Condition Monitoring and Fault Diagnosis of Permanent Magnet Synchronous Motor Stator Winding Using the Continuous Wavelet Transform and Machine Learning
Applying the condition monitoring technology to industrial processes can help detect faults in time, minimise their impact and reduce the cost of unplanned downtime. Since the introduction of the Industry 4.0 paradigm, many companies have been investing in the development of such technology for driv...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Sciendo
2024-01-01
|
Series: | Power Electronics and Drives |
Subjects: | |
Online Access: | https://doi.org/10.2478/pead-2024-0007 |
_version_ | 1797197553760993280 |
---|---|
author | Pietrzak Przemysław Wolkiewicz Marcin |
author_facet | Pietrzak Przemysław Wolkiewicz Marcin |
author_sort | Pietrzak Przemysław |
collection | DOAJ |
description | Applying the condition monitoring technology to industrial processes can help detect faults in time, minimise their impact and reduce the cost of unplanned downtime. Since the introduction of the Industry 4.0 paradigm, many companies have been investing in the development of such technology for drive systems. Permanent magnet synchronous motors (PMSMs) have recently been used in many industries. Therefore, the issues of condition monitoring of PMSM drives are important. This study proposes and compares diagnostic schemes based on the stator phase currents (SPCSCs) signal for condition monitoring and fault diagnosis of PMSM stator winding faults. The continuous wavelet transform (CWT) is used for the extraction of the symptoms of interturn short circuits in PMSM stator winding. Machine learning algorithms are applied to automate the detection and classification of the faults. The concept for an original and intelligent PMSM stator winding condition monitoring system is proposed. |
first_indexed | 2024-03-07T16:19:07Z |
format | Article |
id | doaj.art-c5f3439ef6f34dc1bd1bc1d3e4cefba5 |
institution | Directory Open Access Journal |
issn | 2543-4292 |
language | English |
last_indexed | 2024-04-24T06:45:48Z |
publishDate | 2024-01-01 |
publisher | Sciendo |
record_format | Article |
series | Power Electronics and Drives |
spelling | doaj.art-c5f3439ef6f34dc1bd1bc1d3e4cefba52024-04-22T19:41:03ZengSciendoPower Electronics and Drives2543-42922024-01-019110612110.2478/pead-2024-0007Condition Monitoring and Fault Diagnosis of Permanent Magnet Synchronous Motor Stator Winding Using the Continuous Wavelet Transform and Machine LearningPietrzak Przemysław0Wolkiewicz Marcin11Wrocław University of Science and Technology, 50-370Wrocław, Poland1Wrocław University of Science and Technology, 50-370Wrocław, PolandApplying the condition monitoring technology to industrial processes can help detect faults in time, minimise their impact and reduce the cost of unplanned downtime. Since the introduction of the Industry 4.0 paradigm, many companies have been investing in the development of such technology for drive systems. Permanent magnet synchronous motors (PMSMs) have recently been used in many industries. Therefore, the issues of condition monitoring of PMSM drives are important. This study proposes and compares diagnostic schemes based on the stator phase currents (SPCSCs) signal for condition monitoring and fault diagnosis of PMSM stator winding faults. The continuous wavelet transform (CWT) is used for the extraction of the symptoms of interturn short circuits in PMSM stator winding. Machine learning algorithms are applied to automate the detection and classification of the faults. The concept for an original and intelligent PMSM stator winding condition monitoring system is proposed.https://doi.org/10.2478/pead-2024-0007fault diagnosisinterturn short circuitscontinuous wavelet transformmachine learningpermanent magnet synchronous motor |
spellingShingle | Pietrzak Przemysław Wolkiewicz Marcin Condition Monitoring and Fault Diagnosis of Permanent Magnet Synchronous Motor Stator Winding Using the Continuous Wavelet Transform and Machine Learning Power Electronics and Drives fault diagnosis interturn short circuits continuous wavelet transform machine learning permanent magnet synchronous motor |
title | Condition Monitoring and Fault Diagnosis of Permanent Magnet Synchronous Motor Stator Winding Using the Continuous Wavelet Transform and Machine Learning |
title_full | Condition Monitoring and Fault Diagnosis of Permanent Magnet Synchronous Motor Stator Winding Using the Continuous Wavelet Transform and Machine Learning |
title_fullStr | Condition Monitoring and Fault Diagnosis of Permanent Magnet Synchronous Motor Stator Winding Using the Continuous Wavelet Transform and Machine Learning |
title_full_unstemmed | Condition Monitoring and Fault Diagnosis of Permanent Magnet Synchronous Motor Stator Winding Using the Continuous Wavelet Transform and Machine Learning |
title_short | Condition Monitoring and Fault Diagnosis of Permanent Magnet Synchronous Motor Stator Winding Using the Continuous Wavelet Transform and Machine Learning |
title_sort | condition monitoring and fault diagnosis of permanent magnet synchronous motor stator winding using the continuous wavelet transform and machine learning |
topic | fault diagnosis interturn short circuits continuous wavelet transform machine learning permanent magnet synchronous motor |
url | https://doi.org/10.2478/pead-2024-0007 |
work_keys_str_mv | AT pietrzakprzemysław conditionmonitoringandfaultdiagnosisofpermanentmagnetsynchronousmotorstatorwindingusingthecontinuouswavelettransformandmachinelearning AT wolkiewiczmarcin conditionmonitoringandfaultdiagnosisofpermanentmagnetsynchronousmotorstatorwindingusingthecontinuouswavelettransformandmachinelearning |