Rolling Bearing Degradation Identification Method Based on Improved Monopulse Feature Extraction and 1D Dilated Residual Convolutional Neural Network
To address the challenges of extracting rolling bearing degradation information and the insufficient performance of conventional convolutional networks, this paper proposes a rolling bearing degradation state identification method based on the improved monopulse feature extraction and a one-dimensio...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/14/4299 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849733141258829824 |
|---|---|
| author | Chang Liu Haiyang Wu Gang Cheng Hui Zhou Yusong Pang |
| author_facet | Chang Liu Haiyang Wu Gang Cheng Hui Zhou Yusong Pang |
| author_sort | Chang Liu |
| collection | DOAJ |
| description | To address the challenges of extracting rolling bearing degradation information and the insufficient performance of conventional convolutional networks, this paper proposes a rolling bearing degradation state identification method based on the improved monopulse feature extraction and a one-dimensional dilated residual convolutional neural network (1D-DRCNN). First, the fault pulse envelope waveform features are extracted through phase scanning and synchronous averaging, and a two-stage grid search strategy is employed to achieve FCC calibration. Subsequently, a 1D-DRCNN model is constructed to identify rolling bearing degradation states under different working conditions. The experimental study collects the vibration signals of nine degradation states, including the different sizes of inner and outer ring local faults as well as normal conditions, to comparatively analyze the proposed method’s rapid calibration capability and feature extraction quality. Furthermore, t-SNE visualization is utilized to analyze the network response to bearing degradation features. Finally, the degradation state identification performance across different network architectures is compared in pattern recognition experiments. The results show that the proposed improved feature extraction method significantly reduces the iterative calibration computational burden while effectively extracting local fault degradation information and overcoming complex working condition influence. The established 1D-DRCNN model integrates the advantages of dilated convolution and residual connections and can deeply mine sensitive features and accurately identify different bearing degradation states. The overall recognition accuracy can reach 97.33%. |
| format | Article |
| id | doaj-art-e19c873fc98d4657a64b9a6c64a5f8cb |
| institution | DOAJ |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-e19c873fc98d4657a64b9a6c64a5f8cb2025-08-20T03:08:06ZengMDPI AGSensors1424-82202025-07-012514429910.3390/s25144299Rolling Bearing Degradation Identification Method Based on Improved Monopulse Feature Extraction and 1D Dilated Residual Convolutional Neural NetworkChang Liu0Haiyang Wu1Gang Cheng2Hui Zhou3Yusong Pang4School of Mechanical and Electrical Engineering, Xuzhou University of Technology, Xuzhou 221116, ChinaSchool of Electrical and Mechanical Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Electrical and Mechanical Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Chemical Engineering and Technology, China University of Mining and Technology, Xuzhou 221116, ChinaFaculty of Mechanical Engineering, Delft University of Technology, 2628 CD Delft, The NetherlandsTo address the challenges of extracting rolling bearing degradation information and the insufficient performance of conventional convolutional networks, this paper proposes a rolling bearing degradation state identification method based on the improved monopulse feature extraction and a one-dimensional dilated residual convolutional neural network (1D-DRCNN). First, the fault pulse envelope waveform features are extracted through phase scanning and synchronous averaging, and a two-stage grid search strategy is employed to achieve FCC calibration. Subsequently, a 1D-DRCNN model is constructed to identify rolling bearing degradation states under different working conditions. The experimental study collects the vibration signals of nine degradation states, including the different sizes of inner and outer ring local faults as well as normal conditions, to comparatively analyze the proposed method’s rapid calibration capability and feature extraction quality. Furthermore, t-SNE visualization is utilized to analyze the network response to bearing degradation features. Finally, the degradation state identification performance across different network architectures is compared in pattern recognition experiments. The results show that the proposed improved feature extraction method significantly reduces the iterative calibration computational burden while effectively extracting local fault degradation information and overcoming complex working condition influence. The established 1D-DRCNN model integrates the advantages of dilated convolution and residual connections and can deeply mine sensitive features and accurately identify different bearing degradation states. The overall recognition accuracy can reach 97.33%.https://www.mdpi.com/1424-8220/25/14/4299feature extractiondegradation identificationdilated convolutionresidual connection |
| spellingShingle | Chang Liu Haiyang Wu Gang Cheng Hui Zhou Yusong Pang Rolling Bearing Degradation Identification Method Based on Improved Monopulse Feature Extraction and 1D Dilated Residual Convolutional Neural Network Sensors feature extraction degradation identification dilated convolution residual connection |
| title | Rolling Bearing Degradation Identification Method Based on Improved Monopulse Feature Extraction and 1D Dilated Residual Convolutional Neural Network |
| title_full | Rolling Bearing Degradation Identification Method Based on Improved Monopulse Feature Extraction and 1D Dilated Residual Convolutional Neural Network |
| title_fullStr | Rolling Bearing Degradation Identification Method Based on Improved Monopulse Feature Extraction and 1D Dilated Residual Convolutional Neural Network |
| title_full_unstemmed | Rolling Bearing Degradation Identification Method Based on Improved Monopulse Feature Extraction and 1D Dilated Residual Convolutional Neural Network |
| title_short | Rolling Bearing Degradation Identification Method Based on Improved Monopulse Feature Extraction and 1D Dilated Residual Convolutional Neural Network |
| title_sort | rolling bearing degradation identification method based on improved monopulse feature extraction and 1d dilated residual convolutional neural network |
| topic | feature extraction degradation identification dilated convolution residual connection |
| url | https://www.mdpi.com/1424-8220/25/14/4299 |
| work_keys_str_mv | AT changliu rollingbearingdegradationidentificationmethodbasedonimprovedmonopulsefeatureextractionand1ddilatedresidualconvolutionalneuralnetwork AT haiyangwu rollingbearingdegradationidentificationmethodbasedonimprovedmonopulsefeatureextractionand1ddilatedresidualconvolutionalneuralnetwork AT gangcheng rollingbearingdegradationidentificationmethodbasedonimprovedmonopulsefeatureextractionand1ddilatedresidualconvolutionalneuralnetwork AT huizhou rollingbearingdegradationidentificationmethodbasedonimprovedmonopulsefeatureextractionand1ddilatedresidualconvolutionalneuralnetwork AT yusongpang rollingbearingdegradationidentificationmethodbasedonimprovedmonopulsefeatureextractionand1ddilatedresidualconvolutionalneuralnetwork |