Fault Detection and Diagnosis of PMSM under Unsteady State with Variable Speed and Load Conditions

Zhifu Wang; Chuang Cao; Qiang Song; Wenjiang Li

doi:10.15918/j.jbit1004-0579.201726.S105

Fault Detection and Diagnosis of PMSM under Unsteady State with Variable Speed and Load Conditions

Zhifu Wang^*, Chuang Cao, Qiang Song, Wenjiang Li

^*Corresponding author for this work

School of Mechanical Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

An integrated fault diagnosis method for stator winding faults is proposed. Based on the abc coordinate mathematical model, the fault model of permanent magnet synchronous motor was defined. Drive control system model was established in Matlab/Simulink after that. The spectrum of three-phase stator current was analyzed by fast-Fourier transform (FFT) signal processing. Harmonic component was extracted as the fault feature vector. To achieve accurate diagnosis under unsteady conditions, the three-layer feed-forward artificial neural network (ANN) and the diagnosis swarm was proposed. The diagnosis method was validated by simulation and experimentation. According to the diagnosis result, a very keen degree of recognition for three type short circuits faults was showed. The accuracy rate is over 87%.

Original language	English
Pages (from-to)	28-34
Number of pages	7
Journal	Journal of Beijing Institute of Technology (English Edition)
Volume	26
DOIs	https://doi.org/10.15918/j.jbit1004-0579.201726.S105
Publication status	Published - 1 Dec 2017

Keywords

Artificial neural network
Fast-Fourier transform(FFT)
Fault diagnosis
Permanent magnet synchronous motor (PMSM)

Access to Document

10.15918/j.jbit1004-0579.201726.S105

Cite this

@article{bd3545fc07bc471f871e37dd9afbde01,

title = "Fault Detection and Diagnosis of PMSM under Unsteady State with Variable Speed and Load Conditions",

abstract = "An integrated fault diagnosis method for stator winding faults is proposed. Based on the abc coordinate mathematical model, the fault model of permanent magnet synchronous motor was defined. Drive control system model was established in Matlab/Simulink after that. The spectrum of three-phase stator current was analyzed by fast-Fourier transform (FFT) signal processing. Harmonic component was extracted as the fault feature vector. To achieve accurate diagnosis under unsteady conditions, the three-layer feed-forward artificial neural network (ANN) and the diagnosis swarm was proposed. The diagnosis method was validated by simulation and experimentation. According to the diagnosis result, a very keen degree of recognition for three type short circuits faults was showed. The accuracy rate is over 87%.",

keywords = "Artificial neural network, Fast-Fourier transform(FFT), Fault diagnosis, Permanent magnet synchronous motor (PMSM)",

author = "Zhifu Wang and Chuang Cao and Qiang Song and Wenjiang Li",

note = "Publisher Copyright: {\textcopyright} 2017 Editorial Department of Journal of Beijing Institute of Technology.",

year = "2017",

month = dec,

day = "1",

doi = "10.15918/j.jbit1004-0579.201726.S105",

language = "English",

volume = "26",

pages = "28--34",

journal = "Journal of Beijing Institute of Technology (English Edition)",

issn = "1004-0579",

publisher = "Beijing Institute of Technology",

}

TY - JOUR

T1 - Fault Detection and Diagnosis of PMSM under Unsteady State with Variable Speed and Load Conditions

AU - Wang, Zhifu

AU - Cao, Chuang

AU - Song, Qiang

AU - Li, Wenjiang

PY - 2017/12/1

Y1 - 2017/12/1

N2 - An integrated fault diagnosis method for stator winding faults is proposed. Based on the abc coordinate mathematical model, the fault model of permanent magnet synchronous motor was defined. Drive control system model was established in Matlab/Simulink after that. The spectrum of three-phase stator current was analyzed by fast-Fourier transform (FFT) signal processing. Harmonic component was extracted as the fault feature vector. To achieve accurate diagnosis under unsteady conditions, the three-layer feed-forward artificial neural network (ANN) and the diagnosis swarm was proposed. The diagnosis method was validated by simulation and experimentation. According to the diagnosis result, a very keen degree of recognition for three type short circuits faults was showed. The accuracy rate is over 87%.

AB - An integrated fault diagnosis method for stator winding faults is proposed. Based on the abc coordinate mathematical model, the fault model of permanent magnet synchronous motor was defined. Drive control system model was established in Matlab/Simulink after that. The spectrum of three-phase stator current was analyzed by fast-Fourier transform (FFT) signal processing. Harmonic component was extracted as the fault feature vector. To achieve accurate diagnosis under unsteady conditions, the three-layer feed-forward artificial neural network (ANN) and the diagnosis swarm was proposed. The diagnosis method was validated by simulation and experimentation. According to the diagnosis result, a very keen degree of recognition for three type short circuits faults was showed. The accuracy rate is over 87%.

KW - Artificial neural network

KW - Fast-Fourier transform(FFT)

KW - Fault diagnosis

KW - Permanent magnet synchronous motor (PMSM)

UR - http://www.scopus.com/inward/record.url?scp=85054824419&partnerID=8YFLogxK

U2 - 10.15918/j.jbit1004-0579.201726.S105

DO - 10.15918/j.jbit1004-0579.201726.S105

M3 - Article

AN - SCOPUS:85054824419

SN - 1004-0579

VL - 26

SP - 28

EP - 34

JO - Journal of Beijing Institute of Technology (English Edition)

JF - Journal of Beijing Institute of Technology (English Edition)

ER -

Fault Detection and Diagnosis of PMSM under Unsteady State with Variable Speed and Load Conditions

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this