Optimization of Metro Embedded Track Structure Based on PSO-BP and NSGA-II

doi:10.3901/JME.260826

Abstract

Abstract: Embedded tracks demonstrate superior dynamic characteristics and enhanced vehicle-track interaction performance compared to fastener-based tracks, providing them with excellent vibration reduction and noise mitigation effects. However, their complex structure imposes higher demands on design. Improper selection of structural parameters can significantly compromise the track’s dynamic performance and vibration reduction effects. To optimize the metro embedded track structure parameters, this study proposes an optimization method for metro embedded track structures based on the PSO-BP neural network and NSGA-II. A multi-objective optimization model is developed using nine structural parameters, including track slab length, track slab width, filler stiffness and damp, etc., as decision variables, and three dynamic performance indicators—rail vertical displacement, rail vertical acceleration, and track slab vertical displacement—as objective functions. A PSO-BP neural network-based prediction method is introduced to predict dynamic responses under different parameter settings, and NSGA-II is employed to optimize the model. Furthermore, the Sobol method is utilized to analyze the influence of various parameters on the dynamic performance of the embedded track. Results indicate that: (1) the PSO-BP neural network can accurately and efficiently predict the dynamic responses of embedded tracks, achieving an average accuracy of 97.15%; (2) after optimization, rail vertical displacement, rail vertical acceleration, and track slab vertical displacement are reduced by 20%, 18.7%, and 15.6%, respectively; (3) sensitivity analysis reveals that filler vertical stiffness, vertical damping, and track slab length are the key parameters influencing rail vertical displacement, rail vertical acceleration, and track slab vertical displacement, respectively. This research provides valuable references for the structural design of metro embedded tracks.

Key words: embedded track, PSO-BP neural network, multi objective optimization, NSGA-Ⅱ, Sobol sensitivity analysis

CLC Number:

U213

ZHANG Hong, DU Xiande, LIU Linya, ZHANG Pengfei, CHENG Gong, WANG Huaidong, WANG Wei. Optimization of Metro Embedded Track Structure Based on PSO-BP and NSGA-II[J]. Journal of Mechanical Engineering, 2026, 62(15): 183-194.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://www.cjmenet.com.cn/EN/10.3901/JME.260826

http://www.cjmenet.com.cn/EN/Y2026/V62/I15/183

References

[1] 韩健. 地铁列车-嵌入式轨道系统动力学性能及振动噪声特性研究[D]. 成都：西南交通大学，2018. HAN Jian. Research on the dynamic performance and vibration noise characteristics of subway train embedded track system[D]. Chengdu：Southwest Jiaotong University，2018.
[2] OOSTERMEIJER K H，KOK A W M. Dynamic behaviour of railway superstructures[J]. Heron，2000，45(1)：25-34.
[3] LING Liang，HAN Jian，XIAO Xinbiao，et al. Dynamic behavior of an embedded rail track coupled with a tram vehicle[J]. Journal of Vibration and Control，2017，23(14)：2355-2372.
[4] 房建，杨敏超，雷晓燕，等. 桥上CRTS II型板式无砟轨道参数对轨道结构振动响应的影响[J]. 铁道科学与工程学报，2022，19(8)：2125-2132. FANG Jian，YANG Minchao，LEI Xiaoyan，et al. Study on the impact of track parameters on the CRTS II slab track structure vibration characteristics on bridges[J]. Journal of Railway Science and Engineering，2022，19(8)：2125-2132.
[5] 邓永权. 有轨电车列车-嵌入式轨道动态相互作用研究[D]. 成都：西南交通大学，2014. DENG Yongquan. Study on dynamic interaction of tram train-embedded rail track[D]. Chengdu：Southwest Jiaotong University，2014.
[6] 莫宏愿. 嵌入式轨道结构几何参数优化研究[D]. 成都：西南交通大学，2015. MO Hongyuan. Research on geometric parameter optimization of embedded track structure[D]. Chengdu：Southwest Jiaotong University，2015.
[7] 胥燕军，林红松，王健，等. 现代有轨电车轨道结构关键参数研究[J]. 铁道建筑，2014(11)：174-177. XU Yanjun，LIN Hongsong，WANG Jian，et al. Study on key parameters of track structure of modern tram[J]. Railway Architecture，2014(11)：174-177.
[8] ZHAO Yue，LI Xusheng，LV Qiang，et al. Measuring modelling and optimising an embedded rail track[J]. Applied Acoustics，2017，116：70-81.
[9] 冯青松，孙魁，王威，等. 现代有轨电车嵌入式轨道复合地基优化分析[J]. 中国科学：技术科学，2018， 48(8)：872-880. FENG Qingsong，SUN Kui，WANG Wei，et al. Optimization analysis of modern tram embedded track composite foundation[J]. Scientia Sinica (Technologica)，2018，48(8)：872-880.
[10] 毕澜潇，刘卫星，邢梦婷，等. 嵌入式轨道槽内结构优化设计[J]. 西南交通大学学报，2019，54(6)：1227-1234. BI Lanxiao，LIU Weixing，XING Mengting，et al. Optimization design for Internal structure of embedded rail trough[J]. Journal of Southwest Jiaotong University，2019，54(6)：1227-1234.
[11] 刘占峰. 地铁用嵌入式轨道动力学性能分析与结构优化[D]. 成都：西南交通大学，2018. LIU Zhanfeng. Dynamic performance analysis and structural optimization of embedded rail for metro[D]. Chengdu：Southwest Jiaotong University，2018.
[12] 韩健，肖新标，杨刚，等. 地铁列车-嵌入式轨道系统动力学性能II：轨道参数对动力学性能影响[J]. 机械工程学报，2020，56(24)：173-180. HAN Jian，XIAO Xinbiao，YANG Gang，et al. Dynamic behaviour of metro train and embedded track system II：Effect of track parameters on dynamic behaviour[J]. Journal of Mechanical Engineering，2020，56(24)：173-180.
[13] 杨刚，何远鹏，韩健，等. 嵌入式轨道系统振动传递研究[J]. 城市轨道交通研究，2024，27(7)：197-203. YANG Gang，HE Yuanpeng，HAN Jian，et al. Research on embedded track system vibration transmission[J]. Urban Mass Transit，2024，27(7)：197-203.
[14] HAN Jian，ZHAO Guotang，WANG Ping，et al. Composite embedded track structure considering temperature dependent characteristics for rolling noise reduction of inter-city railway system[J]. Applied Acoustics，2024，219：109936.
[15] YANG Gang，HE Yuanpeng，HAN Jian，et al. Study on the non-linear vibration and impact characteristics of composite structure of embedded track[J]. Journal of Low Frequency Noise，Vibration and Active Control，2025，44(3)：1726-1745.
[16] 卢琪，苏凯新，张继旺，等. 基于BP神经网络和遗传算法的简单链型悬挂接触网结构优化[J]. 机械工程学报，2024，60(12)：313-320. LU Qi，SU Kaixin，ZHANG Jiwang，et al. Structural optimization of simple catenary based on BP neural network and genetic algorithm[J]. Journal of Mechanical Engineering，2024，60(12)：313-320.
[17] 王力东，付岱林，卜秀孟，等. 基于自适应代理模型的桥梁风屏障参数多目标优化方法[J/OL]. 工程力学，2024，41：1-11. DOI:10.6052/j.issn.1000-4750.2024. 02.0108. WANG Lidong，FU Dailin，BU Xiumeng，et al. Multi-objective optimization method for bridge wind barrier parameters based on adaptive surrogate model[J/OL]. Engineering Mechanics，2024，41：1-11. DOI:10.6052/j.issn.1000-4750.2024.02.0108.
[18] 中华人民共和国铁道部，TB 10716-2013高速铁路工程动态验收技术规范[S]. 北京：中国铁道出版社，2013. Ministry of Railways of the People's Republic of China，TB 10716-2013 Technical refulations for dynamic acceptance of high-speed railway construction[S]. Beijing：China Railway Press，2013.
[19] DEB K，PRATAP A，AGARWAL S，et al. A fast and elitist multi-objective genetic algorithm：NSGA-Ⅱ[J]. IEEE Transactions on Evolutionary Computation，2002，6(2)：182-197.
[20] 赵峰，胡伟飞，李光，等. 基于混合指标自适应采样代理模型的多目标优化设计方法[J]. 机械工程学报，2024，60(13)：81-91. ZHAO Feng，HU Weifei，LI Guang，et al. Multi-objective optimization design method based on a hybrid metric adaptive sampling surrogate model[J]. Journal of Mechanical Engineering，2024，60(13)：81-91.
[21] 石一凡，刘立龙，兰胜伟，等. 基于PSO-BP神经网络的中国区域大气加权平均温度模型[J]. 大地测量与地球动力学，2023，43(12)：1300-1306. SHI Yifan，LIU Lilong，LAN Shengwei，et al. An atmospheric weighted mean temperature model of China region based on PSO-BP neural network[J]. Journal of Geodesy and Geodynamics，2023，43(12)：1300-1306.
[22] 张玉平，马超，李传习，等. 基于改进BP算法的混凝土热学参数反演与预测[J]. 交通科学与工程，2022，37(1)：42-50. ZHANG Yuping，MA Cao，LI Chuanxi，et al. Back analysis and prediction of thermal parameters of concrete based on improved BP algorithm[J]. Journal of Transport Science and Engineering，2022，37(1)：42-50.
[23] FU Rongqiang，XU Tongwen，PAN Zhongxiao. Modelling of the adsorption of bovine serum albumin on porous polyethylene membrane by back-propagation artificial neural network[J]. Journal of Membrane Science，2005，251(1-2)：137-144.
[24] LI Mingshun，CHEN Wenchen. Application of BP neural network algorithm in sustainable development of highway construction projects[J]. Physics Procedia，2012，25：1212-1217.
[25] 杨易，高骏，谷正气，等. 基于GA-BP的汽车风振噪声声品质预测模型[J]. 机械工程学报，2021，57(24)：241-249. YANG Yi，GAO Jun，GU Zhengqi，et al. Research on sound quality prediction model of automobile wind buffeting noise based on GA-BP[J]. Journal of Mechanical Engineering，2021，57(24)：241-249.
[26] 张朝龙，赵筛筛，何怡刚. 基于信息熵与PSO-LSTM的锂电池组健康状态估计方法[J]. 机械工程学报，2022，58(10)：180-190. ZHANG Chaolong，ZHAO Shaishai，HE Yigang. State-of-health estimate for lithium-ion battery using Information entropy and PSO-LSTM[J]. Journal of Mechanical Engineering，2022，58(10)：180-190.
[27] 谭振超，成卫，许世春. 基于熵权的道路交通状态模糊综合评判模型[J]. 交通科学与工程，2017，33(3)：69-74. TAN Zhenchao，CHENG Wei，XU Shichun. A fuzzy comprehensive evaluation model for road traffic conditions based on entropy weight[J]. Journal of Transport Science and Engineering，2017，33(3)：69-74.
[28] SOBOL’ I M. On sensitivity estimation for nonlinear mathematical models[J]. Keldysh Applied Mathematics Institute，1990，2(1)：112–118.
[29] GAO Jie，CAO Xiaofei，XIAO Mi，et al. Rational designs of mechanical metamaterials: Formulations, architectures, tessellations and prospects[J]. Materials Science and Engineering: R：Reports，2023，156：100755.
[30] ZHANG Xiao，XIAO Mi，GAO Liang，et al. A T-splines-oriented isogeometric topology optimization for plate and shell structures with arbitrary geometries using Bézier extraction[J]. Computer Methods in Applied Mechanics and Engineering，2024，425：116929.