A Hybrid Data-Driven Method for Main Circuit Gound Faults Diagnosis in Electrical Traction Drive Systems

A main circuit ground fault (MCGF) is a typical system fault in an electrical traction drive system (ETDS). When two or more MCGFs occur, it will cause serious accidents. Therefore, it is particularly important to detect and handle MCGFs in a timely manner. To improve the efficiency of train operati...

Full description

Saved in:
Bibliographic Details
Main Authors: Xinyao Hou, Juntong Liu, Jinxin Zhang, Qiang Ni
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Vehicles
Subjects:
Online Access:https://www.mdpi.com/2624-8921/6/4/91
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850084955139342336
author Xinyao Hou
Juntong Liu
Jinxin Zhang
Qiang Ni
author_facet Xinyao Hou
Juntong Liu
Jinxin Zhang
Qiang Ni
author_sort Xinyao Hou
collection DOAJ
description A main circuit ground fault (MCGF) is a typical system fault in an electrical traction drive system (ETDS). When two or more MCGFs occur, it will cause serious accidents. Therefore, it is particularly important to detect and handle MCGFs in a timely manner. To improve the efficiency of train operation and ensure driving safety, this paper proposes a hybrid data-driven MCGF diagnosis method. First, the voltage signals related to the fault are selected according to the mechanism analysis of the MCGF, and then the initial feature variables are constructed according to these voltage signals. Secondly, the initial feature variables of different types of MCGF are analyzed in the time and frequency domains by wavelet transform, and four feature indicators are calculated. Finally, the fault feature indicators are trained by random forest to obtain a model for subsequent fault diagnosis. After comparative experiments using various machine learning methods, it was found that the RF used in the proposed method has a better diagnostic effect, and the correct isolation rate exceeds 99%.
format Article
id doaj-art-c94dadf046a840848f797e2b519e4072
institution DOAJ
issn 2624-8921
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Vehicles
spelling doaj-art-c94dadf046a840848f797e2b519e40722025-08-20T02:43:50ZengMDPI AGVehicles2624-89212024-11-01641872188510.3390/vehicles6040091A Hybrid Data-Driven Method for Main Circuit Gound Faults Diagnosis in Electrical Traction Drive SystemsXinyao Hou0Juntong Liu1Jinxin Zhang2Qiang Ni3School of Locomotives and Rolling Stock, Guangzhou Railway Polytechnic, Guangzhou 511300, ChinaSchool of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaA main circuit ground fault (MCGF) is a typical system fault in an electrical traction drive system (ETDS). When two or more MCGFs occur, it will cause serious accidents. Therefore, it is particularly important to detect and handle MCGFs in a timely manner. To improve the efficiency of train operation and ensure driving safety, this paper proposes a hybrid data-driven MCGF diagnosis method. First, the voltage signals related to the fault are selected according to the mechanism analysis of the MCGF, and then the initial feature variables are constructed according to these voltage signals. Secondly, the initial feature variables of different types of MCGF are analyzed in the time and frequency domains by wavelet transform, and four feature indicators are calculated. Finally, the fault feature indicators are trained by random forest to obtain a model for subsequent fault diagnosis. After comparative experiments using various machine learning methods, it was found that the RF used in the proposed method has a better diagnostic effect, and the correct isolation rate exceeds 99%.https://www.mdpi.com/2624-8921/6/4/91electrical traction drive system (ETDS)main circuit ground fault (MCGF)fault diagnosiswavelet transformrandom forest (RF)
spellingShingle Xinyao Hou
Juntong Liu
Jinxin Zhang
Qiang Ni
A Hybrid Data-Driven Method for Main Circuit Gound Faults Diagnosis in Electrical Traction Drive Systems
Vehicles
electrical traction drive system (ETDS)
main circuit ground fault (MCGF)
fault diagnosis
wavelet transform
random forest (RF)
title A Hybrid Data-Driven Method for Main Circuit Gound Faults Diagnosis in Electrical Traction Drive Systems
title_full A Hybrid Data-Driven Method for Main Circuit Gound Faults Diagnosis in Electrical Traction Drive Systems
title_fullStr A Hybrid Data-Driven Method for Main Circuit Gound Faults Diagnosis in Electrical Traction Drive Systems
title_full_unstemmed A Hybrid Data-Driven Method for Main Circuit Gound Faults Diagnosis in Electrical Traction Drive Systems
title_short A Hybrid Data-Driven Method for Main Circuit Gound Faults Diagnosis in Electrical Traction Drive Systems
title_sort hybrid data driven method for main circuit gound faults diagnosis in electrical traction drive systems
topic electrical traction drive system (ETDS)
main circuit ground fault (MCGF)
fault diagnosis
wavelet transform
random forest (RF)
url https://www.mdpi.com/2624-8921/6/4/91
work_keys_str_mv AT xinyaohou ahybriddatadrivenmethodformaincircuitgoundfaultsdiagnosisinelectricaltractiondrivesystems
AT juntongliu ahybriddatadrivenmethodformaincircuitgoundfaultsdiagnosisinelectricaltractiondrivesystems
AT jinxinzhang ahybriddatadrivenmethodformaincircuitgoundfaultsdiagnosisinelectricaltractiondrivesystems
AT qiangni ahybriddatadrivenmethodformaincircuitgoundfaultsdiagnosisinelectricaltractiondrivesystems
AT xinyaohou hybriddatadrivenmethodformaincircuitgoundfaultsdiagnosisinelectricaltractiondrivesystems
AT juntongliu hybriddatadrivenmethodformaincircuitgoundfaultsdiagnosisinelectricaltractiondrivesystems
AT jinxinzhang hybriddatadrivenmethodformaincircuitgoundfaultsdiagnosisinelectricaltractiondrivesystems
AT qiangni hybriddatadrivenmethodformaincircuitgoundfaultsdiagnosisinelectricaltractiondrivesystems