During the construction of railway tunnel by drilling and blasting method, the machinery and equipment run in the harsh environment of high load, high dust and high humidity for a long time, and the equipment fails frequently, which seriously affects the construction progress and safety. Traditional methods of periodic maintenance and passive fault repair have been difficult to meet the needs of modern tunnel engineering. This paper presents a machine learning method to predict and manage the fault of railway tunnel construction machinery and equipment by drilling and blasting method. The system collects equipment operation data in real time through sensors, preprocesses it by means of data cleaning, feature extraction, etc., and performs fault prediction and health status assessment through decision tree and other machine learning algorithms. This paper describes the system architecture design, data processing flow, model selection and training methods. The system can predict potential mechanical failures in advance, reduce unplanned downtime, and improve equipment reliability and overall efficiency of tunnel construction. The fault prediction system aided by machine learning can not only reduce the failure rate of equipment, but also provide accurate health assessment and early warning mechanism, which has a wide range of engineering applications.

Jinshuo Zhang. Research on Fault Prediction and Health Management System of Railway Tunnel Drilling and Blasting Construction Machinery Based on Machine Learning. International Journal of New Developments in Engineering and Society (2024) Vol.8, Issue 5: 70-75. https://doi.org/10.25236/IJNDES.2024.080511.

[1] Ma Weiguyu, Wang Bo, He Chuan, etc. Intelligent design of mechanized drilling and Blasting tunnel based on large sample numerical simulation and machine learning algorithm [J]. Journal of applied foundation and engineering science, 2023 (6): 1601-1616. The DOI: 10.16058 / j.i SSN. 1005-0930.2023.06.016.

[2] Chen Guodong, Gan Mufei, Liu Ke. Key technology of mechanized construction design of railway tunnel by drilling and blasting [J]. Modern Tunnel Technology, 2022(002):059.

[3] Zhang Feilian, Wu Zhe, Wang Xiaolan, et al. Safety Risk assessment of Railway tunnel construction with drilling and Blasting method in complex and dangerous areas [J]. Journal of Railway Science and Engineering, 2023.

[4] Wang Qi. Research on perception method of overcut and Undercut under intelligent drilling and Blasting Construction of Railway tunnel [D]. Xi 'an University of Technology, 2024.

[5] Liu Y, Li A, Dai F, et al. An AI-powered approach to improving tunnel blast performance considering geological conditions[J].Tunnelling and underground space technology, 2024(Feb.):144.

[6] Widodo, Phanjaya H, Simon Heru PrassetyoGanda Marihot SimangunsongMade Astawa RaiRidho Kresna Wattimena. Dynamic Slope Stability Subject to Blasting Vibrations: a Case Study of the Jakarta-Bandung High-Speed Railway Tunnel[J]. Transportation infrastructure geotechnology, 2023, 10(5):774-794.

[7] Sun Jingna, Chen Peibin, Zeng Weihong, et al. Image annotation method, classification method and machine learning model training method [P]. CN202110862466.2 [2024-10-10].