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
Engineering Application of Calculation for Interval Protection Distance between Virtual Marshalling Trains in Urban Rail Transit
[Objective] The operation of virtual marshaling trains (abbreviated as V-train) in urban rail transit meets the construction requirements for green energy conservation and green intelligence integrated development proj...
Research on Design Optimization of Levitation Controller Reliability for Medium-low Speed Maglev Vehicles
Objective Levitation controller is a key component of the medium-low speed maglev vehicle, and its reliability directly affects the stability and reliability of the vehicle′s levitation system. Therefore, it is necessary...
Theoretical Study on the Relationship between Stiffness and Modal of Railway Passenger Car Bodies
[Objective] To analyze the relationship between carbody stiffness and modal, and to provide theoretical support for the modal analysis of lightweight carbodies, it is necessary to conduct a theoretical study on both as...
Research on Smooth Tracking and Control of Stair-like Target Speed with Compatible On-Board System in Urban Rail Transit
[Objective] In view of the special phenomenon that the target speed message period is longer than the on-board control period and the message interval is not fixed in urban rail transit compatible on-board system, a dual...
Design and Realization of Urban Rail Transit AFC Intelligent Operation and Maintenance System Architecture Driven by Dual-core of Data and Model
Objective The traditional urban rail transit AFC (automatic fare collection) system suffers from maintenance problems such as slow speed, outdated method, unreasonable plan and high cost. It is necessary to adopt digital...