Multi-Condition PMSM Fault Diagnosis Based on Convolutional Neural Network Phase Tracker
In many industrial systems, symmetry is the key to ensuring efficiency and reliability. For example, in electric vehicles, the driving system often requires high symmetry. As widely used motors, permanent magnet synchronous motors (PMSMs) are often used in highly symmetrical structures as the drivin...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/14/2/295 |
| _version_ | 1797476419078455296 |
|---|---|
| author | Zhiwen Chen Ketian Liang Tao Peng Yang Wang |
| author_facet | Zhiwen Chen Ketian Liang Tao Peng Yang Wang |
| author_sort | Zhiwen Chen |
| collection | DOAJ |
| description | In many industrial systems, symmetry is the key to ensuring efficiency and reliability. For example, in electric vehicles, the driving system often requires high symmetry. As widely used motors, permanent magnet synchronous motors (PMSMs) are often used in highly symmetrical structures as the driving devices. Consequently, maintaining the symmetry of the system relies on the normal and stable operation of the PMSM, and it is necessary to diagnose faults in the PMSM in a timely manner. In PMSM fault diagnosis methods, frequency domain features of the stator current are extensively used. However, these features change with the switching of motor operating conditions, leading to difficulty of diagnosis in multiple operating conditions. Therefore, a fault diagnosis method based on a convolutional neural network (CNN) phase tracker is proposed in this paper. Through phase tracking and angular domain resampling, the fundamental frequency of stator currents in different operating conditions are aligned, so as to fix the distribution of frequency domain features and solve the problem of features changing with operating conditions. Experimental results show that the proposed method can resample the stator current signals with a small error, detect faults in a relatively short time with high accuracy, and diagnose fault type and severity level under multiple operating conditions. |
| first_indexed | 2024-03-09T20:58:26Z |
| format | Article |
| id | doaj.art-86ea14437bc74c939ec8a2158c0bcb72 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-09T20:58:26Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-86ea14437bc74c939ec8a2158c0bcb722023-11-23T22:16:21ZengMDPI AGSymmetry2073-89942022-02-0114229510.3390/sym14020295Multi-Condition PMSM Fault Diagnosis Based on Convolutional Neural Network Phase TrackerZhiwen Chen0Ketian Liang1Tao Peng2Yang Wang3School of Automation, Central South University, Changsha 410083, ChinaSchool of Automation, Central South University, Changsha 410083, ChinaSchool of Automation, Central South University, Changsha 410083, ChinaSchool of Electrical Engineering, Shanghai DianJi University, Shanghai 201306, ChinaIn many industrial systems, symmetry is the key to ensuring efficiency and reliability. For example, in electric vehicles, the driving system often requires high symmetry. As widely used motors, permanent magnet synchronous motors (PMSMs) are often used in highly symmetrical structures as the driving devices. Consequently, maintaining the symmetry of the system relies on the normal and stable operation of the PMSM, and it is necessary to diagnose faults in the PMSM in a timely manner. In PMSM fault diagnosis methods, frequency domain features of the stator current are extensively used. However, these features change with the switching of motor operating conditions, leading to difficulty of diagnosis in multiple operating conditions. Therefore, a fault diagnosis method based on a convolutional neural network (CNN) phase tracker is proposed in this paper. Through phase tracking and angular domain resampling, the fundamental frequency of stator currents in different operating conditions are aligned, so as to fix the distribution of frequency domain features and solve the problem of features changing with operating conditions. Experimental results show that the proposed method can resample the stator current signals with a small error, detect faults in a relatively short time with high accuracy, and diagnose fault type and severity level under multiple operating conditions.https://www.mdpi.com/2073-8994/14/2/295PMSMfault diagnosisCNNmulti-conditionorder tracking |
| spellingShingle | Zhiwen Chen Ketian Liang Tao Peng Yang Wang Multi-Condition PMSM Fault Diagnosis Based on Convolutional Neural Network Phase Tracker Symmetry PMSM fault diagnosis CNN multi-condition order tracking |
| title | Multi-Condition PMSM Fault Diagnosis Based on Convolutional Neural Network Phase Tracker |
| title_full | Multi-Condition PMSM Fault Diagnosis Based on Convolutional Neural Network Phase Tracker |
| title_fullStr | Multi-Condition PMSM Fault Diagnosis Based on Convolutional Neural Network Phase Tracker |
| title_full_unstemmed | Multi-Condition PMSM Fault Diagnosis Based on Convolutional Neural Network Phase Tracker |
| title_short | Multi-Condition PMSM Fault Diagnosis Based on Convolutional Neural Network Phase Tracker |
| title_sort | multi condition pmsm fault diagnosis based on convolutional neural network phase tracker |
| topic | PMSM fault diagnosis CNN multi-condition order tracking |
| url | https://www.mdpi.com/2073-8994/14/2/295 |
| work_keys_str_mv | AT zhiwenchen multiconditionpmsmfaultdiagnosisbasedonconvolutionalneuralnetworkphasetracker AT ketianliang multiconditionpmsmfaultdiagnosisbasedonconvolutionalneuralnetworkphasetracker AT taopeng multiconditionpmsmfaultdiagnosisbasedonconvolutionalneuralnetworkphasetracker AT yangwang multiconditionpmsmfaultdiagnosisbasedonconvolutionalneuralnetworkphasetracker |