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

Research on Metro Vehicle Wheel Wear and Reprofiling Strategy

Objective Wheel wear directly affects the vibration environment of metro vehicles. Severe abnormal wear can lead to structural fatigue exceeding the limit, reducing the safety of train operation. Therefore, it is necessa...

Analysis of Metro Vehicle Operational Stability and Safety under Crosswind Effects

Objective When urban rail transit trains operate on elevated tracks, crosswinds have a significant impact on the stability and safety of vehicle operation. It is essential to conduct a more in-depth study on the dynamics...

Sensitivity Analysis of Design Parameters for Suspended Monorail Single-ribbed Arch Bridge

[Objective] As there are few case studies on suspended monorail single-ribbed arch bridge, it is necessary to analyze the sensitivity of different design parameters to better instruct the design and construction of the b...

Quantitative Assessment Method of Emergency Disposal Operation Complexity for Urban Rail Transit Key Driving Post Personnel in Unattended Train Operation Mode

Objective With the increasing automation levels in urban rail transit, drivers responsible for operation in GOA2 (semi-automated train operation) mode become the multitasking personnel responsible for monitoring and insp...

Reflections on Several Digital Transformation Issues of Urban Rail Transit

Objective Urban rail transit digital transformation has become the future development trend of the industry. Different from the digital transformation of the manufacturing industry, as a large-scale operation service sys...

Download PDF file
  • EP ID EP749206
  • DOI 10.16037/j.1007-869x.2024.10.003
  • Views 30
  • 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