Data-Augmentation Based CBAM-ResNet-GCN Method for Unbalance Fault Diagnosis of Rotating Machinery
In practical engineering scenarios, machines are seldom in a faulty operating state, so it is difficult to get enough available sample data to train the fault diagnosis model, leading to the problem of the small and unbalanced number of rotating machinery fault samples and low fault diagnosis accura...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10443404/ |
| _version_ | 1797243361512390656 |
|---|---|
| author | Haitao Wang Xiyang Dai Lichen Shi Mingjun Li Zelin Liu Ruihua Wang Xiaohua Xia |
| author_facet | Haitao Wang Xiyang Dai Lichen Shi Mingjun Li Zelin Liu Ruihua Wang Xiaohua Xia |
| author_sort | Haitao Wang |
| collection | DOAJ |
| description | In practical engineering scenarios, machines are seldom in a faulty operating state, so it is difficult to get enough available sample data to train the fault diagnosis model, leading to the problem of the small and unbalanced number of rotating machinery fault samples and low fault diagnosis accuracy. To solve this problem, this paper introduces a novel approach to machinery fault diagnosis. This approach involves the integration of a Convolutional Attention Residual Network (CBAM-ResNet) with a Graph Convolutional Neural Network (GCN). Firstly, to comprehensively exploit time-domain information from one-dimensional vibration signals, this study utilize Gram Angular Field (GAF) coding to transform traits of vibration signals into two-dimensional image characteristics. The resultant two-dimensional image is then expanded by applying the Wasserstein Distance Gradient Penalty Generation Adversarial Network (WGAN-GP) to produce a representative sample image. Secondly, the image is input to CBAM-ResNet to perform focused feature extraction and construct the feature matrix. Lastly, the adjacency matrix is derived through Graph Generation Layer (GGL); subsequently, the feature matrix and adjacency matrix are utilized as inputs for the GCN. After deep feature extraction, fault feature classification is executed via Softmax. Performance tests were conducted using the Case Western Reserve University bearing dataset and the planetary gearbox dataset. The method demonstrated remarkable results, achieving an accuracy of over 99% on the unbalanced dataset and surpassing 98% in 0dB noise compared to various other models. This illustrates the effectiveness and feasibility of the proposed method. |
| first_indexed | 2024-04-24T18:53:54Z |
| format | Article |
| id | doaj.art-4df3257ec6774b2bb7635f59b7102e98 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T18:53:54Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4df3257ec6774b2bb7635f59b7102e982024-03-26T17:47:00ZengIEEEIEEE Access2169-35362024-01-0112347853479910.1109/ACCESS.2024.336875510443404Data-Augmentation Based CBAM-ResNet-GCN Method for Unbalance Fault Diagnosis of Rotating MachineryHaitao Wang0https://orcid.org/0000-0001-9048-6494Xiyang Dai1https://orcid.org/0009-0001-3066-7098Lichen Shi2https://orcid.org/0000-0001-5408-9205Mingjun Li3https://orcid.org/0009-0002-7721-6988Zelin Liu4https://orcid.org/0009-0004-2759-2963Ruihua Wang5https://orcid.org/0009-0005-0835-8917Xiaohua Xia6https://orcid.org/0000-0001-7848-2255School of Mechanical and Electrical Engineering, Xi’an University of Architecture and Technology, Xi’an, ChinaSchool of Mechanical and Electrical Engineering, Xi’an University of Architecture and Technology, Xi’an, ChinaSchool of Mechanical and Electrical Engineering, Xi’an University of Architecture and Technology, Xi’an, ChinaSchool of Mechanical and Electrical Engineering, Xi’an University of Architecture and Technology, Xi’an, ChinaSchool of Mechanical and Electrical Engineering, Xi’an University of Architecture and Technology, Xi’an, ChinaSchool of Mechanical and Electrical Engineering, Xi’an University of Architecture and Technology, Xi’an, ChinaKey Laboratory of Road Construction Technology and Equipment of Ministry of Education, Chang’an University, Xi’an, ChinaIn practical engineering scenarios, machines are seldom in a faulty operating state, so it is difficult to get enough available sample data to train the fault diagnosis model, leading to the problem of the small and unbalanced number of rotating machinery fault samples and low fault diagnosis accuracy. To solve this problem, this paper introduces a novel approach to machinery fault diagnosis. This approach involves the integration of a Convolutional Attention Residual Network (CBAM-ResNet) with a Graph Convolutional Neural Network (GCN). Firstly, to comprehensively exploit time-domain information from one-dimensional vibration signals, this study utilize Gram Angular Field (GAF) coding to transform traits of vibration signals into two-dimensional image characteristics. The resultant two-dimensional image is then expanded by applying the Wasserstein Distance Gradient Penalty Generation Adversarial Network (WGAN-GP) to produce a representative sample image. Secondly, the image is input to CBAM-ResNet to perform focused feature extraction and construct the feature matrix. Lastly, the adjacency matrix is derived through Graph Generation Layer (GGL); subsequently, the feature matrix and adjacency matrix are utilized as inputs for the GCN. After deep feature extraction, fault feature classification is executed via Softmax. Performance tests were conducted using the Case Western Reserve University bearing dataset and the planetary gearbox dataset. The method demonstrated remarkable results, achieving an accuracy of over 99% on the unbalanced dataset and surpassing 98% in 0dB noise compared to various other models. This illustrates the effectiveness and feasibility of the proposed method.https://ieeexplore.ieee.org/document/10443404/Attentional mechanismfault diagnosisgram angle difference fieldgenerative adversarial networkgraph neural network (GCN)rotating machinery |
| spellingShingle | Haitao Wang Xiyang Dai Lichen Shi Mingjun Li Zelin Liu Ruihua Wang Xiaohua Xia Data-Augmentation Based CBAM-ResNet-GCN Method for Unbalance Fault Diagnosis of Rotating Machinery IEEE Access Attentional mechanism fault diagnosis gram angle difference field generative adversarial network graph neural network (GCN) rotating machinery |
| title | Data-Augmentation Based CBAM-ResNet-GCN Method for Unbalance Fault Diagnosis of Rotating Machinery |
| title_full | Data-Augmentation Based CBAM-ResNet-GCN Method for Unbalance Fault Diagnosis of Rotating Machinery |
| title_fullStr | Data-Augmentation Based CBAM-ResNet-GCN Method for Unbalance Fault Diagnosis of Rotating Machinery |
| title_full_unstemmed | Data-Augmentation Based CBAM-ResNet-GCN Method for Unbalance Fault Diagnosis of Rotating Machinery |
| title_short | Data-Augmentation Based CBAM-ResNet-GCN Method for Unbalance Fault Diagnosis of Rotating Machinery |
| title_sort | data augmentation based cbam resnet gcn method for unbalance fault diagnosis of rotating machinery |
| topic | Attentional mechanism fault diagnosis gram angle difference field generative adversarial network graph neural network (GCN) rotating machinery |
| url | https://ieeexplore.ieee.org/document/10443404/ |
| work_keys_str_mv | AT haitaowang dataaugmentationbasedcbamresnetgcnmethodforunbalancefaultdiagnosisofrotatingmachinery AT xiyangdai dataaugmentationbasedcbamresnetgcnmethodforunbalancefaultdiagnosisofrotatingmachinery AT lichenshi dataaugmentationbasedcbamresnetgcnmethodforunbalancefaultdiagnosisofrotatingmachinery AT mingjunli dataaugmentationbasedcbamresnetgcnmethodforunbalancefaultdiagnosisofrotatingmachinery AT zelinliu dataaugmentationbasedcbamresnetgcnmethodforunbalancefaultdiagnosisofrotatingmachinery AT ruihuawang dataaugmentationbasedcbamresnetgcnmethodforunbalancefaultdiagnosisofrotatingmachinery AT xiaohuaxia dataaugmentationbasedcbamresnetgcnmethodforunbalancefaultdiagnosisofrotatingmachinery |