slope point of the non-noise cluster with the fewest samples. Simulations and calculations have been carried out for both HV (high voltage) and MV (medium voltage) cables. Results indicate that the arrival time of the traveling wave can be identified for both HV cables and MV cables with/without noise, and the method is suitable with few random time errors of the recorded data. A lab based experiment was carried out to validate the proposed method and helped to prove the effectiveness of the clustering and the fault location.

KW - circuit faults

KW - fault currents

KW - fault location

KW - power cables

KW - sheath currents

U2 - 10.3390/s19092083

DO - 10.3390/s19092083

M3 - Article

VL - 19

SP - 2083

EP - 2107

IS - 9

ER -