Fault Diagnosis of Permanent Magnet DC Motors Based on Multi-Segment Feature Extraction

For permanent magnet DC motors (PMDCMs), the amplitude of the current signals gradually decreases after the motor starts. Only using the signal features of current in a single segment is not conducive to fault diagnosis for PMDCMs. In this work, multi-segment feature extraction is presented for impr...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lixin Lu, Weihao Wang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	fault diagnosis permanent magnet DC motor support vector machine classification and regression tree <i>k</i>-nearest neighbor feature extraction Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/4038e4d982a7445a8ba7e8e5ddea4bf7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4038e4d982a7445a8ba7e8e5ddea4bf7
record_format	dspace
spelling	oai:doaj.org-article:4038e4d982a7445a8ba7e8e5ddea4bf72021-11-25T18:56:58ZFault Diagnosis of Permanent Magnet DC Motors Based on Multi-Segment Feature Extraction10.3390/s212275051424-8220https://doaj.org/article/4038e4d982a7445a8ba7e8e5ddea4bf72021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7505https://doaj.org/toc/1424-8220For permanent magnet DC motors (PMDCMs), the amplitude of the current signals gradually decreases after the motor starts. Only using the signal features of current in a single segment is not conducive to fault diagnosis for PMDCMs. In this work, multi-segment feature extraction is presented for improving the effect of fault diagnosis of PMDCMs. Additionally, a support vector machine (SVM), a classification and regression tree (CART), and the <i>k</i>-nearest neighbor algorithm (<i>k</i>-NN) are utilized for the construction of fault diagnosis models. The time domain features extracted from several successive segments of current signals make up a feature vector, which is adopted for fault diagnosis of PMDCMs. Experimental results show that multi-segment features have a better diagnostic effect than single-segment features; the average accuracy of fault diagnosis improves by 19.88%. This paper lays the foundation of fault diagnosis for PMDCMs through multi-segment feature extraction and provides a novel method for feature extraction.Lixin LuWeihao WangMDPI AGarticlefault diagnosispermanent magnet DC motorsupport vector machineclassification and regression tree<i>k</i>-nearest neighborfeature extractionChemical technologyTP1-1185ENSensors, Vol 21, Iss 7505, p 7505 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	fault diagnosis permanent magnet DC motor support vector machine classification and regression tree <i>k</i>-nearest neighbor feature extraction Chemical technology TP1-1185
spellingShingle	fault diagnosis permanent magnet DC motor support vector machine classification and regression tree <i>k</i>-nearest neighbor feature extraction Chemical technology TP1-1185 Lixin Lu Weihao Wang Fault Diagnosis of Permanent Magnet DC Motors Based on Multi-Segment Feature Extraction
description	For permanent magnet DC motors (PMDCMs), the amplitude of the current signals gradually decreases after the motor starts. Only using the signal features of current in a single segment is not conducive to fault diagnosis for PMDCMs. In this work, multi-segment feature extraction is presented for improving the effect of fault diagnosis of PMDCMs. Additionally, a support vector machine (SVM), a classification and regression tree (CART), and the <i>k</i>-nearest neighbor algorithm (<i>k</i>-NN) are utilized for the construction of fault diagnosis models. The time domain features extracted from several successive segments of current signals make up a feature vector, which is adopted for fault diagnosis of PMDCMs. Experimental results show that multi-segment features have a better diagnostic effect than single-segment features; the average accuracy of fault diagnosis improves by 19.88%. This paper lays the foundation of fault diagnosis for PMDCMs through multi-segment feature extraction and provides a novel method for feature extraction.
format	article
author	Lixin Lu Weihao Wang
author_facet	Lixin Lu Weihao Wang
author_sort	Lixin Lu
title	Fault Diagnosis of Permanent Magnet DC Motors Based on Multi-Segment Feature Extraction
title_short	Fault Diagnosis of Permanent Magnet DC Motors Based on Multi-Segment Feature Extraction
title_full	Fault Diagnosis of Permanent Magnet DC Motors Based on Multi-Segment Feature Extraction
title_fullStr	Fault Diagnosis of Permanent Magnet DC Motors Based on Multi-Segment Feature Extraction
title_full_unstemmed	Fault Diagnosis of Permanent Magnet DC Motors Based on Multi-Segment Feature Extraction
title_sort	fault diagnosis of permanent magnet dc motors based on multi-segment feature extraction
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/4038e4d982a7445a8ba7e8e5ddea4bf7
work_keys_str_mv	AT lixinlu faultdiagnosisofpermanentmagnetdcmotorsbasedonmultisegmentfeatureextraction AT weihaowang faultdiagnosisofpermanentmagnetdcmotorsbasedonmultisegmentfeatureextraction
_version_	1718410519205904384

Fault Diagnosis of Permanent Magnet DC Motors Based on Multi-Segment Feature Extraction

Ejemplares similares