LIU Qingjie,CHEN Yanwen,LIU Boliang,CHENG Gong,FENG Qingsong,LUO Xinwei,QIAN Dingwei

• 1:State Key Laboratory of Safety and Resilience of Civil Engineering in Mountain Area
• 2: East China Jiaotong University
• 3:Guangzhou Metro Design & Research Institute Co.
• 4: Ltd.

摘要(Abstract)：

To develop a fast and accurate data-driven framework for predicting environmental vibration during the planning and design stages of urban rail transit lines, a large dataset of measured vibration responses from an operating metro system is processed through systematic data cleaning and feature extraction to construct an environmental vibration database. The vibration source intensity is predicted using a neural network-based model driven by processed rail vibration data. The predicted source intensity is subsequently combined with a standardized chain calculation method specified in the technical guidelines for environmental impact assessment to estimate ground vibration levels. On this basis, a digital vibration mapping approach is developed to translate prediction results into a spatially explicit form. Through coordinate transformation, key parameters influencing environmental vibration, such as train speed, slope, buried depth, and tunnel type, are mapped onto the geographic coordinates of the rail alignment, enabling visualization of vibration levels and functional zones along the study section. The resulting vibration maps of source intensity and ground vibration demonstrate the applicability of the proposed framework for efficient and practical environmental vibration assessment.

关键词(KeyWords)：

Abstract:

Keywords:

基金项目(Foundation): supported by the Railway Basic Research Joint Fund of the National Natural Science Foundation of China and China State Railway Group Co.,Ltd.(U2468226)

作者(Author): LIU Qingjie,CHEN Yanwen,LIU Boliang,CHENG Gong,FENG Qingsong,LUO Xinwei,QIAN Dingwei

参考文献(References)：

• [1] Hou X F, Feng C, Yan H M, et al. Overview of urban rail transit operations in 2024. Urban Rapid Rail Transit, 2025, 38(1):13–19(in Chinese)
• [2] Sun X J, Ma M, Jiang B L, et al. Ground vibration from freight railway:environmental impact and potential mitigation measure at propagation path. Environ. Sci. Pollut. Res., 2022, 29(29):1–14
• [3] Sun X J, Liu W N, Guo J P, et al. Vibration impact on sensitive instrument and equipment due to metro train and its reduction measures. China Saf. Sci. J., 2005(11):78–81(in Chinese)
• [4] Ma M, Markine V, Liu W N, et al. Metro train-induced vibrations on historic buildings in Chengdu, China. J. Zhejiang Univ. Sci. A, 2011,12(10):782–793
• [5] Kurzweil L G. Ground-borne noise and vibration from underground rail systems. J. Sound Vib., 1979, 66(3):363–370
• [6] Wu Z Z. Transfer function prediction methods for environmental influence of metro train-induced vibrations. Doctoral dissertation, Beijing:Beijing Jiaotong University, 2016(in Chinese)
• [7] Lei X Y, Chen S S. Space dynamic analyses for track structure of high speed railway. J. China Railw. Soc., 2000, 5:76–80(in Chinese)
• [8] Lei X Y, Sheng X Z. Advanced studies in modern track theory.Beijing:China Railway Publishing House, 2006(in Chinese)
• [9] Lei X Y. Progress in the development of track dynamic models and associated numerical methods. J. East China Jiaotong Univ., 2011,28(3):1–12(in Chinese)
• [10] Feng Q S, Lei X Y, Lian S L. Vibration analysis of high-speed railway subgrade-ground system. J. Railw. Sci. Eng., 2010, 7(1):1–6(in Chinese)
• [11] Zhai W M, He Z X, Song X L. Prediction of high-speed train induced ground vibration based on train-track-ground system model.Earthq. Eng. Eng. Vib., 2010, 9(4):545–554
• [12] Sheng X Z, Jones C J C, Thompson J D. Modelling ground vibration from railways using wavenumber finite-and boundaryelement methods. Proc. R. Soc. A, 2005, 461(2059):2043–2070
• [13] Elkordy M F, Chang K C, Lee G C. A Structural damage neural network monitoring system. Comput.-Aided Civ. Infrastruct. Eng.,2010, 9(2):83–96
• [14] Yao J B, Xia H, Zhang N, et al. Prediction on building vibration induced by moving train based on support vector machine and wavelet analysis. J. Mech. Sci. Technol., 2014, 28(6):2065–2074
• [15] Yao J B, Yao B Z, Du Y W, et al. Train-induced vibration prediction in multi-story buildings using support vector machine. Neural Netw. World, 2014, 24(1):89–102
• [16] Wang X L, Pan L, Peng G L, et al. The subway vibration forecast analysis based on RBF neural network. J. Tianjin Chengjian Univ.,2016, 22(6):465–470(in Chinese)
• [17] Paneiro G, Dur??o O F, Silva E C M, et al. Artificial neural network model for ground vibration amplitudes prediction due to light railway traffic in urban areas. Neural Comput. Appl., 2018, 29(11):1045–1057
• [18] Liang R H, Liu W F, Ma M, et al. An efficient model for predicting the train-induced ground-borne vibration and uncertainty quantification based on Bayesian neural network. J. Sound Vib., 2020, 495:115908
• [19] Mao J F, Li Z, Wu J, et al. Predicting random vibration response of heavy-haul train-track-bridge system based on PSOLSTM. J. Railw. Sci. Eng., 2024, 21(9):3661–3671(in Chinese)
• [20] He W, Niu D S, Song S Q. Prediction method of subway vibration source based on measured data-driven MLP neural network.J. Vib. Eng., 2026, 39(3):783–791(in Chinese)
• [21] Wang W N, Wu K, Chen R L, et al. Comprehensive evaluation of building damage in mining area based on GIS and random forest. Coal Sci. Technol., 2022, 50(3):201–207(in Chinese)
• [22] Liu Q J, Liu B L, Feng Q S, et al. Prediction model of vibration source intensity of urban rail underground line based on SSA-GA-BP neural network. J. Railw. Sci. Eng., 2025, 22(5):2355–2366(in Chinese)
• [23] National Environmental Protection Standards of the People’s Republic of China. Technical Guidelines for Environmental Impact Assessment—Urban Rail Transit:HJ 453–2018. Beijing:China Environmental Science Press, 2018(in Chinese)