Bearing fault diagnosis with parallel CNN and LSTM
Intelligent diagnosis of bearing faults is fundamental to machinery automation and their intelligent operation. Deep learning-based analysis of bearing vibration data has emerged as one research mainstream for fault diagnosis. To enhance the quality of feature extraction from bearing vibration signa...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2024-01-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2024105?viewType=HTML |
| _version_ | 1827347988627849216 |
|---|---|
| author | Guanghua Fu Qingjuan Wei Yongsheng Yang |
| author_facet | Guanghua Fu Qingjuan Wei Yongsheng Yang |
| author_sort | Guanghua Fu |
| collection | DOAJ |
| description | Intelligent diagnosis of bearing faults is fundamental to machinery automation and their intelligent operation. Deep learning-based analysis of bearing vibration data has emerged as one research mainstream for fault diagnosis. To enhance the quality of feature extraction from bearing vibration signals and the robustness of the model, we construct a fault diagnostic model based on convolutional neural network (CNN) and long short-term memory (LSTM) parallel network to extract their temporal and spatial features from two perspectives. First, via resampling, vibration signal is split into equal-sized slices which are then converted into time-frequency images by continuous wavelet transform (CWT). Second, LSTM extracts the time-correlation features of 1D signals as one path, and 2D-CNN extracts the local frequency distribution features of time-frequency images as another path. Third, 1D-CNN further extracts integrated features from the fusion features yielded by former parallel paths. Finally, these categories are calculated through the softmax function. According to experimental results, the proposed model has satisfactory diagnostic accuracy and robustness in different contexts on two different datasets. |
| first_indexed | 2024-03-08T00:03:19Z |
| format | Article |
| id | doaj.art-b2af88e06d2d41aebdd6b4e0f7b9e777 |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-03-08T00:03:19Z |
| publishDate | 2024-01-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-b2af88e06d2d41aebdd6b4e0f7b9e7772024-02-18T01:36:18ZengAIMS PressMathematical Biosciences and Engineering1551-00182024-01-012122385240610.3934/mbe.2024105Bearing fault diagnosis with parallel CNN and LSTMGuanghua Fu0Qingjuan Wei1Yongsheng Yang2Institute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai 201306, ChinaInstitute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai 201306, ChinaInstitute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai 201306, ChinaIntelligent diagnosis of bearing faults is fundamental to machinery automation and their intelligent operation. Deep learning-based analysis of bearing vibration data has emerged as one research mainstream for fault diagnosis. To enhance the quality of feature extraction from bearing vibration signals and the robustness of the model, we construct a fault diagnostic model based on convolutional neural network (CNN) and long short-term memory (LSTM) parallel network to extract their temporal and spatial features from two perspectives. First, via resampling, vibration signal is split into equal-sized slices which are then converted into time-frequency images by continuous wavelet transform (CWT). Second, LSTM extracts the time-correlation features of 1D signals as one path, and 2D-CNN extracts the local frequency distribution features of time-frequency images as another path. Third, 1D-CNN further extracts integrated features from the fusion features yielded by former parallel paths. Finally, these categories are calculated through the softmax function. According to experimental results, the proposed model has satisfactory diagnostic accuracy and robustness in different contexts on two different datasets.https://www.aimspress.com/article/doi/10.3934/mbe.2024105?viewType=HTMLbearing fault diagnosiscwtcnnlstmparallel path |
| spellingShingle | Guanghua Fu Qingjuan Wei Yongsheng Yang Bearing fault diagnosis with parallel CNN and LSTM Mathematical Biosciences and Engineering bearing fault diagnosis cwt cnn lstm parallel path |
| title | Bearing fault diagnosis with parallel CNN and LSTM |
| title_full | Bearing fault diagnosis with parallel CNN and LSTM |
| title_fullStr | Bearing fault diagnosis with parallel CNN and LSTM |
| title_full_unstemmed | Bearing fault diagnosis with parallel CNN and LSTM |
| title_short | Bearing fault diagnosis with parallel CNN and LSTM |
| title_sort | bearing fault diagnosis with parallel cnn and lstm |
| topic | bearing fault diagnosis cwt cnn lstm parallel path |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2024105?viewType=HTML |
| work_keys_str_mv | AT guanghuafu bearingfaultdiagnosiswithparallelcnnandlstm AT qingjuanwei bearingfaultdiagnosiswithparallelcnnandlstm AT yongshengyang bearingfaultdiagnosiswithparallelcnnandlstm |