To address the issues in identifying the radial tire load of straddle-type monorail vehicles - such as the high cost and complexity of direct measurement methods, and the poor stability, large computational load, and insufficient accuracy of physics-based models, a vehicle dynamic model is established. The model balances the rationality of physical relationships and the convenience of measurements. Vehicle posture information, including body and frame vibration acceleration that can be obtained via observability decomposition, and easily measurable parameters like displacement, rotation angle, and angular velocity, are selected to construct a dataset and validate the accuracy of the dynamic model. During dataset preprocessing, noise is added to enhance the data robustness, normalization is performed to facilitate data calculation, and time step expansion is carried out to strengthen the temporal correlation of the data. Based on this, a tire radial load identification model is built using a deep neural network consisting of a 1D convolutional neural network (1DCNN) and a bidirectional gated recurrent unit (BiGRU) in a serial architecture. The Hyperband algorithm is employed to optimize the hyperparameters of the model. By setting optimal learning rates, batch sizes, and optimizer types, and planning the data dimensions of each layer with appropriate convolutional kernel sizes and the number of GRU units, pointwise and dilated convolutions are introduced into the 1DCNN to improve model identification performance. The model's load identification performance is evaluated from the perspectives of accuracy, robustness, and generalization. The results show that, compared to traditional models, the 1DCNN-BiGRU-based load identification model achieves a root mean square error lower than 0.106 with higher accuracy. The model still maintains good recognition performance under noise conditions with a signal-to-noise ratio as low as 27 dB, demonstrating strong robustness. Furthermore, under varying operational conditions, such as different curve radii, cant deficiency, and inertia parameter perturbations, the model maintains good recognition performance, demonstrating excellent generalization.
CRRCPuzhen Alstom Transportation Systems Limited, Tongji University, Anhui Zhongkemi Point Sensor Co., Ltd. A Six-Component Force Sensor and Its Manufacturing Technology: CN, 202310185491.0 [P]. 2023-05-30. in Chinese)
[3]
BARTLETTF D, FLANNELLYW G. Model Verification of Force Determination for Measuring Vibratory Loads [J].Journal of the American Helicopter Society, 1979, 24 (2): 10-18.
[4]
JIAY, YANGZ C, LIUE Q, et al. Prediction of Random Dynamic Loads Using Second-Order Blind Source Identification Algorithm [J].Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2020, 234 (9): 1720-1732.
[5]
DESANGHEREG, SNOEYSR. Indirect Identification of Excitation Forces by Modal Coordinate Transformation [C]// Proceedings of 3rd IMAC. Bethel: Society for Experimental Mechanics, 1985: 685-690.
[6]
LIM Q, WANGL J, LUOC S, et al. A New Improved Fractional Tikhonov Regularization Method for Moving Force Identification [J]. Structures, 2024, 60: 105840.
[7]
DOYLEJ F. A Wavelet Deconvolution Method for Impact Force Identification [J]. Experimental Mechanics, 1997, 37 (4): 403-408.
[8]
WANGLei, XUHanying, LIUYaru. A Novel Dynamic Load Identification Approach for Multi-Source Uncertain Structures Based on the Set-Theoretical Wavelet Transform and Layered Noise Reduction [J]. Structures, 2023, 51: 91-104.
[9]
MASRIS F, CHASSIAKOSA G, CAUGHEYT K. Identification of Nonlinear Dynamic Systems Using Neural Networks [J]. Journal of Applied Mechanics, 1993, 60 (1): 123-133.
GUOJianfeng, WANGWeidong, LIUJinzhao, et al. Study on Prediction of Wheel-Rail Forces Based on ELM [J]. Railway Engineering, 2014, (4): 114-117. in Chinese
GUOJianfeng, KEZaitian, LIUJinzhao, et al. Identification of Railway Pantograph-Catenary Contact Force Based on Data Modeling [J]. China Railway Science, 2021, 42 (4): 145-154. in Chinese
ZENGJunwei, JIYuanjin, RENLihui, et al. Radial Load Identification Method of APM Vehicle Tires Based on 1D CNN and BiGRU [J]. China Mechanical Engineering, 2023, 34 (3): 359-368. in Chinese
CAOShuqian, ZHANGWende, XIAOLongxiang. Theoretical Experiment and Application of Modal Analysis of Vibration Structures [M]. 2nd ed. Tianjin: Tianjin University Press, 2014. in Chinese
[18]
刘豹,唐万生. 现代控制理论[M]. 3版. 北京:机械工业出版社,2006.
[19]
LIUBao, TANGWansheng. Modern Control Theory [M]. 3rd ed. Beijing: China Machine Press, 2006. in Chinese
[20]
KESKARN S, MUDIGERED, NOCEDALJ, et al. On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima [J/OL]. Ithaca: arXiv, (2017-02-09) [2023-12-25]. arxiv.org/abs/1609.04836.
[21]
LISHAL, KEVINJ, GIULIAD, et al. Hyperband: a Novel Bandit-Based Approach to Hyperparameter Optimization [J]. Journal of Machine Learning Research, 2016, 18: 1-52.
ZHANGRang, RENLihui, JIYuanjin. Critical Lateral Force and Curve Speed Limit of Straddle Type Monorail Vehicle [J]. Journal of the China Railway Society, 2020, 42 (2): 50-56. in Chinese