Research of Feature Extraction Method Based on Sparse Reconstruction and Multiscale Dispersion Entropy
As one of the most important components in rotating machinery, it’s necessary and essential to monitor the rolling bearing operating condition to prevent equipment failure or accidents. However, in vibration signal processing, the bearing initial fault detection under background noise is q...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2076-3417/8/6/888 |
| _version_ | 1828764824503320576 |
|---|---|
| author | Yidong Zhang Shuiguang Tong Feiyun Cong Jian Xu |
| author_facet | Yidong Zhang Shuiguang Tong Feiyun Cong Jian Xu |
| author_sort | Yidong Zhang |
| collection | DOAJ |
| description | As one of the most important components in rotating machinery, it’s necessary and essential to monitor the rolling bearing operating condition to prevent equipment failure or accidents. However, in vibration signal processing, the bearing initial fault detection under background noise is quite difficult. Therefore, in this paper a new feature extraction method combining sparse reconstruction and Multiscale Dispersion Entropy (MDErms) is proposed. Firstly, the Sliding Matrix Sequences (SMS) truncation and sparse reconstruction by Hankel-matrix are applied to the vibration signal. Then MDErms is utilized as a characteristic index of vibration signal, which is suitable for a short time series. Additionally, the MDErms is employed in the sparse reconstructed matrix sequences to achieve the Multiscale Fusion Entropy Value Sequence (MFEVS). The MFEVS keeps the fault potential feature information in different scales and is superior in distinguishing fault periodic impulses from heavy background noise. Finally, the designed FIR bandpass filter based on the MFEVS, shows prominent features in denoising and detecting weak bearing faults, which is separately verified by simulation studies and artificial fault experiments in different cases. By comparison with traditional methods like EEMD, Wavelet Packet (WP), and fast kurtogram, it can be concluded that the proposed method has a remarkable ability in removing noise and detecting rolling bearing faint fault. |
| first_indexed | 2024-12-11T06:38:56Z |
| format | Article |
| id | doaj.art-a9fa34b9d1c34c2ab643f1b06d1a07a7 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-11T06:38:56Z |
| publishDate | 2018-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-a9fa34b9d1c34c2ab643f1b06d1a07a72022-12-22T01:17:18ZengMDPI AGApplied Sciences2076-34172018-05-018688810.3390/app8060888app8060888Research of Feature Extraction Method Based on Sparse Reconstruction and Multiscale Dispersion EntropyYidong Zhang0Shuiguang Tong1Feiyun Cong2Jian Xu3The State Key Lab of Fluid Power Transmission and Controls, Zhejiang University, No.38, Zheda Rd, Hangzhou 310027, ChinaThe State Key Lab of Fluid Power Transmission and Controls, Zhejiang University, No.38, Zheda Rd, Hangzhou 310027, ChinaThe State Key Lab of Fluid Power Transmission and Controls, Zhejiang University, No.38, Zheda Rd, Hangzhou 310027, ChinaThe State Key Lab of Fluid Power Transmission and Controls, Zhejiang University, No.38, Zheda Rd, Hangzhou 310027, ChinaAs one of the most important components in rotating machinery, it’s necessary and essential to monitor the rolling bearing operating condition to prevent equipment failure or accidents. However, in vibration signal processing, the bearing initial fault detection under background noise is quite difficult. Therefore, in this paper a new feature extraction method combining sparse reconstruction and Multiscale Dispersion Entropy (MDErms) is proposed. Firstly, the Sliding Matrix Sequences (SMS) truncation and sparse reconstruction by Hankel-matrix are applied to the vibration signal. Then MDErms is utilized as a characteristic index of vibration signal, which is suitable for a short time series. Additionally, the MDErms is employed in the sparse reconstructed matrix sequences to achieve the Multiscale Fusion Entropy Value Sequence (MFEVS). The MFEVS keeps the fault potential feature information in different scales and is superior in distinguishing fault periodic impulses from heavy background noise. Finally, the designed FIR bandpass filter based on the MFEVS, shows prominent features in denoising and detecting weak bearing faults, which is separately verified by simulation studies and artificial fault experiments in different cases. By comparison with traditional methods like EEMD, Wavelet Packet (WP), and fast kurtogram, it can be concluded that the proposed method has a remarkable ability in removing noise and detecting rolling bearing faint fault.http://www.mdpi.com/2076-3417/8/6/888fault diagnosisfeature extractionrolling bearingsignal processing |
| spellingShingle | Yidong Zhang Shuiguang Tong Feiyun Cong Jian Xu Research of Feature Extraction Method Based on Sparse Reconstruction and Multiscale Dispersion Entropy Applied Sciences fault diagnosis feature extraction rolling bearing signal processing |
| title | Research of Feature Extraction Method Based on Sparse Reconstruction and Multiscale Dispersion Entropy |
| title_full | Research of Feature Extraction Method Based on Sparse Reconstruction and Multiscale Dispersion Entropy |
| title_fullStr | Research of Feature Extraction Method Based on Sparse Reconstruction and Multiscale Dispersion Entropy |
| title_full_unstemmed | Research of Feature Extraction Method Based on Sparse Reconstruction and Multiscale Dispersion Entropy |
| title_short | Research of Feature Extraction Method Based on Sparse Reconstruction and Multiscale Dispersion Entropy |
| title_sort | research of feature extraction method based on sparse reconstruction and multiscale dispersion entropy |
| topic | fault diagnosis feature extraction rolling bearing signal processing |
| url | http://www.mdpi.com/2076-3417/8/6/888 |
| work_keys_str_mv | AT yidongzhang researchoffeatureextractionmethodbasedonsparsereconstructionandmultiscaledispersionentropy AT shuiguangtong researchoffeatureextractionmethodbasedonsparsereconstructionandmultiscaledispersionentropy AT feiyuncong researchoffeatureextractionmethodbasedonsparsereconstructionandmultiscaledispersionentropy AT jianxu researchoffeatureextractionmethodbasedonsparsereconstructionandmultiscaledispersionentropy |