Mei Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mei Chen has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Yu Sun
Nanjing Tech University
2 shared publications Lei Xu
School of Civil Engineering, Central South University, Changsha, People’s Republic of China
1 shared publication- Shengyang Zhu
Southwest Jiaotong University
1 shared publication Wanming Zhai
State Key Laboratory of Traction Power, Southwest Jiaotong University, Chengdu, People’s Republic of China
1 shared publication- Wanming Zhai
Southwest Jiaotong University
1 shared publication
Latest Publications
- 4 March 2021
- Published by Taylor & Francis in Vehicle System Dynamics
- Vol. 60 (7) , 2191-2210
Vibration-based damage detection of rail fastener using fully convolutional networks
The rail fastener plays an important role in supporting the rail and isolating the train-track system vibrations. Its damage detection is therefore an inevitable part in railway maintenance to ensure the system performance. Recently, deep learning techniques are widely applied to structural health monitoring, including damage detection of the rail fastener based on visions. However, the vision-based detection is mainly limited to visible damages. To address this limitation, this work presents a vibration-based detection method by introducing the fully convolutional network (FCN) to identify invisible damages of fasteners. Firstly, three damage categories are defined and five damage degrees are equivalently represented by modifying the stiffness and damping coefficients of target fasteners. Then, a vehicle-track vertically coupled dynamics model with variable vehicle speeds is established to obtain axle box accelerations (ABAs) under excitations of fastener damage and track irregularity. Finally, a fastener damage detection network is designed based on the FCN architecture to predict damage degrees by inputting the ABA, the track irregularity and the vehicle speed simultaneously. The detection performance is estimated and the network robustness to noise is analysed. The results show that the proposed method is capable of achieving accurate, real-time and robust identification of the fastener damage.
- 4 March 2021
- Published by Taylor & Francis in Vehicle System Dynamics
- Vol. 60 (7) , 2191-2210
Vibration-based damage detection of rail fastener using fully convolutional networks
The rail fastener plays an important role in supporting the rail and isolating the train-track system vibrations. Its damage detection is therefore an inevitable part in railway maintenance to ensure the system performance. Recently, deep learning techniques are widely applied to structural health monitoring, including damage detection of the rail fastener based on visions. However, the vision-based detection is mainly limited to visible damages. To address this limitation, this work presents a vibration-based detection method by introducing the fully convolutional network (FCN) to identify invisible damages of fasteners. Firstly, three damage categories are defined and five damage degrees are equivalently represented by modifying the stiffness and damping coefficients of target fasteners. Then, a vehicle-track vertically coupled dynamics model with variable vehicle speeds is established to obtain axle box accelerations (ABAs) under excitations of fastener damage and track irregularity. Finally, a fastener damage detection network is designed based on the FCN architecture to predict damage degrees by inputting the ABA, the track irregularity and the vehicle speed simultaneously. The detection performance is estimated and the network robustness to noise is analysed. The results show that the proposed method is capable of achieving accurate, real-time and robust identification of the fastener damage.
- 22 April 2019
- Published by Taylor & Francis in Vehicle System Dynamics
- Vol. 58 (7) , 1076-1100
High efficient dynamic analysis of vehicle–track–subgrade vertical interaction based on Green function method
A new method is proposed to efficiently simulate vehicle-track-subgrade vertical dynamic interactions based on the Green function method. In this simulation, the vehicle-track-subgrade system is divided into two subsystems, the vehicle-rail subsystem and the slab-subgrade subsystem, which are coupled through fastener connections. In the vehicle-rail subsystem, the vehicle is modelled as a multi-rigid-body system with 10 degrees of freedom, and the rail is simplified as a Bernoulli-Euler beam supported by rail pads. Dynamic equations of the vehicle-rail subsystem are described by differential equations. In the slab-subgrade subsystem, a three-dimensional finite element model is established to obtain the Green functions of the system induced by a unit impulse excitation. Based on the derived Green functions, dynamic equations of the slab-subgrade subsystem are formulated by the Duhamel integral. The interaction between the two subsystems is transferred by the fastener forces, and the dynamic responses of the whole system are solved through explicit numerical methods. The proposed method is subsequently validated through a detailed numerical comparison with the result obtained by the finite element method. Finally, the method is applied to investigate the dynamic property of the subgrade system under high-speed train operation.
- 22 April 2019
- Published by Taylor & Francis in Vehicle System Dynamics
- Vol. 58 (7) , 1076-1100
High efficient dynamic analysis of vehicle–track–subgrade vertical interaction based on Green function method
A new method is proposed to efficiently simulate vehicle-track-subgrade vertical dynamic interactions based on the Green function method. In this simulation, the vehicle-track-subgrade system is divided into two subsystems, the vehicle-rail subsystem and the slab-subgrade subsystem, which are coupled through fastener connections. In the vehicle-rail subsystem, the vehicle is modelled as a multi-rigid-body system with 10 degrees of freedom, and the rail is simplified as a Bernoulli-Euler beam supported by rail pads. Dynamic equations of the vehicle-rail subsystem are described by differential equations. In the slab-subgrade subsystem, a three-dimensional finite element model is established to obtain the Green functions of the system induced by a unit impulse excitation. Based on the derived Green functions, dynamic equations of the slab-subgrade subsystem are formulated by the Duhamel integral. The interaction between the two subsystems is transferred by the fastener forces, and the dynamic responses of the whole system are solved through explicit numerical methods. The proposed method is subsequently validated through a detailed numerical comparison with the result obtained by the finite element method. Finally, the method is applied to investigate the dynamic property of the subgrade system under high-speed train operation.