MVB Fault Diagnosis Based on Waveform Feature Extraction and FA-Grid SVM

The fault diagnosis of train communication network has always been achallenge in train health management. A fault diagnosis method based on waveform feature extraction and FA-Grid SVM for multi-function vehicle bus(MVB) was proposed. The time-domain features were extracted from physical waveform of...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaomin DU, Lide WANG, Zhaozhao LI, Hui SONG
Format: Article
Language:zho
Published: Editorial Department of Electric Drive for Locomotives 2020-03-01
Series:机车电传动
Subjects:
Online Access:http://edl.csrzic.com/thesisDetails#10.13890/j.issn.1000-128x.2020.02.015
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850143075048882176
author Xiaomin DU
Lide WANG
Zhaozhao LI
Hui SONG
author_facet Xiaomin DU
Lide WANG
Zhaozhao LI
Hui SONG
author_sort Xiaomin DU
collection DOAJ
description The fault diagnosis of train communication network has always been achallenge in train health management. A fault diagnosis method based on waveform feature extraction and FA-Grid SVM for multi-function vehicle bus(MVB) was proposed. The time-domain features were extracted from physical waveform of the MVB bus and used as inputs of SVM which construct MVB fault dataset. Due to the concentration of optimal parameters of SVM, a two-step parameter optimization method based on FA-Grid was provided. Experimental results show that compared with traditional grid optimization and genetic algorithm (GA), the proposed FA-Grid optimization model has lower complexity and higher efficiency and could accurately diagnose MVB faults.
format Article
id doaj-art-196d55226cc44801bc308dced7c1c1a5
institution OA Journals
issn 1000-128X
language zho
publishDate 2020-03-01
publisher Editorial Department of Electric Drive for Locomotives
record_format Article
series 机车电传动
spelling doaj-art-196d55226cc44801bc308dced7c1c1a52025-08-20T02:28:50ZzhoEditorial Department of Electric Drive for Locomotives机车电传动1000-128X2020-03-017174,8020921352MVB Fault Diagnosis Based on Waveform Feature Extraction and FA-Grid SVMXiaomin DULide WANGZhaozhao LIHui SONGThe fault diagnosis of train communication network has always been achallenge in train health management. A fault diagnosis method based on waveform feature extraction and FA-Grid SVM for multi-function vehicle bus(MVB) was proposed. The time-domain features were extracted from physical waveform of the MVB bus and used as inputs of SVM which construct MVB fault dataset. Due to the concentration of optimal parameters of SVM, a two-step parameter optimization method based on FA-Grid was provided. Experimental results show that compared with traditional grid optimization and genetic algorithm (GA), the proposed FA-Grid optimization model has lower complexity and higher efficiency and could accurately diagnose MVB faults.http://edl.csrzic.com/thesisDetails#10.13890/j.issn.1000-128x.2020.02.015MVB networkfault diagnosiswaveform feature extractionFA-Grid SVMtrain communication
spellingShingle Xiaomin DU
Lide WANG
Zhaozhao LI
Hui SONG
MVB Fault Diagnosis Based on Waveform Feature Extraction and FA-Grid SVM
机车电传动
MVB network
fault diagnosis
waveform feature extraction
FA-Grid SVM
train communication
title MVB Fault Diagnosis Based on Waveform Feature Extraction and FA-Grid SVM
title_full MVB Fault Diagnosis Based on Waveform Feature Extraction and FA-Grid SVM
title_fullStr MVB Fault Diagnosis Based on Waveform Feature Extraction and FA-Grid SVM
title_full_unstemmed MVB Fault Diagnosis Based on Waveform Feature Extraction and FA-Grid SVM
title_short MVB Fault Diagnosis Based on Waveform Feature Extraction and FA-Grid SVM
title_sort mvb fault diagnosis based on waveform feature extraction and fa grid svm
topic MVB network
fault diagnosis
waveform feature extraction
FA-Grid SVM
train communication
url http://edl.csrzic.com/thesisDetails#10.13890/j.issn.1000-128x.2020.02.015
work_keys_str_mv AT xiaomindu mvbfaultdiagnosisbasedonwaveformfeatureextractionandfagridsvm
AT lidewang mvbfaultdiagnosisbasedonwaveformfeatureextractionandfagridsvm
AT zhaozhaoli mvbfaultdiagnosisbasedonwaveformfeatureextractionandfagridsvm
AT huisong mvbfaultdiagnosisbasedonwaveformfeatureextractionandfagridsvm