A lightweight model for train bearing fault diagnosis based on multiscale attentional feature fusion

He, Changfu; He, Deqiang; Lao, Zhenpeng; Wei, Zexian; Xiang, Zaiyu; Xiang, Weibin

doi:10.1088/1361-6501/aca170

Cited by 10 publications

(8 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset [47] is widely used in bearing fault diagnosis tasks [48]. The components of the experimental rig are shown in figure 20.…”

Section: Methodsmentioning

confidence: 99%

A new weak fault diagnosis approach for train bearings based on improved grey wolf optimizer and adaptive variational mode decomposition

Jin

et al. 2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Accurately identifying the health status of train running gear bearings is crucial to en-sure the quality of operation. As the early fault information of bearings is weak and submerged in the complex noise environment, which is difficult to diagnose. Therefore, a new weak fault diagnosis approach for train running gear bearings based on variational mode decomposition (VMD) with improved performance and refined weighted kurtosis (RWK) index is proposed to solve this problem. First, an improved grey wolf optimizer (IGWO) based on a variety of strategies is proposed. Secondly, the VMD performance is improved using the IGWO algorithm, and the improved VMD is used to process the early weak signals of bearings. A new fault-sensitive index called the RWK is proposed to detect the mode with the most fault information. Finally, the envelope analysis of the characteristic signals is performed to achieve the early weak fault diagnosis of bearings. Compared with the other nine optimization algorithms, the IGWO algorithm has strong optimization ability, stable performance and a fast convergence speed. Four cases verify that the RWK index has the highest sensitivity to fault information and can more effec-tively filter out modal components containing rich fault information than the compari-son methods.

show abstract

“…The dataset [47] is widely used in bearing fault diagnosis tasks [48]. The components of the experimental rig are shown in figure 20.…”

Section: Methodsmentioning

confidence: 99%

A new weak fault diagnosis approach for train bearings based on improved grey wolf optimizer and adaptive variational mode decomposition

Jin

et al. 2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Efforts need to be made to maintain the lightweight nature of a model while ensuring its performance. Based on multiscale attentional feature fusion, a lightweight CNN was proposed by He et al [29] to have better fault diagnosis performance than contrast models. Combined with a convolutional attention mechanism, an improved CNN was proposed by Chang et al [30] to improve the network feature extraction efficiency and reduce the network complexity.…”

Section: Attention Mechanismmentioning

confidence: 99%

Rapid learning of bearing signal pattern using CfCs promoted by a self-attention mechanism

Yang,

Pan,

Zhou

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Deep learning is helpful for improving the fault recognition ability of bearings, but this kind of model relies on a large number of training samples and computing resources. In this paper, an algorithm termed a closed-form continuous-depth neural network (CfC) assisted by an information compression-interaction (ICI) module and spatial conjunction attention (SCA) module (CfC-ISCA) is proposed. The ICI module extracts the main features of input signals, the SCA module is designed for positioning target features and capturing more useful features, and the CfC module is used to further fuse features and achieve rapid learning of samples. This algorithm can learn bearing fault signal patterns rapidly and has excellent fault identification ability under small sample conditions. Some public datasets are used to validate the model performance. The test results show that the proposed CfC-ISCA algorithm has comprehensive advantages in fault signal recognition, consumption of computing resources and fast learning compared to comparative methods.

show abstract

“…38 Results and analysis. To verify the effectiveness and robustness of the IDRN model, the CNN, LeNet, 39 MA-LCNN, 31 IDRN model has obvious advantages in convergence speed and accuracy.…”

Section: Case 1: Bearing Dataset Of Train Traction Motormentioning

confidence: 99%

“…The overall fault recognition accuracy of the new method is improved by 6.75%, and both the diagnosis accuracy and training speed are increased. He et al 31 proposed a lightweight CNN based on multiscale attentional feature fusion. The squeeze and excitation (SE) attention mechanism can strengthen the features of important channels and weaken the features of non-important channels, which makes the model obtain good results in bearing fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Fault diagnosis of train traction motor bearing based on improved deep residual network

Sun,

He,

Lao

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part C:

Self Cite

View full text Add to dashboard Cite

As one of the important components of train traction motor, the bearing plays a key role in ensuring the safety of train operation. At present, the existing fault diagnosis methods for train traction motor bearings have the disadvantages of poor feature extraction ability, slow diagnosis speed, and low diagnosis accuracy. To solve the above problems, an improved deep residual network (IDRN) is proposed in this paper. Firstly, a new residual convolution block (RCB) is proposed to improve the extraction ability of hidden features. Secondly, the squeeze and excitation block (SE) is embedded in the residual block to increase the sensitivity of the model to features. Lastly, Adan is selected as the optimizer to increase the convergence speed of IDRN. The train traction motor bearing bench built by our research team is selected for the experiment. The results show that the test accuracy of IDRN on the bearing dataset of train traction motor is 98.72%, which is at least 2.27% higher than other comparative models. The IDRN model converges with fewer iterations in the training process, shortening the entire experiment time. At the same time, the CWRU bearing dataset and the bearing dataset with natural defects are selected for comparative verification. The experimental results show that the IDRN model exhibits strong robustness and practicability on different datasets.

show abstract

A lightweight model for train bearing fault diagnosis based on multiscale attentional feature fusion

Cited by 10 publications

References 46 publications

A new weak fault diagnosis approach for train bearings based on improved grey wolf optimizer and adaptive variational mode decomposition

A new weak fault diagnosis approach for train bearings based on improved grey wolf optimizer and adaptive variational mode decomposition

Rapid learning of bearing signal pattern using CfCs promoted by a self-attention mechanism

Fault diagnosis of train traction motor bearing based on improved deep residual network

Contact Info

Product

Resources

About