Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 2;15(1):23288.
doi: 10.1038/s41598-025-05202-x.

Intelligent identification of ballastless track subgrade settlement based on vehicle-rail vibration data

Chong Li  1 , Yu Guo  2   3   4
Affiliations

Intelligent identification of ballastless track subgrade settlement based on vehicle-rail vibration data

Chong Li et al. Sci Rep. .

Abstract

Monitoring uneven subgrade settlement in ballastless track systems remains challenging due to the limited accuracy and discontinuous nature of conventional detection methods. In this study, we propose a novel deep learning approach based on a convolutional neural network and long short-term memory (CNN-LSTM) model to accurately identify uneven subgrade settlement by analyzing vehicle-rail dynamic response data. First, a vehicle-track-subgrade coupled model simulates vibration responses under differential settlements. Through sensitivity analysis of vehicle and track dynamics, we identify carbody vertical acceleration, nodding angular velocity, and rail displacement as optimal CNN-LSTM inputs. By leveraging the convolutional neural network (CNN)'s capability to extract spatial features and the long short-term memory (LSTM)'s strength in capturing temporal dependencies, the hybrid network effectively models the relationships between dynamic indicators and subgrade settlement. The results indicate that combined vehicle-rail responses enhances identification, particularly for track-subgrade deformation mismatches. The CNN-LSTM model achieves a detection accuracy of 99.26%, outperforming four benchmark models-backpropagation (BP) neural network, radial basis function (RBF) network, CNN, and LSTM-which validates its robustness and practical effectiveness. This research provides both theoretical insights and practical guidelines for intelligent monitoring of subgrade settlement in ballastless track systems.

Keywords: Ballastless track; CNN-LSTM network; Intelligent identification; Uneven subgrade settlement; Vehicle-track-subgrade dynamic model.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Technical route of this study.
Fig. 2
Fig. 2
Dynamic model diagram of the vehicle-track-subgrade coupled system.
Fig. 3
Fig. 3
An example LSTM cell.
Fig. 4
Fig. 4
CNN-LSTM network structure.
Fig. 5
Fig. 5
Correlation analysis diagram of subgrade settlement.
Fig. 6
Fig. 6
Chart of sensitive indicators under different work condition.
Fig. 6
Fig. 6
Chart of sensitive indicators under different work condition.
Fig. 7
Fig. 7
CNN-LSTM recognition result.
Fig. 8
Fig. 8
Multi-source vs. single-source identification.
Fig. 9
Fig. 9
Comparative analysis identification.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Zhang, X., Burrow, M. & Zhou, S. An investigation of subgrade differential settlement on the dynamic response of the vehicle–track system. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit 230.7 : 1760–1773. (2016).
    1. Lazorenko, G. et al. Dynamic behavior and stability of soil foundation in heavy haul railway tracks: A review. Constr. Build. Mater.205, 111–136 (2019).
    1. Guo, Y., Zhai, W. & Sun, Y. A mechanical model of vehicle-slab track coupled system with differential subgrade settlement. Struct. Eng. Mechanics: Int. J.66(1), 15–25 (2018).
    1. Jiang, H. et al. Geometry mapping and additional stresses of ballastless track structure caused by subgrade differential settlement under self-weight loads in high-speed railways. Transp. Geotechnics. 18, 103–110 (2019).
    1. Qiu, D. et al. Safety monitoring information system of urban subway. 2009 WASE International Conference on Information Engineering. Vol. 2. IEEE, (2009).

LinkOut - more resources