Train bearing fault diagnosis based on multi-sensor data fusion and dual-scale residual network

He, Deqiang; Lao, Zhenpeng; Jin, Zhenzhen; He, Changfu; Shan, Sheng; Miao, Jianyin

doi:10.1007/s11071-023-08638-w

Cited by 21 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Firstly, a brief introduction of the comparison methods was provided. Then, these methods were applied to two datasets: the TTMB Dataset [38] and the Case Western Reserve University (CWRU) Bearing Dataset. The experiments included 7-way, 4-way and 5-way diagnosis cases on the TTMB dataset and a 10-way diagnosis case on the CWRU dataset.…”

Section: Experiments and Results Analysismentioning

confidence: 99%

Improved metric-based meta learning with attention mechanism for few-shot cross-domain train bearing fault diagnosis

Zhong,

He,

Lao

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Traction motor bearings, as a crucial component of subway trains, play a pivotal role in ensuring the safety of train operations. Therefore, intelligent diagnosis of train bearings holds significant importance. However, due to the complex and dynamic nature of bearing conditions coupled with limited fault data availability, traditional diagnostic methods fail to yield satisfactory results. To address this issue, we propose an improved metrics-based meta-learning (IMML) approach for accurate few-shot cross-domain fault diagnosis of train bearings. Firstly, we introduce a 1D-signal channel attention mechanism that effectively extracts latent features and enhances recognition accuracy. Secondly, by incorporating the Adabound algorithm into our model framework, we further enhance its classification performance. Finally, through several case studies, we demonstrate the effectiveness of our proposed method in comparison to other approaches within similar settings.

show abstract

Section: Experiments and Results Analysismentioning

confidence: 99%

Improved metric-based meta learning with attention mechanism for few-shot cross-domain train bearing fault diagnosis

Zhong,

He,

Lao

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The train traction motor bearing test bench consists of a test system, control unit, and cooling system. 37 Figure 7 is the simulation test device. The test system mainly includes an electric motor, dynamic torque sensor, cylindrical roller bearing, brake system, a vibration acceleration sensor (ZM-YD500), computer and signal acquisition equipment, etc.…”

Section: Experiments and Resultsmentioning

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

“…The highly developed transportation in modern society has formed a large-scale multi-level complex transportation network, which makes people raise higher demands for the [18].…”

Section: Related Workmentioning

confidence: 99%

“…If there are multiple relationships in the connecting line, its value is equal to the sum of the proportional traffic generated by each relationship. In addition, the BC of the node needs to be redefined as shown in equation (18).…”

Section: B Design and Implementation Of Multiple Composite Network Mo...mentioning

confidence: 99%

Application of K-Shell Algorithm in Key Point Identification and Cascading Failure in Urban Public Safety Transportation Network

Xiao,

Ren

2024

IEEE Access

View full text Add to dashboard Cite

The rapid development of modern urban public transportation and people's demand for efficient transportation have made intelligent management of urban public transportation networks a hot research field. In view of this, a composite complex traffic network node classification algorithm model is established based on the shell decomposition algorithm combined with a cascading failure model. The final research findings denote that the classification refinement level of the comprehensive shell decomposition value is about 50% higher than that of the WK-shell decomposition value. The comprehensive shell decomposition algorithm, which integrates global and local influence factors, can almost achieve one shell decomposition value per node in classification. The number of layers with nodes below 30 in the actual transportation network dataset test accounts for about 98% of the total number under the improved comprehensive shell decomposition algorithm, and roughly 50% under the composite shell decomposition algorithm, indicating that the accuracy of the former algorithm is higher. When the relationship ratio in robustness testing is 1:1:1, the average comprehensive shell decomposition value is at a higher position, which is about 3% higher than the WK-shell decomposition value and about 5% higher than the traditional shell decomposition value. In addition, when the proportions are 5:1:1, 1:5:1, and 1:1:5, the failure points tested under the comprehensive shell decomposition value are still the most, indicating that the comprehensive shell decomposition value considers more factors, is more cautious, and is closer to the actual situation. Through experimental data, the proposed composite complex traffic network node classification algorithm model, which integrates improved shell decomposition algorithm and cascading failure model, has certain practicality and feasibility.

show abstract

Train bearing fault diagnosis based on multi-sensor data fusion and dual-scale residual network

Cited by 21 publications

References 41 publications

Improved metric-based meta learning with attention mechanism for few-shot cross-domain train bearing fault diagnosis

Improved metric-based meta learning with attention mechanism for few-shot cross-domain train bearing fault diagnosis

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

Application of K-Shell Algorithm in Key Point Identification and Cascading Failure in Urban Public Safety Transportation Network

Contact Info

Product

Resources

About