Page 172 - 《振动工程学报》2026年第5期

1376 振 动 工 程 学 报 第 39 卷

LU Fang，WANG Liyu，QIAO Yingli，et al. Research on [13] LI M W，LYU G C，WANG X D，et al. High-speed maglev
application difficulties of ultra-high speed maglev rail transit train suspension gap prediction based on CNN-AGCRN[C]//
above 600 km/h[J]. China Transportation Review， 2023， Proceedings of 5th International Conference on Machine
45（5）：17-21. Learning and Computer Application (ICMLCA). Hangzhou：
[4] NI F， LUO Y F， XU J Q， et al. Review of fault-tolerant IEEE，2024：425-430.
control methods for suspension systems：from road vehicles [14] WANG C F，ZHENG J W，WU C，et al. Suspension gap
to maglev trains[J]. Mathematics，2024，12（16）：2576. prediction of high-speed maglev train based on Mcon-
[5] 余志武，张鹏，丁叁叁. 轨道梁参数随机的磁悬浮列车- vTimeNet[C]// Proceedings of 8th International Conference on
轨 道 梁 系 统 概 率 密 度 演 化 分析 [J]. 铁 道 学 报 ， 2023， Electrical, Mechanical and Computer Engineering (ICEMCE).
45（12）：138-147. Xi’an：IEEE，2024：1987-1991.
YU Zhiwu， ZHANG Peng， DING Sansan. Probability [15] NI F， DAI Y W， ZHENG Q H， et al. Physics-informed
density evolution analysis of maglev train-guideway system machine learning for robust inverse problem solving in maglev
with random guideway parameters[J]. Journal of the China train levitation systems under noisy measurement [J]. Nonlin-
Railway Society，2023，45（12）：138-147. ear Dynamics，2025, 113(20)：26981-26999.
[6] 卜秀孟，王力东，黎清蓉，等. 高速磁浮车-桥耦合振动控 [16] HAN P C，XU J Q，RONG L J，et al. Data-driven control
制参数影响分析 [J]. 西南交通大学学报，2024，59（4）： method based on Koopman operator for suspension system of
848-857. maglev train[J]. Actuators，2024，13（10）：397.
BU Xiumeng， WANG Lidong， LI Qingrong， et al. Influ- [17] CHEN C，XU J Q，LIN G B，et al. Model identification and
ence analysis of vibration control parameters for high-speed nonlinear adaptive control of suspension system of high-speed
maglev train-bridge coupling[J]. Journal of Southwest Jiao- maglev train[J]. Vehicle System Dynamics， 2022， 60（ 3） ：
tong University，2024，59（4）：848-857. 884-905.
[7] 龙志强，窦峰山，王志强，等. 高速磁浮悬浮导向控制技 [18] SALINAS-CAMUS M， GOEBEL K， ELEFTHEROGLOU
术现状及展望 [J]. 前瞻科技，2023，2（4）：78-88. N. A comprehensive review and evaluation framework for
LONG Zhiqiang，DOU Fengshan，WANG Zhiqiang，et al. data-driven prognostics： uncertainty， robustness， inter-
Current status and prospects of high-speed maglev suspension pretability，and feasibility[J]. Mechanical Systems and Signal
and guidance control technology[J]. Science and Technology Processing，2025，237：113015.
Foresight，2023，2（4）：78-88. [19] WU W，DANEKER M，JOLLEY M A，et al. Effective data
[8] 谢义染. 轨道不平顺高速磁浮列车的复合抗干扰控制研究 sampling strategies and boundary condition constraints of
[D]. 北京：北京交通大学，2024. physics-informed neural networks for identifying material
XIE Yiran. Research on composite anti-disturbance control of properties in solid mechanics[J]. Applied Mathematics and
high-speed maglev trains with track irregularities[D]. Beijing ： Mechanics (English Edition)，2023，44（7）：1039-1068.
Beijing Jiaotong University，2024. [20] DE O TELOLI R， TITTARELLI R， BIGOT M， et al. A
[9] 倪菲，范琳，徐俊起，等. 基于 Sobol’法的高速磁浮列车 physics-informed neural networks framework for model
单点悬浮系统全局灵敏度分析 [J]. 西南交通大学学报， parameter identification of beam-like structures[J]. Mechani-
2025，60（4）：812-822. cal Systems and Signal Processing，2025，224：112189.
NI Fei，FAN Lin，XU Junqi，et al. Global sensitivity analy- [21] HE J L，TIAMIYU A T. Physics-informed neural networks in
sis of single-point levitation system for high-speed maglev iterative form of nonlinear equations for numerical algorithms
train based on Sobol’ method[J]. Journal of Southwest Jiao- and simulations of delay differential equations[J]. Physica A：
tong University，2025，60（4）：812-822. Statistical Mechanics and its Applications， 2025， 660：
[10] 吴晗，刘梦娟，曾晓辉. 高速磁浮列车悬浮间隙仿真预测 130368.
[J]. 同济大学学报（自然科学版），2023，51（3）：351-359. [22] WEI Z， CHEN X D. Uncertainty quantification in inverse
WU Han，LIU Mengjuan，ZENG Xiaohui. Suspension gap scattering problems with Bayesian convolutional neural
prediction of highspeed maglev train[J]. Journal of Tongji networks[J]. IEEE Transactions on Antennas and Propaga-
University（Natural Science），2023，51（3）：351-359. tion，2021，69（6）：3409-3418.
[11] HAN Y R，YAO X M，YANG Y. Disturbance rejection tube [23] LAN S W， LI S Y， SHAHBABA B. Scaling up Bayesian
model predictive levitation control of maglev trains[J]. High- uncertainty quantification for inverse problems using deep
speed Railway，2024，2（1）：57-63. neural networks[J]. SIAM/ASA Journal on Uncertainty Quan-
[12] HU W J，ZHOU Y H，ZHANG Z L，et al. Model predic- tification，2022，10（4）：1684-1713.
tive control for hybrid levitation systems of maglev trains with [24] XIE Z Y，YASEEN M，WU X. Functional PCA and deep
state constraints[J]. IEEE Transactions on Vehicular Technol- neural networks-based Bayesian inverse uncertainty quantifi-
ogy，2021，70（10）：9972-9985. cation with transient experimental data[J]. Computer Methods