Prediction of dynamic characteristics for an air spring with an airbag based on physics-data hybrid model under large amplitude excitation

Wu QIN, Xundong LIAO, Licheng XU, Feifei LIU, Gang LI, Shoulong ZHANG, Pengfei HAN

Journal of Tsinghua University(Science and Technology) ›› 2026, Vol. 66 ›› Issue (8) : 1575-1586.

PDF(2428 KB)
PDF(2428 KB)
Journal of Tsinghua University(Science and Technology) ›› 2026, Vol. 66 ›› Issue (8) : 1575-1586. DOI: 10.16511/j.cnki.qhdxxb.2026.28.010
Vehicle and Traffic

Prediction of dynamic characteristics for an air spring with an airbag based on physics-data hybrid model under large amplitude excitation

Author information +
History +

Abstract

Objective: The air spring with an auxiliary airbag (ASAA) is a novel dual-chamber throttling tube air spring featuring a lightweight design, with low cost and flexible installation layout. Different from conventional air springs with constant-volume auxiliary chambers, the ASAA employs an elastic airbag whose volume varies with internal pressure, enabling a wide adjustable range of stiffness and damping. Because of this structural feature, the ASAA exhibits strong adaptability across diverse operating conditions and shows great potential in intelligent air suspension systems. However, under large-amplitude excitation, the coupled nonlinear effects of airbag expansion, the complex viscoelastic behavior of the rubber bladder, and turbulent airflow within the throttling tube lead to highly nonlinear dynamic characteristics. These strong nonlinearities drastically limit the prediction accuracy of traditional physical models. To address this problem, a physics-data hybrid modeling approach is proposed to enhance the prediction accuracy of dynamic stiffness and lag angle under large-amplitude conditions. Methods: A simplified physical model of the ASAA was developed based on the thermodynamic theory, flow resistance analysis of the throttling tube, and viscoelastic modeling of the rubber bladder. For the compressed air part, governing equations were derived under adiabatic assumptions. The nonlinear airbag volume variation term, which is difficult to linearize, was simplified to reduce model complexity, whereas the nonlinear airflow term in the throttling tube was linearized using a first-order Fourier series expansion. The rubber bladder was modeled by combining a Coulomb friction model, which captured amplitude-dependent hysteresis, and a fractional-order Kelvin-Voigt model, which reproduced frequency-dependent viscoelastic effects. Static and dynamic experiments were conducted to identify the key structural parameters. Dynamic experiments were further carried out at excitation frequencies ranging from 0 to 6 Hz and amplitudes ranging from 5 to 40 mm to obtain the experimental data on dynamic stiffness and lag angle. A deep neural network (DNN) was subsequently constructed to learn the residual errors between the experimental measurements and the physical model calculations. Excitation frequency and amplitude were used as input features, and the corresponding errors in dynamic stiffness and lag angle were taken as output targets. The DNN had two hidden layers with rectified linear unit activation and dropout regularization and is trained using the Adam optimization algorithm on normalized datasets to ensure convergence stability and generalization capability. Results: Validation results demonstrated that the proposed physics-data hybrid model considerably improved the prediction performance, particularly under large-amplitude excitation. In the test cases with excitation amplitudes of 35 mm and 40 mm, which were not included in the training dataset, the hybrid model demonstrated strong generalization ability. For these test cases, the maximum relative errors of dynamic stiffness prediction reduced to approximately 3.22% and 3.98%, respectively, representing an improvement of approximately 6% compared with the conventional physical model. For lag angle prediction, the maximum relative errors were 17.21% and 15.83%, respectively, corresponding to an error reduction of approximately 35% compared with the conventional physical model. Although lag angle prediction remains more sensitive because of its small baseline value and the strong nonlinear stiffness-damping correlation, the hybrid model effectively captures the overall variation trend and achieves substantially improved accuracy. Conclusions: By integrating physics-based modeling with machine learning-based residual compensation, the proposed hybrid approach effectively overcomes the limitations of simplified physical models in describing strong nonlinear behavior. The method substantially enhances the prediction accuracy of dynamic stiffness and lag angle under highly nonlinear, large-amplitude conditions, providing theoretical support and practical guidance for the design and dynamic modeling of intelligent air suspension systems.

Key words

air spring / expansion work / dynamic characteristics / machine learning

Cite this article

Download Citations
Wu QIN , Xundong LIAO , Licheng XU , et al . Prediction of dynamic characteristics for an air spring with an airbag based on physics-data hybrid model under large amplitude excitation[J]. Journal of Tsinghua University(Science and Technology). 2026, 66(8): 1575-1586 https://doi.org/10.16511/j.cnki.qhdxxb.2026.28.010

References

1
MA C Y, LU Y K, ZHEN R, et al. On-the-market air suspension systems for passenger cars[J]. SAE International Journal of Vehicle Dynamics, Stability, and NVH, 2025, 9(2): 299- 313.
2
廖林清, 张君, 程美娥, 等. 变载荷空气悬架固有频率的控制研究[J]. 机械设计与制造, 2017(7): 86- 90.
LIAO L Q, ZHANG J, CHENG M E, et al. The research on controlling natural frequency of variable load air suspension[J]. Machinery Design & Manufacture, 2017(7): 86- 90.
3
周恩临, 何梦圆, 赵启航, 等. 宽温域乘用车空气弹簧动力学建模与控制[J]. 汽车工程, 2024, 46(8): 1489- 1500.
ZHOU E L, HE M Y, ZHAO Q H, et al. Modeling and control of air spring dynamics in wide temperature range passenger vehicle[J]. Automotive Engineering, 2024, 46(8): 1489- 1500.
4
LIU H, LEE J C. Model development and experimental research on an air spring with auxiliary reservoir[J]. International Journal of Automotive Technology, 2011, 12(6): 839- 847.
5
ODA N, NISHIMURA S. Vibration of air suspension bogies and their design[J]. Bulletin of JSME, 1970, 13(55): 43- 50.
6
EICKHOFF B M, EVANS J R, MINNIS A J. A review of modelling methods for railway vehicle suspension components[J]. Vehicle System Dynamics, 1995, 24(6–7): 469- 496.
7
BERG M. A three-dimensional airspring model with friction and orifice damping[J]. Vehicle System Dynamics, 1999, 33(S1): 528- 539.
8
QUAGLIA G, SORLI M. Air suspension dimensionless analysis and design procedure[J]. Vehicle System Dynamics, 2001, 35(6): 443- 475.
9
DOCQUIER N, FISETTE P, JEANMART H. Multiphysic modelling of railway vehicles equipped with pneumatic suspensions[J]. Vehicle System Dynamics, 2007, 45(6): 505- 524.
10
郑益谦, 上官文斌. 管路型带附加气室空气弹簧的时域动态特性建模[J]. 振动工程学报, 2023, 36(6): 1539- 1545.
ZHENG Y Q, SHANGGUAN W B. Modeling of time-domain dynamic characteristics of a pipe-type air spring with an auxiliary chamber[J]. Journal of Vibration Engineering, 2023, 36(6): 1539- 1545.
11
TOYOFUKU K, YAMADA C, KAGAWA T, et al. Study on dynamic characteristic analysis of air spring with auxiliary chamber[J]. JSAE Review, 1999, 20(3): 349- 355.
12
YIN Z H, JIANG J, SHANGGUAN W B. Complex stiffness model of an air spring with auxiliary chamber considering inertial effects of gas in connecting pipeline[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2023, 237(1): 145- 158.
13
王家胜, 朱思洪. 带附加气室空气弹簧动刚度影响因素试验研究[J]. 振动与冲击, 2010, 29(6): 1–3, 20.
WANG J S, ZHU S H. Experimental study on influential factors on dynamic stiffness of air spring with auxiliary chamber[J]. Journal of Vibration and Shock, 2010, 29(6): 1–3, 20.
14
陈耿彪, 刘志文, 尹来容, 等. 半主动三附气室空气弹簧吸振器特性分析[J]. 机械工程学报, 2024, 60(17): 194- 207.
CHEN G B, LIU Z W, YIN L R, et al. Characteristic analysis of semi-active triple-auxiliary-chambers air spring vibration absorber[J]. Journal of Mechanical Engineering, 2024, 60(17): 194- 207.
15
LI G, ZHONG L, SUN W J, et al. A variable horizon model predictive control for magnetorheological semi-active suspension with air springs[J]. Sensors, 2024, 24(21): 6926.
16
QIN W, PAN J C, GE P Z, et al. Dynamic characteristics modeling and optimization for hydraulic engine mounts based on deep neural network coupled with genetic algorithm[J]. Engineering Applications of Artificial Intelligence, 2024, 130, 107683.
17
韩愈琪, 刘雪莱, 上官文斌. 基于本构神经网络橡胶隔振器动态特性建模[J]. 噪声与振动控制, 2023, 43(3): 265- 270.
HAN Y Q, LIU X L, SHANGGUAN W B. Modeling of dynamic behaviors of rubber isolators using constitutive model and BP neural network model[J]. Noise and Vibration Control, 2023, 43(3): 265- 270.
18
ZHENG Y Q, SHANGGUAN W B, YIN Z H, et al. A hybrid modeling approach for automotive vibration isolation mounts and shock absorbers[J]. Nonlinear Dynamics, 2023, 111(17): 15911- 15932.
19
VO N Y P, NGUYEN M K, LE T D. Analytical study of a pneumatic vibration isolation platform featuring adjustable stiffness[J]. Communications in Nonlinear Science and Numerical Simulation, 2021, 98, 105775.
20
陈俊杰, 徐进嫄, 沈钰杰, 等. 空气弹簧内部压缩气体热迟滞等效力学模型[J]. 汽车工程, 2024, 46(7): 1294- 1301.
CHEN J J, XU J Y, SHEN Y J, et al. Thermal hysteresis equivalent mechanical model of compressed air inside air springs[J]. Automotive Engineering, 2024, 46(7): 1294- 1301.
21
ZHU H J, YANG J, ZHANG Y Q, et al. Nonlinear dynamic model of air spring with a damper for vehicle ride comfort[J]. Nonlinear Dynamics, 2017, 89(2): 1545- 1568.
22
陈俊杰, 殷智宏, 何江华, 等. 带节流阻尼孔和附加气室的空气弹簧系统建模和动态特性研究[J]. 机械工程学报, 2017, 53(8): 166- 174.
CHEN J J, YIN Z H, HE J H, et al. Study on modelling and dynamic characteristic of air spring with throttling damping orifice and auxiliary chamber[J]. Journal of Mechanical Engineering, 2017, 53(8): 166- 174.
23
WU M Y, HOU J, TONG H, et al. A universal dynamical model of dual-chamber air springs with experimental validation[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2023, 237(10–11): 2553- 2564.
24
FACCHINETTI A, MAZZOLA L, ALFI S, et al. Mathematical modelling of the secondary airspring suspension in railway vehicles and its effect on safety and ride comfort[J]. Vehicle System Dynamics, 2010, 48(S1): 429- 449.
25
ZHU H J, YANG J, ZHANG Y Q, et al. A novel air spring dynamic model with pneumatic thermodynamics, effective friction and viscoelastic damping[J]. Journal of Sound and Vibration, 2017, 408, 87- 104.
26
秦武, 廖迅东, 胡红成, 等. 双管双腔室空气弹簧动态特性优化设计[J]. 振动与冲击, 2025, 44(21): 54- 63.
QIN W, LIAO X D, HU H C, et al. Optimization design of dynamic characteristics of dual-tube dual-chamber air spring[J]. Journal of Vibration and Shock, 2025, 44(21): 54- 63.
27
LEE J H, KIM K J. Modeling of nonlinear complex stiffness of dual-chamber pneumatic spring for precision vibration isolations[J]. Journal of Sound and Vibration, 2007, 301(3–5): 909- 926.
28
WHITE F M. Fluid mechanics[M]. 7th ed New York: McGraw-Hill, 2011.
29
龙天渝, 蔡增基. 流体力学[M]. 3版 北京: 中国建筑工业出版社, 2019.
LONG T Y, CAI Z J. Fluid mechanics[M]. 3rd ed Beijing: China Architecture & Building Press, 2019.
30
杨树军, 刘泓江, 陈俊杰, 等. 变压强工况下膜式空气弹簧橡胶气囊迟滞力学特性统一模型研究[J]. 机械工程学报, 2024, 60(16): 241- 248.
YANG S J, LIU H J, CHEN J J, et al. Research on unified model of hysteretic mechanical characteristic of rubber bellows for rolling lobe air spring under variable pressure working conditions[J]. Journal of Mechanical Engineering, 2024, 60(16): 241- 248.
31
陈琨, 王安志. 卷积神经网络的正则化方法综述[J]. 计算机应用研究, 2024, 41(4): 961- 969.
CHEN K, WANG A Z. Survey on regularization methods for convolutional neural network[J]. Application Research of Computers, 2024, 41(4): 961- 969.

RIGHTS & PERMISSIONS

All rights reserved. Unauthorized reproduction is prohibited.
PDF(2428 KB)

Accesses

Citation

Detail

Sections
Recommended

/