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

Controlled Blasting Technology for Connection Passage between Metro Shield Sections in Hard Rock Stratum

Objective At present, a relatively systematic, mature and rapid excavation construction method for the connection passage construction in hard rock stratum has not been formed yet. Due to the small cross-section and limi...

Fire Hazard Analysis and Application in Trains

Objective Fire accidents are major safety hazards in metro operation. To reduce fire hazards to an acceptable level and ensure the safe operation of trains, the research is specifically carried out. Method The safety ana...

Evaluation Method of Bogie Outer Positioning Anti-rolling Torsion Bar Structural Strength

Objective In order to solve the TBS (torsion bar shaft) torsional stiffness and strength for the outer support anti-rolling device in railway vehicles, an analytical method of introducing the TBS deformation coordination...

Quantitative Ultrasonic Testing and Evaluation of Laser Welds for Stainless Steel Carbody of Rail Transit Vehicles

[Objective] During the laser welding process of stainless steel carbody of rail transit vehicles, energy transfer from the laser beam to the material is dynamically variable. To ensure the quality of laser welding, non...

Tram Emergency Braking Control Optimization Method Based on Magnetic Rail Braking Friction Characteristics

[Objective] The emergency braking of trams is significantly vulnerable to the characteristics of magnetic rail braking. With changes in train load and train operating speed, the instantaneous deceleration of trams can...

Download PDF file
  • EP ID EP749206
  • DOI 10.16037/j.1007-869x.2024.10.003
  • Views 46
  • 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