Bearing Fault Diagnosis Based on Shallow Multi-Scale Convolutional Neural Network with Attention
Recently, deep learning technology was successfully applied to mechanical fault diagnosis. The convolutional neural network (CNN), as a prevalent deep learning model, occupies a place in intelligent fault diagnosis, which reduces the need for human feature extraction and prior knowledge, thereby ach...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/12/20/3937 |
| _version_ | 1798038728666513408 |
|---|---|
| author | Tengda Huang Sheng Fu Haonan Feng Jiafeng Kuang |
| author_facet | Tengda Huang Sheng Fu Haonan Feng Jiafeng Kuang |
| author_sort | Tengda Huang |
| collection | DOAJ |
| description | Recently, deep learning technology was successfully applied to mechanical fault diagnosis. The convolutional neural network (CNN), as a prevalent deep learning model, occupies a place in intelligent fault diagnosis, which reduces the need for human feature extraction and prior knowledge, thereby achieving an end-to-end intelligent fault diagnosis model. However, the data for mechanical fault diagnosis in practical application are limited, the CNN model is too deep and too complex, making it prone to overfitting, and a model with too simple a structure and shallow layers cannot fully learn the effective features of the data. Convolutional filters with fixed window sizes are widely used in existing CNN models, which cannot flexibly select variable pivotal features. The model may be interfered with by redundant information in feature maps during training. Therefore, in this paper, a novel shallow multi-scale convolutional neural network with attention is proposed for bearing fault diagnosis. The shallow multi-scale convolutional neural network structure can fully learn the feature information of input data without overfitting. For the first time, a feature attention mechanism is developed for fault diagnosis to adaptively select features for classification more effectively, where the pivotal feature was emphasized, and the redundant feature was weakened through an attention mechanism. The time frequency representations as the input of the model were obtained from the vibration time domain signals, which contain the complete time domain and frequency domain information of the vibration signals. Compared with the current popular diagnostic methods, the results show that the proposed diagnostic method has fairly high accuracy, and its performance is superior to the existing methods. The average recognition accuracy was 99.86%, and the weak recognition rate of I-07 and I-14 labels was improved. |
| first_indexed | 2024-04-11T21:44:14Z |
| format | Article |
| id | doaj.art-bbb29e74244e4aa0b66b91bb42069ec1 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-11T21:44:14Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-bbb29e74244e4aa0b66b91bb42069ec12022-12-22T04:01:28ZengMDPI AGEnergies1996-10732019-10-011220393710.3390/en12203937en12203937Bearing Fault Diagnosis Based on Shallow Multi-Scale Convolutional Neural Network with AttentionTengda Huang0Sheng Fu1Haonan Feng2Jiafeng Kuang3Institute of Intelligent Monitoring and Diagnosis, Beijing University of Technology, Beijing 100124, ChinaInstitute of Intelligent Monitoring and Diagnosis, Beijing University of Technology, Beijing 100124, ChinaInstitute of Intelligent Monitoring and Diagnosis, Beijing University of Technology, Beijing 100124, ChinaInstitute of Intelligent Monitoring and Diagnosis, Beijing University of Technology, Beijing 100124, ChinaRecently, deep learning technology was successfully applied to mechanical fault diagnosis. The convolutional neural network (CNN), as a prevalent deep learning model, occupies a place in intelligent fault diagnosis, which reduces the need for human feature extraction and prior knowledge, thereby achieving an end-to-end intelligent fault diagnosis model. However, the data for mechanical fault diagnosis in practical application are limited, the CNN model is too deep and too complex, making it prone to overfitting, and a model with too simple a structure and shallow layers cannot fully learn the effective features of the data. Convolutional filters with fixed window sizes are widely used in existing CNN models, which cannot flexibly select variable pivotal features. The model may be interfered with by redundant information in feature maps during training. Therefore, in this paper, a novel shallow multi-scale convolutional neural network with attention is proposed for bearing fault diagnosis. The shallow multi-scale convolutional neural network structure can fully learn the feature information of input data without overfitting. For the first time, a feature attention mechanism is developed for fault diagnosis to adaptively select features for classification more effectively, where the pivotal feature was emphasized, and the redundant feature was weakened through an attention mechanism. The time frequency representations as the input of the model were obtained from the vibration time domain signals, which contain the complete time domain and frequency domain information of the vibration signals. Compared with the current popular diagnostic methods, the results show that the proposed diagnostic method has fairly high accuracy, and its performance is superior to the existing methods. The average recognition accuracy was 99.86%, and the weak recognition rate of I-07 and I-14 labels was improved.https://www.mdpi.com/1996-1073/12/20/3937bearing fault diagnosismulti-attention mechanismmulti-scale convolutional neural networktime frequency representation |
| spellingShingle | Tengda Huang Sheng Fu Haonan Feng Jiafeng Kuang Bearing Fault Diagnosis Based on Shallow Multi-Scale Convolutional Neural Network with Attention Energies bearing fault diagnosis multi-attention mechanism multi-scale convolutional neural network time frequency representation |
| title | Bearing Fault Diagnosis Based on Shallow Multi-Scale Convolutional Neural Network with Attention |
| title_full | Bearing Fault Diagnosis Based on Shallow Multi-Scale Convolutional Neural Network with Attention |
| title_fullStr | Bearing Fault Diagnosis Based on Shallow Multi-Scale Convolutional Neural Network with Attention |
| title_full_unstemmed | Bearing Fault Diagnosis Based on Shallow Multi-Scale Convolutional Neural Network with Attention |
| title_short | Bearing Fault Diagnosis Based on Shallow Multi-Scale Convolutional Neural Network with Attention |
| title_sort | bearing fault diagnosis based on shallow multi scale convolutional neural network with attention |
| topic | bearing fault diagnosis multi-attention mechanism multi-scale convolutional neural network time frequency representation |
| url | https://www.mdpi.com/1996-1073/12/20/3937 |
| work_keys_str_mv | AT tengdahuang bearingfaultdiagnosisbasedonshallowmultiscaleconvolutionalneuralnetworkwithattention AT shengfu bearingfaultdiagnosisbasedonshallowmultiscaleconvolutionalneuralnetworkwithattention AT haonanfeng bearingfaultdiagnosisbasedonshallowmultiscaleconvolutionalneuralnetworkwithattention AT jiafengkuang bearingfaultdiagnosisbasedonshallowmultiscaleconvolutionalneuralnetworkwithattention |