Rotor Fault Diagnosis Based on Characteristic Frequency Band Energy Entropy and Support Vector Machine
Rotor is a widely used and easily defected mechanical component. Thus, it is significant to develop effective techniques for rotor fault diagnosis. Fault signature extraction and state classification of the extracted signatures are two key steps for diagnosing rotor faults. To complete the accurate...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-12-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/20/12/932 |
| _version_ | 1798005653287993344 |
|---|---|
| author | Bin Pang Guiji Tang Chong Zhou Tian Tian |
| author_facet | Bin Pang Guiji Tang Chong Zhou Tian Tian |
| author_sort | Bin Pang |
| collection | DOAJ |
| description | Rotor is a widely used and easily defected mechanical component. Thus, it is significant to develop effective techniques for rotor fault diagnosis. Fault signature extraction and state classification of the extracted signatures are two key steps for diagnosing rotor faults. To complete the accurate recognition of rotor states, a novel evaluation index named characteristic frequency band energy entropy (CFBEE) was proposed to extract the defective features of rotors, and support vector machine (SVM) was employed to automatically identify the rotor fault types. Specifically, the raw vibration signal of rotor was first analyzed by a joint time⁻frequency method based on improved singular spectrum decomposition (ISSD) and Hilbert transform (HT) to derive its time⁻frequency spectrum (TFS), which is named ISSD-HT TFS in this paper. Then, the CFBEE of the ISSD-HT TFS was calculated as the fault feature vector. Finally, SVM was used to complete the automatic identification of rotor faults. Simulated processing results indicate that ISSD improves the end effects of singular spectrum decomposition (SSD) and is superior to empirical mode decomposition (EMD) in extracting the sub-components of rotor vibration signal. The ISSD-HT TFS can more accurately reflect the time⁻frequency information compared to the EMD-HT TFS. Experimental verification demonstrates that the proposed method can accurately identify rotor defect types and outperform some other methods. |
| first_indexed | 2024-04-11T12:42:45Z |
| format | Article |
| id | doaj.art-1116a69aac4b490e92fda0a7a8aef46d |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-04-11T12:42:45Z |
| publishDate | 2018-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-1116a69aac4b490e92fda0a7a8aef46d2022-12-22T04:23:26ZengMDPI AGEntropy1099-43002018-12-01201293210.3390/e20120932e20120932Rotor Fault Diagnosis Based on Characteristic Frequency Band Energy Entropy and Support Vector MachineBin Pang0Guiji Tang1Chong Zhou2Tian Tian3Department of Mechanical Engineering, North China Electric Power University, Baoding 071000, ChinaDepartment of Mechanical Engineering, North China Electric Power University, Baoding 071000, ChinaDepartment of Mechanical Engineering, North China Electric Power University, Baoding 071000, ChinaDepartment of Mechanical Engineering, North China Electric Power University, Baoding 071000, ChinaRotor is a widely used and easily defected mechanical component. Thus, it is significant to develop effective techniques for rotor fault diagnosis. Fault signature extraction and state classification of the extracted signatures are two key steps for diagnosing rotor faults. To complete the accurate recognition of rotor states, a novel evaluation index named characteristic frequency band energy entropy (CFBEE) was proposed to extract the defective features of rotors, and support vector machine (SVM) was employed to automatically identify the rotor fault types. Specifically, the raw vibration signal of rotor was first analyzed by a joint time⁻frequency method based on improved singular spectrum decomposition (ISSD) and Hilbert transform (HT) to derive its time⁻frequency spectrum (TFS), which is named ISSD-HT TFS in this paper. Then, the CFBEE of the ISSD-HT TFS was calculated as the fault feature vector. Finally, SVM was used to complete the automatic identification of rotor faults. Simulated processing results indicate that ISSD improves the end effects of singular spectrum decomposition (SSD) and is superior to empirical mode decomposition (EMD) in extracting the sub-components of rotor vibration signal. The ISSD-HT TFS can more accurately reflect the time⁻frequency information compared to the EMD-HT TFS. Experimental verification demonstrates that the proposed method can accurately identify rotor defect types and outperform some other methods.https://www.mdpi.com/1099-4300/20/12/932improved singular spectrum decompositioncharacteristic frequency band energy entropysupport vector machinerotorfault diagnosis |
| spellingShingle | Bin Pang Guiji Tang Chong Zhou Tian Tian Rotor Fault Diagnosis Based on Characteristic Frequency Band Energy Entropy and Support Vector Machine Entropy improved singular spectrum decomposition characteristic frequency band energy entropy support vector machine rotor fault diagnosis |
| title | Rotor Fault Diagnosis Based on Characteristic Frequency Band Energy Entropy and Support Vector Machine |
| title_full | Rotor Fault Diagnosis Based on Characteristic Frequency Band Energy Entropy and Support Vector Machine |
| title_fullStr | Rotor Fault Diagnosis Based on Characteristic Frequency Band Energy Entropy and Support Vector Machine |
| title_full_unstemmed | Rotor Fault Diagnosis Based on Characteristic Frequency Band Energy Entropy and Support Vector Machine |
| title_short | Rotor Fault Diagnosis Based on Characteristic Frequency Band Energy Entropy and Support Vector Machine |
| title_sort | rotor fault diagnosis based on characteristic frequency band energy entropy and support vector machine |
| topic | improved singular spectrum decomposition characteristic frequency band energy entropy support vector machine rotor fault diagnosis |
| url | https://www.mdpi.com/1099-4300/20/12/932 |
| work_keys_str_mv | AT binpang rotorfaultdiagnosisbasedoncharacteristicfrequencybandenergyentropyandsupportvectormachine AT guijitang rotorfaultdiagnosisbasedoncharacteristicfrequencybandenergyentropyandsupportvectormachine AT chongzhou rotorfaultdiagnosisbasedoncharacteristicfrequencybandenergyentropyandsupportvectormachine AT tiantian rotorfaultdiagnosisbasedoncharacteristicfrequencybandenergyentropyandsupportvectormachine |