Application of simplified convolutional neural networks for initial stator winding fault detection of the PMSM drive using different raw signal data
Abstract Permanent magnet synchronous motors (PMSM) have become one of the most substantial components of modern industrial drives. These motors, like all the others, can unfortunately undergo various failures, causing production line downtime and resulting losses. Accordingly, it is necessary to de...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-07-01
|
| Series: | IET Electric Power Applications |
| Online Access: | https://doi.org/10.1049/elp2.12066 |
| _version_ | 1811188444375810048 |
|---|---|
| author | Maciej Skowron Teresa Orlowska‐Kowalska Czeslaw T. Kowalski |
| author_facet | Maciej Skowron Teresa Orlowska‐Kowalska Czeslaw T. Kowalski |
| author_sort | Maciej Skowron |
| collection | DOAJ |
| description | Abstract Permanent magnet synchronous motors (PMSM) have become one of the most substantial components of modern industrial drives. These motors, like all the others, can unfortunately undergo various failures, causing production line downtime and resulting losses. Accordingly, it is necessary to develop fault diagnostic techniques which detect the damages at the earliest possible stage. This study presents a method of detecting incipient faults of the PMSM stator windings using direct signal analysis and a convolutional neural network (CNN). During the tests, the structures of CNN were optimised to constitute a balance between the high efficiency of fault detection and a small number of network parameters. The effectiveness of the CNNs with inputs constituted by different electrical signals measured in the drive system is compared. Three raw data signals are tested as CNN inputs, namely: stator phase currents, phase‐to‐phase voltages and axial flux, without data preprocessing. The article aims to show the possibility of detecting the incipient interturn short circuits in the PMSM stator winding based on the information obtained directly from the measured signals as well as to present the influence of the drive operating conditions and the type of measurement signals used on the structure and performance of the developed CNNs. |
| first_indexed | 2024-04-11T14:18:52Z |
| format | Article |
| id | doaj.art-4350520c8c804354902d5c38dc4ea56b |
| institution | Directory Open Access Journal |
| issn | 1751-8660 1751-8679 |
| language | English |
| last_indexed | 2024-04-11T14:18:52Z |
| publishDate | 2021-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Electric Power Applications |
| spelling | doaj.art-4350520c8c804354902d5c38dc4ea56b2022-12-22T04:19:07ZengWileyIET Electric Power Applications1751-86601751-86792021-07-0115793294610.1049/elp2.12066Application of simplified convolutional neural networks for initial stator winding fault detection of the PMSM drive using different raw signal dataMaciej Skowron0Teresa Orlowska‐Kowalska1Czeslaw T. Kowalski2Department of Electrical Machines Drives and Measurements Wroclaw University of Science and Technology Wroclaw PolandDepartment of Electrical Machines Drives and Measurements Wroclaw University of Science and Technology Wroclaw PolandDepartment of Electrical Machines Drives and Measurements Wroclaw University of Science and Technology Wroclaw PolandAbstract Permanent magnet synchronous motors (PMSM) have become one of the most substantial components of modern industrial drives. These motors, like all the others, can unfortunately undergo various failures, causing production line downtime and resulting losses. Accordingly, it is necessary to develop fault diagnostic techniques which detect the damages at the earliest possible stage. This study presents a method of detecting incipient faults of the PMSM stator windings using direct signal analysis and a convolutional neural network (CNN). During the tests, the structures of CNN were optimised to constitute a balance between the high efficiency of fault detection and a small number of network parameters. The effectiveness of the CNNs with inputs constituted by different electrical signals measured in the drive system is compared. Three raw data signals are tested as CNN inputs, namely: stator phase currents, phase‐to‐phase voltages and axial flux, without data preprocessing. The article aims to show the possibility of detecting the incipient interturn short circuits in the PMSM stator winding based on the information obtained directly from the measured signals as well as to present the influence of the drive operating conditions and the type of measurement signals used on the structure and performance of the developed CNNs.https://doi.org/10.1049/elp2.12066 |
| spellingShingle | Maciej Skowron Teresa Orlowska‐Kowalska Czeslaw T. Kowalski Application of simplified convolutional neural networks for initial stator winding fault detection of the PMSM drive using different raw signal data IET Electric Power Applications |
| title | Application of simplified convolutional neural networks for initial stator winding fault detection of the PMSM drive using different raw signal data |
| title_full | Application of simplified convolutional neural networks for initial stator winding fault detection of the PMSM drive using different raw signal data |
| title_fullStr | Application of simplified convolutional neural networks for initial stator winding fault detection of the PMSM drive using different raw signal data |
| title_full_unstemmed | Application of simplified convolutional neural networks for initial stator winding fault detection of the PMSM drive using different raw signal data |
| title_short | Application of simplified convolutional neural networks for initial stator winding fault detection of the PMSM drive using different raw signal data |
| title_sort | application of simplified convolutional neural networks for initial stator winding fault detection of the pmsm drive using different raw signal data |
| url | https://doi.org/10.1049/elp2.12066 |
| work_keys_str_mv | AT maciejskowron applicationofsimplifiedconvolutionalneuralnetworksforinitialstatorwindingfaultdetectionofthepmsmdriveusingdifferentrawsignaldata AT teresaorlowskakowalska applicationofsimplifiedconvolutionalneuralnetworksforinitialstatorwindingfaultdetectionofthepmsmdriveusingdifferentrawsignaldata AT czeslawtkowalski applicationofsimplifiedconvolutionalneuralnetworksforinitialstatorwindingfaultdetectionofthepmsmdriveusingdifferentrawsignaldata |