Train Bearing Fault Diagnosis Based on Convolution Temporal-spatial Mutual Fusion Network

Journal Title: Urban Mass Transit - Year 2024, Vol 27, Issue 10

Abstract

Objective The diverse and complex operating environment of axle box bearings makes it challenging for bearing fault diagnostic methods to achieve satisfactory results with the single sensor. To address this issue, research is conducted on train bearing fault diagnosis based on convolutional temporal-spatial mutual fusion network. Method A multi-sensor fusion approach is adopted, applying the proposed CTS-MFN (a convolutional temporal-spatial mutual fusion network) for bearing fault diagnosis upon horizontal and vertical vibration datasets. The ECA module (efficient channel attention), LSTM (long short-term memory network), and similarity distance constraints are introduced to the convolutional autoencoder, enabling the model to extract temporal-spatial attention features that include inter-modal interaction information. An MLP (multilayer perceptron) is then used to fuse and infer temporal-spatial features from each modality. Result & Conclusion Comparative experiments, ablation studies, and generalization performance analysis demonstrate the effectiveness of the proposed model.

Authors and Affiliations

Jia HE

Keywords

Related Articles

Recommendations for Passenger Flow Demand-oriented City Railway Transportation Organization Optimization under Four-network Integration

Objective The construction of regional integration places higher demands on the integrated development of multi-level rail transit networks in the region. Following the trend of four-network integration, it is crucial to...

Research on Personnel Excavation in Metro Station Fire Based on Real-time Key Indicator Validation

[Objective] The objective is to accurately assess whether individuals can safely evacuate during a metro station fire, promptly identify and prevent people from entering hazardous areas, providing effective measures and...

Analysis on the Performance of New Mountain Gear Rail Train Brake

Objective The maximum slope of the mountain gear rail line can reach 250‰. As the sliding force generated by the component of the gravity is much greater than the maximum friction force between wheel and rail, relying so...

Thoughts on Coordination and Minimization of Urban Rail Transit Systems

[Objective] Current urban rail transit system faces issues such as information silos and low coordination efficiency, which hinder the ability to meet the demands for digital transformation, high safety, and high autom...

Impact Analysis of Road and Parking Lot Congestion on Urban Rail Transit Modal Share

[Objective] To determine the optimal metrics indicators for measuring parking lot congestion and road congestion levels, it is essential to study their impact on the modal share of urban rail transit. [Method] Eight...

Download PDF file
  • EP ID EP749206
  • DOI 10.16037/j.1007-869x.2024.10.003
  • Views 40
  • Downloads 0

How To Cite

Jia HE (2024). Train Bearing Fault Diagnosis Based on Convolution Temporal-spatial Mutual Fusion Network. Urban Mass Transit, 27(10), -. https://europub.co.uk./articles/-A-749206