Research on the Construction and Application of AI-Based Failure Prediction Model for Rail Transportation Equipment

Tao Lin

doi:10.62051/ijcsit.v6n3.05

Authors

Tao Lin

DOI:

https://doi.org/10.62051/ijcsit.v6n3.05

Keywords:

Rail transportation, Fault prediction, Artificial intelligence, Smart city

Abstract

In order to improve the intelligent operation and maintenance level of rail transit systems in smart cities, the application of artificial intelligence (AI)-based fault prediction models in rail transit equipment maintenance is studied. A fault prediction model with strong predictive ability and adaptability is constructed by fusing multi-source data, including equipment operation status, environmental factors and city dynamic information. The results show that the model has significant advantages in reducing operation interruptions, lowering maintenance costs, optimizing resource scheduling, and improving the reliability and efficiency of rail transit systems. Through multi-system collaboration and intelligent operation and maintenance, the model helps to promote the intelligent upgrading of rail transit and improve the response speed and service quality of urban transportation systems.

Downloads

Download data is not yet available.

References

[1] Sun Y, Dai C. Application of Artificial Intelligence in Condition Monitoring and Predictive Maintenance of Rail Transit Vehicle Equipment [C]// Proceedings of the 2024 Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence. 2024: 801-806. 801-806.

[2] Zeng C, Huang J, Wang H, et al. Rail break prediction and cause analysis using imbalanced in-service train data [J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-14.

[3] Daniyan I, Mpofu K, Muvunzi R, et al. Implementation of Artificial intelligence for maintenance operation in the rail industry [J]. Procedia CIRP, 2022, 109: 449-453.

[4] WANG Yue-Long, LIU Peng, YAO Wei-Jun. Prediction of the number of overhaul even replacement parts for key equipment of rail transit vehicles based on ARIMA-SVR model [J]. Urban Rail Transportation Research, 2025, 28(3):246-251.

[5] Zhang X, Ru Y. Fault prediction of railway track circuit based on machine learning [J]. International Journal of Sensor Networks, 2024, 45(4): 216-228.

[6] Kumar S. Rail Defect Measurement System: Integrating AI and IoT for Predictive Operations [J]. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 2021, 2(2): 39-50.

[7] LIN Wo-Chi. Fault prediction and maintenance of rail transportation based on artificial intelligence [J]. People's Public Transportation, 2025(6):160-162.

[8] HONG Xu, CHEN Meixia, SHI Jin. Research on the prediction model of axle solid failure in rail transit vehicles [J]. Urban Rail Transportation Research, 2024, 27(5):171-174.

[9] LI Jianwei, GUO Pan, MA Junjie. Failure prediction model of gear reducer for mining equipment [J]. Metal Mining, 2025(3):175-180.

[10] JIANG Shanghang, GUANG Guoqing, ZHU Jianming, HUANG Jun. CatBoost-based fault prediction model for power grid equipment under severe weather [J]. Safety and Environmental Engineering, 2025, 32(2):133-142.

[11] Zhang J, Xiang A, Cheng Y, et al. Research on Detection of Floating Objects in River and Lake Based on AI Image Recognition [J]. Journal of Artificial Intelligence Practice, 2024, 7(2): 97-106.