Visualized Stacked Denoising Auto-Encoder Model for Extracting and Evaluating the State Features of Rolling Bearings
Extracting intuitive operating state features from vibration signals without prior knowledge is a prospective requirement for health monitoring and fault diagnosis in bearings. In this paper, a visualized stacked denoising auto-encoder (VSDAE) model is proposed for the unsupervised extraction and qu...
| Published in: | Machines |
|---|---|
| Main Authors: | , , , |
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/10/10/849 |
| _version_ | 1851952948378075136 |
|---|---|
| author | Qing Zhang Junshen Zhang Ye Wang Lie Chen |
| author_facet | Qing Zhang Junshen Zhang Ye Wang Lie Chen |
| author_sort | Qing Zhang |
| collection | DOAJ |
| container_title | Machines |
| description | Extracting intuitive operating state features from vibration signals without prior knowledge is a prospective requirement for health monitoring and fault diagnosis in bearings. In this paper, a visualized stacked denoising auto-encoder (VSDAE) model is proposed for the unsupervised extraction and quantitative evaluation of bearings’ state features. First, the stacked denoising auto-encoder (SDAE) was used to reconstruct vibration signals. The intermediate vector of the SDAE, which is a high-information-density representation of vibration signals, was regarded as the pending state feature. Then, the dimension of the intermediate vector was reduced by the <i>t</i>-distributed stochastic neighbor embedding (<i>t</i>-SNE) method to the two-dimensional visualization space. Finally, the silhouette coefficient of feature distribution was calculated to quantitatively evaluate the extracted features. The proposed model was evaluated using experimental bearing signals simulating various operating states. The results proved that the features, extracted and evaluated by the VSDAE, allowed the recognition of the operating states of the examined bearings. |
| format | Article |
| id | doaj-art-ddb2fccc1901411c853a23bccc3147fc |
| institution | Directory of Open Access Journals |
| issn | 2075-1702 |
| language | English |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| spelling | doaj-art-ddb2fccc1901411c853a23bccc3147fc2025-08-19T21:45:54ZengMDPI AGMachines2075-17022022-09-01101084910.3390/machines10100849Visualized Stacked Denoising Auto-Encoder Model for Extracting and Evaluating the State Features of Rolling BearingsQing Zhang0Junshen Zhang1Ye Wang2Lie Chen3School of Mechanical Engineering, Xi′an Jiaotong University, Xi′an 710049, ChinaSchool of Mechanical Engineering, Xi′an Jiaotong University, Xi′an 710049, ChinaSchool of Mechanical Engineering, Xi′an Jiaotong University, Xi′an 710049, ChinaSchool of Mechanical Engineering, Xi′an Jiaotong University, Xi′an 710049, ChinaExtracting intuitive operating state features from vibration signals without prior knowledge is a prospective requirement for health monitoring and fault diagnosis in bearings. In this paper, a visualized stacked denoising auto-encoder (VSDAE) model is proposed for the unsupervised extraction and quantitative evaluation of bearings’ state features. First, the stacked denoising auto-encoder (SDAE) was used to reconstruct vibration signals. The intermediate vector of the SDAE, which is a high-information-density representation of vibration signals, was regarded as the pending state feature. Then, the dimension of the intermediate vector was reduced by the <i>t</i>-distributed stochastic neighbor embedding (<i>t</i>-SNE) method to the two-dimensional visualization space. Finally, the silhouette coefficient of feature distribution was calculated to quantitatively evaluate the extracted features. The proposed model was evaluated using experimental bearing signals simulating various operating states. The results proved that the features, extracted and evaluated by the VSDAE, allowed the recognition of the operating states of the examined bearings.https://www.mdpi.com/2075-1702/10/10/849stacked denoising auto-encodervisualizationfeature extractionfeature evaluationrolling bearing |
| spellingShingle | Qing Zhang Junshen Zhang Ye Wang Lie Chen Visualized Stacked Denoising Auto-Encoder Model for Extracting and Evaluating the State Features of Rolling Bearings stacked denoising auto-encoder visualization feature extraction feature evaluation rolling bearing |
| title | Visualized Stacked Denoising Auto-Encoder Model for Extracting and Evaluating the State Features of Rolling Bearings |
| title_full | Visualized Stacked Denoising Auto-Encoder Model for Extracting and Evaluating the State Features of Rolling Bearings |
| title_fullStr | Visualized Stacked Denoising Auto-Encoder Model for Extracting and Evaluating the State Features of Rolling Bearings |
| title_full_unstemmed | Visualized Stacked Denoising Auto-Encoder Model for Extracting and Evaluating the State Features of Rolling Bearings |
| title_short | Visualized Stacked Denoising Auto-Encoder Model for Extracting and Evaluating the State Features of Rolling Bearings |
| title_sort | visualized stacked denoising auto encoder model for extracting and evaluating the state features of rolling bearings |
| topic | stacked denoising auto-encoder visualization feature extraction feature evaluation rolling bearing |
| url | https://www.mdpi.com/2075-1702/10/10/849 |
| work_keys_str_mv | AT qingzhang visualizedstackeddenoisingautoencodermodelforextractingandevaluatingthestatefeaturesofrollingbearings AT junshenzhang visualizedstackeddenoisingautoencodermodelforextractingandevaluatingthestatefeaturesofrollingbearings AT yewang visualizedstackeddenoisingautoencodermodelforextractingandevaluatingthestatefeaturesofrollingbearings AT liechen visualizedstackeddenoisingautoencodermodelforextractingandevaluatingthestatefeaturesofrollingbearings |