Fault detection of broken rotor bar in LS-PMSM using random forests
This paper proposes a new approach to diagnose broken rotor bar failure in a line start-permanent magnet synchronous motor (LS-PMSM) using random forests. The transient current signal during the motor startup was acquired from a healthy motor and a faulty motor with a broken rotor bar fault. We extr...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2018
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/72740/1/Fault%20detection%20of%20broken%20rotor%20bar%20in%20LS-PMSM%20using%20random%20forests.pdf |
| _version_ | 1825950136345296896 |
|---|---|
| author | Quiroz, Juan C. Mariun, Norman Mehrjou, Mohammad Rezazadeh Izadi, Mahdi Misron, Norhisam Mohd Radzi, Mohd Amran |
| author_facet | Quiroz, Juan C. Mariun, Norman Mehrjou, Mohammad Rezazadeh Izadi, Mahdi Misron, Norhisam Mohd Radzi, Mohd Amran |
| author_sort | Quiroz, Juan C. |
| collection | UPM |
| description | This paper proposes a new approach to diagnose broken rotor bar failure in a line start-permanent magnet synchronous motor (LS-PMSM) using random forests. The transient current signal during the motor startup was acquired from a healthy motor and a faulty motor with a broken rotor bar fault. We extracted 13 statistical time domain features from the startup transient current signal, and used these features to train and test a random forest to determine whether the motor was operating under normal or faulty conditions. For feature selection, we used the feature importances from the random forest to reduce the number of features to two features. The results showed that the random forest classifies the motor condition as healthy or faulty with an accuracy of 98.8% using all features and with an accuracy of 98.4% by using only the mean-index and impulsion features. The performance of the random forest was compared with a decision tree, Naïve Bayes classifier, logistic regression, linear ridge, and a support vector machine, with the random forest consistently having a higher accuracy than the other algorithms. The proposed approach can be used in industry for online monitoring and fault diagnostic of LS-PMSM motors and the results can be helpful for the establishment of preventive maintenance plans in factories. |
| first_indexed | 2024-03-06T10:10:00Z |
| format | Article |
| id | upm.eprints-72740 |
| institution | Universiti Putra Malaysia |
| language | English |
| last_indexed | 2024-03-06T10:10:00Z |
| publishDate | 2018 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | upm.eprints-727402021-01-30T02:23:10Z http://psasir.upm.edu.my/id/eprint/72740/ Fault detection of broken rotor bar in LS-PMSM using random forests Quiroz, Juan C. Mariun, Norman Mehrjou, Mohammad Rezazadeh Izadi, Mahdi Misron, Norhisam Mohd Radzi, Mohd Amran This paper proposes a new approach to diagnose broken rotor bar failure in a line start-permanent magnet synchronous motor (LS-PMSM) using random forests. The transient current signal during the motor startup was acquired from a healthy motor and a faulty motor with a broken rotor bar fault. We extracted 13 statistical time domain features from the startup transient current signal, and used these features to train and test a random forest to determine whether the motor was operating under normal or faulty conditions. For feature selection, we used the feature importances from the random forest to reduce the number of features to two features. The results showed that the random forest classifies the motor condition as healthy or faulty with an accuracy of 98.8% using all features and with an accuracy of 98.4% by using only the mean-index and impulsion features. The performance of the random forest was compared with a decision tree, Naïve Bayes classifier, logistic regression, linear ridge, and a support vector machine, with the random forest consistently having a higher accuracy than the other algorithms. The proposed approach can be used in industry for online monitoring and fault diagnostic of LS-PMSM motors and the results can be helpful for the establishment of preventive maintenance plans in factories. Elsevier 2018-02 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/72740/1/Fault%20detection%20of%20broken%20rotor%20bar%20in%20LS-PMSM%20using%20random%20forests.pdf Quiroz, Juan C. and Mariun, Norman and Mehrjou, Mohammad Rezazadeh and Izadi, Mahdi and Misron, Norhisam and Mohd Radzi, Mohd Amran (2018) Fault detection of broken rotor bar in LS-PMSM using random forests. Measurement, 116. 273 - 280. ISSN 0263-2241 https://www.sciencedirect.com/science/article/abs/pii/S0263224117307066 10.1016/j.measurement.2017.11.004 |
| spellingShingle | Quiroz, Juan C. Mariun, Norman Mehrjou, Mohammad Rezazadeh Izadi, Mahdi Misron, Norhisam Mohd Radzi, Mohd Amran Fault detection of broken rotor bar in LS-PMSM using random forests |
| title | Fault detection of broken rotor bar in LS-PMSM using random forests |
| title_full | Fault detection of broken rotor bar in LS-PMSM using random forests |
| title_fullStr | Fault detection of broken rotor bar in LS-PMSM using random forests |
| title_full_unstemmed | Fault detection of broken rotor bar in LS-PMSM using random forests |
| title_short | Fault detection of broken rotor bar in LS-PMSM using random forests |
| title_sort | fault detection of broken rotor bar in ls pmsm using random forests |
| url | http://psasir.upm.edu.my/id/eprint/72740/1/Fault%20detection%20of%20broken%20rotor%20bar%20in%20LS-PMSM%20using%20random%20forests.pdf |
| work_keys_str_mv | AT quirozjuanc faultdetectionofbrokenrotorbarinlspmsmusingrandomforests AT mariunnorman faultdetectionofbrokenrotorbarinlspmsmusingrandomforests AT mehrjoumohammadrezazadeh faultdetectionofbrokenrotorbarinlspmsmusingrandomforests AT izadimahdi faultdetectionofbrokenrotorbarinlspmsmusingrandomforests AT misronnorhisam faultdetectionofbrokenrotorbarinlspmsmusingrandomforests AT mohdradzimohdamran faultdetectionofbrokenrotorbarinlspmsmusingrandomforests |