A Stress-Informed Approach with Vibration Analysis for Railway Safety Monitoring

Subject Areas : advanced manufacturing technology

Hosein Esmaili ¹ , Mohammad Ali Afshar Kazemi ² , Reza Radfar ³ , nazanin pilevari ⁴

1 - دانشجوي دكتري
2 - Department of Industrial Management, CT.C, Islamic Azad University, Tehran, Iran
3 - عضو هیات علمی دانشگاه آزاد اسلامی واحد علوم و تحقیقات
4 - Department of Industrial Management, West Tehran Branch, Islamic Azad University, Tehran, Iran

Received: 2024-12-08 Accepted : 2025-06-09 Published : 2025-11-23

Keywords: Railway Safety, Machine Learning, LIDAR Point Cloud, Random Forest, Risk Prediction, Feature Importance.,

Abstract :

Abstract: Railway safety requires diligent risk assessment due to the complexity of transportation systems. This study explored the application of machine learning, specifically Random Forest modeling, to LIDAR point clouds for predicting risks. Key features, including Z (Height), Intensity, X, and Y, were analyzed to classify risk levels into High, Medium, and Low. The model achieved perfect classification, validating its effectiveness with high accuracy and strong predictive capabilities. Feature importance analysis identified Z (Height) and Intensity as the most predictive features, aligning with expectations for LIDAR-based hazard detection. Comprehensive visualizations, such as confusion matrices and scatter plots, further corroborated the robustness of the model. Future work could integrate LIDAR data with advanced object detection models, such as YOLO, to enable real-time obstacle identification. Additionally, leveraging multi-modal learning by combining LIDAR data with visual and thermal inputs could enhance robustness under varying environmental conditions. Temporal analysis of point cloud data and the development of lightweight models for real-time applications also hold significant promise for advancing predictive capabilities in dynamic railway environments.

 

References:

[1] Z. Nan, G. Zhu, X. Zhang, X. Lin, Y. Yang, A novel high-precision railway obstacle detection algorithm based on 3D LiDAR, Sensors, Vol. 24, No. 10, 2024, p. 3148. https://doi.org/10.3390/s24103148.
[2] L. Wen, Y. Peng, M. Lin, N. Gan, R. Tan, Multi-modal contrastive learning for LiDAR point cloud rail-obstacle detection in complex weather, Electronics, Vol. 13, No. 1, 2024, p. 220. https://doi.org/10.3390/electronics13010220.
[3] J. Chen, Research on railway tunnel risk control method based on data mining, Sixth International Conference on Advanced Electronic Materials, Computers, and Software Engineering (AEMCSE 2023), Vol. 93, 2023. https://doi.org/10.1117/12.3004917.
[4] S. Cuomo, M. De Rosa, F. Piccialli, L. Pompameo, Railway safety through predictive vertical displacement analysis using the PINN-EKF synergy, Mathematics and Computers in Simulation, Vol. 223, 2024, pp. 368–379. https://doi.org/10.1016/j.matcom.2024.04.026.
[5] X. Ge, Z. Cao, Y. Qin, Y. Gao, L. Lian, J. Bai, H. Yu, An anomaly detection method for railway track using semi-supervised learning and vision-LiDAR decision fusion, IEEE Transactions on Instrumentation and Measurement, Vol. 73, 2024, pp. 1–15. https://doi.org/10.1109/tim.2024.3417537.
[6] H. Wang, X. Liu, L. Song, Y. Zhang, X. Rong, Y. Wang, Research on a train safety driving method based on fusion of an incremental clustering algorithm and lightweight shared convolution, Sensors, Vol. 24, No. 15, 2024, p. 4951. https://doi.org/10.3390/s24154951.
[7] J. Qu, S. Li, Y. Li, L. Liu, Research on railway obstacle detection method based on developed Euclidean clustering, Electronics, Vol. 12, No. 5, 2023, p. 1175. https://doi.org/10.3390/electronics12051175.
[8] M. Cserép, A. Demján, F. Mayer, B. Tábori, P. Hudoba, Effective railroad fragmentation and infrastructure recognition based on dense LiDAR point clouds, ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. V-2–2022, 2022, pp. 103–109. https://doi.org/10.5194/isprs-annals-v-2-2022-103-2022.
[9] X. Chen, P. Wang, S. Wu, Railway obstacle intrusion monitoring based on point cloud and image fusion, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023), Vol. 104, 2023. https://doi.org/10.1117/12.3011595.
[10] M. Cserep, Hungarian MLS point clouds of railroad environment and annotated ground truth data, Mendeley Data, V1, 2022. https://doi.org/10.17632/ccxpzhx9dj.1.